Publications

Talk by J. Weyler: Joint Plant Instance Detection and Leaf Count Estimation … (RAL+ICRA’21)
Talk by N. Chebrolu: Adaptive Robust Kernels for Non-Linear Least Squares Problems (RAL+ICRA’21)
Talk by A. Reinke: Simple But Effective Redundant Odometry for Autonomous Vehicles (ICRA’21)
Talk by X. Chen: Range Image-based LiDAR Localization for Autonomous Vehicles (ICRA’21)
Talk by I. Vizzo: Poisson Surface Reconstruction for LiDAR Odometry and Mapping (ICRA’21)
SIGSPATIAL’2020: A Time-Window Data-Structure for Spatial Density Maps (Annika Bonerath)
Talk by R. Sheikh on Gradient and Log-based Active Learning for Semantic Segmentation… (ICRA’20)
Talk by J. Quenzel on Beyond Photometric Consistency: Gradient-based Dissimilarity for VO (ICRA’20)
Talk by L. Nardi on Long-Term Robot Navigation in Indoor Environments… (ICRA’20)
Talk by X. Chen on OverlapNet – Loop Closing for LiDAR-based SLAM (RSS’20)
DIGICROP’20: Spatio-Temporal Registration of Plant Point Clouds by Chebrolu et al.
IROS’20: Segmentation-Based 4D Registration of Plants Point Clouds for Phenotyping by Magistri et al
Talk by D. Gogoll: Unsupervised Domain Adaptation for Transferring Plant Classification…(IROS’20)
IROS’20: LiDAR Panoptic Segmentation for Autonomous Driving presented by J. Behley
IROS’20: Learning an Overlap-based Observation Model for 3D LiDAR Localization by Chen et al.
IROS’20: Domain Transfer for Semantic Segmentation of LiDAR Data using DNNs presented by J. Behley
Deep Learning for Non-Invasive Diagnosis of Nutrient Deficiencies in Sugar Beet Using RGB Images
RSS 2020′: LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices
EuroCG’2020: Tight Rectilinear Hulls of Simple Polygons
SIGSPATIAL’2019: Retrieving alpha-Shapes and Schematic Polygonal Approximations for Sets of Points..
ICRA’2020: Visual Servoing-based Navigation for Monitoring Row-Crop Fields
IROS’18: Joint Stem Detection and Crop-Weed Classification for Plant-specific Treatment
RAL’18: FCNs with Sequential Information for Robust Crop and Weed Detection by Lottes et al.
RAL-ICRA’19: Effective Visual Place Recognition Using Multi-Sequence Maps by Vysotska & Stachniss
ICRA’19: Actively Improving Robot Navigation On Different Terrains Using GPMMs by Nardi et al.
ICRA’19: Robot Localization Based on Aerial Images for Precision Agriculture by Chebrolu et al.

2021

  • A. T. Leite-Filho, B. S. Soares-Filho, J. L. Davis, G. M. Abrahão, and J. Börner, “Deforestation reduces rainfall and agricultural revenues in the Brazilian Amazon,” Nature Communications, vol. 12, iss. 1, p. 2591, 2021. doi:10.1038/s41467-021-22840-7
    [BibTeX] [PDF]

    It has been suggested that rainfall in the Amazon decreases if forest loss exceeds some threshold, but the specific value of this threshold remains uncertain. Here, we investigate the relationship between historical deforestation and rainfall at different geographical scales across the Southern Brazilian Amazon (SBA). We also assess impacts of deforestation policy scenarios on the region’s agriculture. Forest loss of up to 55–60{\%} within 28 km grid cells enhances rainfall, but further deforestation reduces rainfall precipitously. This threshold is lower at larger scales (45–50{\%} at 56 km and 25–30{\%} at 112 km grid cells), while rainfall decreases linearly within 224 km grid cells. Widespread deforestation results in a hydrological and economic negative-sum game, because lower rainfall and agricultural productivity at larger scales outdo local gains. Under a weak governance scenario, SBA may lose 56{\%} of its forests by 2050. Reducing deforestation prevents agricultural losses in SBA up to US{\$} 1 billion annually.

    @article{312312312312,
    Abstract = {It has been suggested that rainfall in the Amazon decreases if forest loss exceeds some threshold, but the specific value of this threshold remains uncertain. Here, we investigate the relationship between historical deforestation and rainfall at different geographical scales across the Southern Brazilian Amazon (SBA). We also assess impacts of deforestation policy scenarios on the region's agriculture. Forest loss of up to 55--60{\%} within 28 km grid cells enhances rainfall, but further deforestation reduces rainfall precipitously. This threshold is lower at larger scales (45--50{\%} at 56 km and 25--30{\%} at 112 km grid cells), while rainfall decreases linearly within 224 km grid cells. Widespread deforestation results in a hydrological and economic negative-sum game, because lower rainfall and agricultural productivity at larger scales outdo local gains. Under a weak governance scenario, SBA may lose 56{\%} of its forests by 2050. Reducing deforestation prevents agricultural losses in SBA up to US{\$} 1 billion annually.},
    Author = {Leite-Filho, Argemiro Teixeira and Soares-Filho, Britaldo Silveira and Davis, Juliana Leroy and Abrah{\~a}o, Gabriel Medeiros and B{\"o}rner, Jan},
    Da = {2021/05/10},
    Date-Added = {2021-06-20 19:44:53 +0000},
    Date-Modified = {2021-06-20 19:44:53 +0000},
    Doi = {10.1038/s41467-021-22840-7},
    Id = {Leite-Filho2021},
    Isbn = {2041-1723},
    Journal = {Nature Communications},
    Number = {1},
    Pages = {2591},
    Title = {Deforestation reduces rainfall and agricultural revenues in the Brazilian Amazon},
    Ty = {JOUR},
    Url = {https://doi.org/10.1038/s41467-021-22840-7},
    Volume = {12},
    Year = {2021},
    }

  • D. Schulz, H. Yin, B. Tischbein, S. Verleysdonk, R. Adamou, and N. Kumar, “Land use mapping using Sentinel-1 and Sentinel-2 time series in a heterogeneous landscape in Niger, Sahel,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 178, pp. 97-111, 2021. doi:https://doi.org/10.1016/j.isprsjprs.2021.06.005
    [BibTeX] [PDF]

    Land use maps describe the spatial distribution of natural resources, cultural landscapes, and human settlements, serving as an important planning tool for decision makers. In the Sahel area, such information is valuable for risk management and mitigation in challenging sectors like food security, flood control, and urban planning. Due to its uniform quality across large areas in regular time steps, remote sensing imageries are essential input for producing land use maps. However, spatially and temporally heterogeneous landscapes in Sahel make classification of landscape features difficult. Our overall goal is to create an accurate, high resolution land use map covering Niamey, the capital of Niger and its surroundings which represents the unique landscape features in the Sahel using Sentinel-1 and Sentinel-2 archives. We assessed the performance of three commonly used classifiers (i.e. Maximum Likelihood (ML), Support Vector Machine (SVM) and Random Forest (RF)) for land use classification. To understand the utility of different features from Sentinel-1 and Sentinel-2 imagery for classification, we performed feature selection and compared mapping accuracies with and without feature selection. To leverage the strength of each classifier, we developed a classifier ensemble (CE) map based on the mapping accuracy of each land use class and each classifier. The results of this study showed that the performance of individual classifiers depends on feature selection method and accuracies can be improved by combining different classifiers. The ensemble map had an overall accuracy of 72+-3.9 percent and it was found superior in terms of accuracy particularly with respect to built-up areas compared to the existing global land cover products in the study area. Our classification scheme also better characterized the regional environment in the Sahel. For example, we mapped rice and bare rocks that have important regional implication, which are not included in the existing products. Overall, our approach highlights the potentiality of combining multi-modal imageries and multiple classifiers for mapping a heterogenous environment such as the Sahel with high spatial resolution.

    @article{SCHULZ202197,
    title = {Land use mapping using Sentinel-1 and Sentinel-2 time series in a heterogeneous landscape in Niger, Sahel},
    journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
    volume = {178},
    pages = {97-111},
    year = {2021},
    issn = {0924-2716},
    doi = {https://doi.org/10.1016/j.isprsjprs.2021.06.005},
    url = {https://www.sciencedirect.com/science/article/pii/S0924271621001635},
    author = {Dario Schulz and He Yin and Bernhard Tischbein and Sarah Verleysdonk and Rabani Adamou and Navneet Kumar},
    keywords = {Classifier ensemble, Land cover, Feature selection, West Africa, Seasonal change},
    abstract = {Land use maps describe the spatial distribution of natural resources, cultural landscapes, and human settlements, serving as an important planning tool for decision makers. In the Sahel area, such information is valuable for risk management and mitigation in challenging sectors like food security, flood control, and urban planning. Due to its uniform quality across large areas in regular time steps, remote sensing imageries are essential input for producing land use maps. However, spatially and temporally heterogeneous landscapes in Sahel make classification of landscape features difficult. Our overall goal is to create an accurate, high resolution land use map covering Niamey, the capital of Niger and its surroundings which represents the unique landscape features in the Sahel using Sentinel-1 and Sentinel-2 archives. We assessed the performance of three commonly used classifiers (i.e. Maximum Likelihood (ML), Support Vector Machine (SVM) and Random Forest (RF)) for land use classification. To understand the utility of different features from Sentinel-1 and Sentinel-2 imagery for classification, we performed feature selection and compared mapping accuracies with and without feature selection. To leverage the strength of each classifier, we developed a classifier ensemble (CE) map based on the mapping accuracy of each land use class and each classifier. The results of this study showed that the performance of individual classifiers depends on feature selection method and accuracies can be improved by combining different classifiers. The ensemble map had an overall accuracy of 72+-3.9 percent and it was found superior in terms of accuracy particularly with respect to built-up areas compared to the existing global land cover products in the study area. Our classification scheme also better characterized the regional environment in the Sahel. For example, we mapped rice and bare rocks that have important regional implication, which are not included in the existing products. Overall, our approach highlights the potentiality of combining multi-modal imageries and multiple classifiers for mapping a heterogenous environment such as the Sahel with high spatial resolution.}
    }

  • M. Gerullis, T. Heckelei, and S. Rasch, “Toward understanding the governance of varietal and genetic diversity,” Ecology and Society, vol. 26, iss. 2, 2021.
    [BibTeX]
    @article{gerullis2021toward,
    title={Toward understanding the governance of varietal and genetic diversity},
    author={Gerullis, Maria and Heckelei, Thomas and Rasch, Sebastian},
    journal={Ecology and Society},
    volume={26},
    number={2},
    year={2021},
    publisher={The Resilience Alliance}
    doi={10.5751/ES-12333-260228}
    }

  • T. A. Marton and H. Storm, “The case of organic dairy conversion in Norway: Assessment of multivariate neighbourhood effects,” Q Open, vol. 1, iss. 1, 2021. doi:10.1093/qopen/qoab009
    [BibTeX] [PDF]

    {This study examines the impact of neighbourhood effects and individual farm characteristics on the decision process of organic dairy conversion in Norway, using a unique, spatially explicit farm-level panel set comprising information at the population level from 2003 to 2015. Our results reveal a positive spatial spillover of neighbouring conversion, confirming previous findings. Additionally, we demonstrate that neighbouring organic dairy reversion (i.e. switching back to conventional dairy farming) and organic dairy exits (ceasing to farm altogether) exert notable negative spatial spillovers on organic conversion decisions that have not yet been shown in the literature. If organic dairy production is an important policy goal, such negative spatial spillover requires consideration within policy design and extension.}

    @article{10.1093/qopen/qoab009,
    author = {Marton, Tibor A and Storm, Hugo},
    title = "{The case of organic dairy conversion in Norway: Assessment of multivariate neighbourhood effects}",
    journal = {Q Open},
    volume = {1},
    number = {1},
    year = {2021},
    month = {05},
    abstract = "{This study examines the impact of neighbourhood effects and individual farm characteristics on the decision process of organic dairy conversion in Norway, using a unique, spatially explicit farm-level panel set comprising information at the population level from 2003 to 2015. Our results reveal a positive spatial spillover of neighbouring conversion, confirming previous findings. Additionally, we demonstrate that neighbouring organic dairy reversion (i.e. switching back to conventional dairy farming) and organic dairy exits (ceasing to farm altogether) exert notable negative spatial spillovers on organic conversion decisions that have not yet been shown in the literature. If organic dairy production is an important policy goal, such negative spatial spillover requires consideration within policy design and extension.}",
    issn = {2633-9048},
    doi = {10.1093/qopen/qoab009},
    url = {https://doi.org/10.1093/qopen/qoab009},
    note = {qoab009},
    eprint = {https://academic.oup.com/qopen/article-pdf/1/1/qoab009/38391645/qoab009.pdf},
    }

  • S. J. Seidel, T. Gaiser, H. E. Ahrends, H. Hüging, S. Siebert, S. L. Bauke, M. I. Gocke, M. Koch, K. Schweitzer, G. Schaaf, and F. Ewert, “Crop response to P fertilizer omission under a changing climate – Experimental and modeling results over 115 years of a long-term fertilizer experiment,” Field Crops Research, vol. 268, p. 108174, 2021. doi:https://doi.org/10.1016/j.fcr.2021.108174
    [BibTeX] [PDF]

    Phosphorus (P) is an essential plant nutrient. However, our understanding of the complex interactions between soil P availability, environment, management and crop growth is still limited. We used unique historic and recent soil and crop data spanning more than a century combined with a process-based crop model to analyze the impact of P fertilizer omission and P fertilization on the biomass production of five crops. The long-term field experiment at Dikopshof, Germany, was established in 1904 with a 5-year crop rotation of sugar beet, winter wheat, winter rye, clover and oat/potato (potato replaced oat in 1953) on a fertile Luvisol. Averaged over the period from 1906 to 2018, the yield loss due to P omission was low for winter wheat and winter rye (7–8 %). In contrast, yield losses for sugar beet, clover and potato were relatively high (15–24 %). The yield loss from P fertilizer omission in comparison to the reference treatment (rotation mean excluding oat/potato) increased until the middle of the last century from 7% to 18 %, but subsequently decreased to 13 %. Trend and correlation analyses suggest that this decrease was related to an increase in air temperatures in especial during spring and a lower yield loss under P omission. Crop model simulations showed decreasing topsoil organic carbon concentrations after the 1930ies as manure was discontinued in 1942 but also due to increasing air temperatures. The increase in plant-available topsoil P concentrations during the last decades was one of the main factors offsetting yield losses despite P fertilizer omission. Our study suggests that climate change and, in particular, a marked increase in temperature since the middle of the last century most likely influenced soil P dynamics with a significant impact on crop production.

    @article{SEIDEL2021108174,
    title = {Crop response to P fertilizer omission under a changing climate - Experimental and modeling results over 115 years of a long-term fertilizer experiment},
    journal = {Field Crops Research},
    volume = {268},
    pages = {108174},
    year = {2021},
    issn = {0378-4290},
    doi = {https://doi.org/10.1016/j.fcr.2021.108174},
    url = {https://www.sciencedirect.com/science/article/pii/S0378429021001209},
    author = {S.J. Seidel and T. Gaiser and H.E. Ahrends and H. Hüging and S. Siebert and S.L. Bauke and M.I. Gocke and M. Koch and K. Schweitzer and G. Schaaf and F. Ewert},
    keywords = {Long-term field experiment, Climate change, Nutrient availability, Soil phosphorus simulation, Crop modeling},
    abstract = {Phosphorus (P) is an essential plant nutrient. However, our understanding of the complex interactions between soil P availability, environment, management and crop growth is still limited. We used unique historic and recent soil and crop data spanning more than a century combined with a process-based crop model to analyze the impact of P fertilizer omission and P fertilization on the biomass production of five crops. The long-term field experiment at Dikopshof, Germany, was established in 1904 with a 5-year crop rotation of sugar beet, winter wheat, winter rye, clover and oat/potato (potato replaced oat in 1953) on a fertile Luvisol. Averaged over the period from 1906 to 2018, the yield loss due to P omission was low for winter wheat and winter rye (7–8 %). In contrast, yield losses for sugar beet, clover and potato were relatively high (15–24 %). The yield loss from P fertilizer omission in comparison to the reference treatment (rotation mean excluding oat/potato) increased until the middle of the last century from 7% to 18 %, but subsequently decreased to 13 %. Trend and correlation analyses suggest that this decrease was related to an increase in air temperatures in especial during spring and a lower yield loss under P omission. Crop model simulations showed decreasing topsoil organic carbon concentrations after the 1930ies as manure was discontinued in 1942 but also due to increasing air temperatures. The increase in plant-available topsoil P concentrations during the last decades was one of the main factors offsetting yield losses despite P fertilizer omission. Our study suggests that climate change and, in particular, a marked increase in temperature since the middle of the last century most likely influenced soil P dynamics with a significant impact on crop production.}
    }

  • O. Spykman, A. Gabriel, M. Ptacek, and M. Gandorfer, “Farmers’ perspectives on field crop robots – Evidence from Bavaria, Germany,” Computers and Electronics in Agriculture, vol. 186, p. 106176, 2021. doi:https://doi.org/10.1016/j.compag.2021.106176
    [BibTeX] [PDF]

    Farmers’ attitudes toward field crop robots in a European setting have hardly been studied despite an increasing availability of the technology. Given the relevance of robots for small-scale agriculture, however, their acceptability in regions dominated by small-scale agriculture such as Bavaria, Germany, is of particular interest. Based on a sample of 174 farmers, an exploratory investigation of factors influencing the preference for large or small field crop robots in general and in specific settings and for mode of operation was carried out. Data were gathered using questionnaires at two events including lectures and field demonstrations and analyzed using bivariate tests. Farm size, farming system (organic/conventional), and occupational structure (part-time/full-time) were relevant attributes influencing the evaluation of advantages and disadvantages of field crop robots. Generally, respondents from larger farms focus more on financial benefits from robots and prefer large autonomous tractors. Conversely, small-scale or organic farmers consider environmental benefits of field crop robots relatively more important and favor small robots. Organic farming also positively correlates with the intent to purchase field crop robots within the next five years. More farmers can generally imagine owning small robots as opposed to an autonomous tractor in ten years, but at the same time view autonomous tractors as more suitable for most specified agronomic tasks. Non-purchase options such as contractor services and machinery sharing represent the preferred modes of robot deployment.

    @article{SPYKMAN2021106176,
    title = {Farmers’ perspectives on field crop robots – Evidence from Bavaria, Germany},
    journal = {Computers and Electronics in Agriculture},
    volume = {186},
    pages = {106176},
    year = {2021},
    issn = {0168-1699},
    doi = {https://doi.org/10.1016/j.compag.2021.106176},
    url = {https://www.sciencedirect.com/science/article/pii/S0168169921001939},
    author = {O. Spykman and A. Gabriel and M. Ptacek and M. Gandorfer},
    keywords = {Farmer survey, Attitude, Autonomous, Digitalization, Field crop robot},
    abstract = {Farmers’ attitudes toward field crop robots in a European setting have hardly been studied despite an increasing availability of the technology. Given the relevance of robots for small-scale agriculture, however, their acceptability in regions dominated by small-scale agriculture such as Bavaria, Germany, is of particular interest. Based on a sample of 174 farmers, an exploratory investigation of factors influencing the preference for large or small field crop robots in general and in specific settings and for mode of operation was carried out. Data were gathered using questionnaires at two events including lectures and field demonstrations and analyzed using bivariate tests. Farm size, farming system (organic/conventional), and occupational structure (part-time/full-time) were relevant attributes influencing the evaluation of advantages and disadvantages of field crop robots. Generally, respondents from larger farms focus more on financial benefits from robots and prefer large autonomous tractors. Conversely, small-scale or organic farmers consider environmental benefits of field crop robots relatively more important and favor small robots. Organic farming also positively correlates with the intent to purchase field crop robots within the next five years. More farmers can generally imagine owning small robots as opposed to an autonomous tractor in ten years, but at the same time view autonomous tractors as more suitable for most specified agronomic tasks. Non-purchase options such as contractor services and machinery sharing represent the preferred modes of robot deployment.}
    }

  • F. Görlich, E. Marks, A. Mahlein, K. König, P. Lottes, and C. Stachniss, “UAV-Based Classification of Cercospora Leaf Spot Using RGB Images,” Drones, vol. 5, iss. 2, 2021. doi:10.3390/drones5020034
    [BibTeX] [PDF]

    Plant diseases can impact crop yield. Thus, the detection of plant diseases using sensors that can be mounted on aerial vehicles is in the interest of farmers to support decision-making in integrated pest management and to breeders for selecting tolerant or resistant genotypes. This paper investigated the detection of Cercospora leaf spot (CLS), caused by Cercospora beticola in sugar beet using RGB imagery. We proposed an approach to tackle the CLS detection problem using fully convolutional neural networks, which operate directly on RGB images captured by a UAV. This efficient approach does not require complex multi- or hyper-spectral sensors, but provides reliable results and high sensitivity. We provided a detection pipeline for pixel-wise semantic segmentation of CLS symptoms, healthy vegetation, and background so that our approach can automatically quantify the grade of infestation. We thoroughly evaluated our system using multiple UAV datasets recorded from different sugar beet trial fields. The dataset consisted of a training and a test dataset and originated from different fields. We used it to evaluate our approach under realistic conditions and analyzed its generalization capabilities to unseen environments. The obtained results correlated to visual estimation by human experts significantly. The presented study underlined the potential of high-resolution RGB imaging and convolutional neural networks for plant disease detection under field conditions. The demonstrated procedure is particularly interesting for applications under practical conditions, as no complex and cost-intensive measuring system is required.

    @Article{goerlich2021drones,
    AUTHOR = {Görlich, Florian and Marks, Elias and Mahlein, Anne-Katrin and König, Kathrin and Lottes, Philipp and Stachniss, Cyrill},
    TITLE = {{UAV-Based Classification of Cercospora Leaf Spot Using RGB Images}},
    JOURNAL = {Drones},
    VOLUME = {5},
    YEAR = {2021},
    NUMBER = {2},
    ARTICLE-NUMBER = {34},
    URL = {https://www.mdpi.com/2504-446X/5/2/34/pdf},
    ISSN = {2504-446X},
    ABSTRACT = {Plant diseases can impact crop yield. Thus, the detection of plant diseases using sensors that can be mounted on aerial vehicles is in the interest of farmers to support decision-making in integrated pest management and to breeders for selecting tolerant or resistant genotypes. This paper investigated the detection of Cercospora leaf spot (CLS), caused by Cercospora beticola in sugar beet using RGB imagery. We proposed an approach to tackle the CLS detection problem using fully convolutional neural networks, which operate directly on RGB images captured by a UAV. This efficient approach does not require complex multi- or hyper-spectral sensors, but provides reliable results and high sensitivity. We provided a detection pipeline for pixel-wise semantic segmentation of CLS symptoms, healthy vegetation, and background so that our approach can automatically quantify the grade of infestation. We thoroughly evaluated our system using multiple UAV datasets recorded from different sugar beet trial fields. The dataset consisted of a training and a test dataset and originated from different fields. We used it to evaluate our approach under realistic conditions and analyzed its generalization capabilities to unseen environments. The obtained results correlated to visual estimation by human experts significantly. The presented study underlined the potential of high-resolution RGB imaging and convolutional neural networks for plant disease detection under field conditions. The demonstrated procedure is particularly interesting for applications under practical conditions, as no complex and cost-intensive measuring system is required.},
    DOI = {10.3390/drones5020034}
    }

  • C. Latka, T. Heckelei, A. Kuhn, H. Witzke, and L. Kornher, “CAP measures towards environmental sustainability—Trade opportunities for Africa?,” Q Open, vol. 1, iss. 1, 2021. doi:10.1093/qopen/qoab003
    [BibTeX] [PDF]

    {Environmental sustainability is a core aspect of the proposed future EU Common Agricultural Policy (CAP). Policy changes must not compromise socioeconomic development in low-income countries, whereas the extensification of EU agriculture may also create trade opportunities abroad. We apply a global agricultural-economic model to assess EU–African trade-related impacts of potential, environmentally motivated CAP changes. Restrictions on livestock density and nitrogen application reveal reduced EU production levels of meat. This lowers the EU’s agricultural environmental burden and share in agricultural trade flows to Africa. However, overall food supply in Africa is not projected to deteriorate substantially, as imports from other world regions and increasing domestic production fill the gap. While this weakens the global emission reduction potential, net livestock producers in Africa may benefit from increasing producer prices. How far potentials for domestic production and trade can be used in African regions depends at least partly on their competitiveness vis-á-vis substituting importers.}

    @article{10.1093/qopen/qoab003,
    author = {Latka, Catharina and Heckelei, Thomas and Kuhn, Arnim and Witzke, Heinz-Peter and Kornher, Lukas},
    title = "{CAP measures towards environmental sustainability—Trade opportunities for Africa?}",
    journal = {Q Open},
    volume = {1},
    number = {1},
    year = {2021},
    month = {03},
    abstract = "{Environmental sustainability is a core aspect of the proposed future EU Common Agricultural Policy (CAP). Policy changes must not compromise socioeconomic development in low-income countries, whereas the extensification of EU agriculture may also create trade opportunities abroad. We apply a global agricultural-economic model to assess EU–African trade-related impacts of potential, environmentally motivated CAP changes. Restrictions on livestock density and nitrogen application reveal reduced EU production levels of meat. This lowers the EU's agricultural environmental burden and share in agricultural trade flows to Africa. However, overall food supply in Africa is not projected to deteriorate substantially, as imports from other world regions and increasing domestic production fill the gap. While this weakens the global emission reduction potential, net livestock producers in Africa may benefit from increasing producer prices. How far potentials for domestic production and trade can be used in African regions depends at least partly on their competitiveness vis-á-vis substituting importers.}",
    issn = {2633-9048},
    doi = {10.1093/qopen/qoab003},
    note = {qoab003},
    url = {https://academic.oup.com/qopen/article-pdf/1/1/qoab003/37766860/qoab003.pdf},
    }

  • A. Haupenthal, M. Brax, J. Bentz, H. F. Jungkunst, K. Schützenmeister, and E. Kroener, “Plants control soil gas exchanges possibly via mucilage,” Journal of Plant Nutrition and Soil Science, 2021. doi:https://doi.org/10.1002/jpln.202000496
    [BibTeX] [PDF]

    Abstract Background: Gaseous matter exchanges in soil are determined by the connectivity of the pore system which is easily clogged by fresh root exudates. However, it remains unclear how a hydrogel (e.g., mucilage) affects soil pore tortuosity and gas diffusion properties when drying. Aims: The aim of this viewpoint study is to extend the understanding of gas exchange processes in the rhizosphere by (a) relating it to the patterns formed by drying mucilage within pore space and (b) to give a concept of the effect of drying mucilage on soil gas diffusivity using the combination of experimental evidence and simulations. Methods: To describe the effect of mucilage on soil gas exchanges, we performed gas diffusion experiments on dry soil–mucilage samples and took images of glass beads mixed with mucilage to visualize the formation of mucilage after drying, using Environmental Scanning Electron Microscopy. Finally, we set up simulations to characterize the geometric distribution of mucilage within soil during the drying process. Results: Experiments of gas diffusion show that mucilage decreases gas diffusion coefficient in dry soil without significantly altering bulk density and porosity. Electron microscopy indicates that during drying mucilage forms filaments and interconnected structures throughout the pore space reducing gas phase connectivity. The evolution of these geometric structures is explained via pore scale modelling based on identifying the elastic strength of rhizodeposition during soil drying. Conclusion: Our results suggest that releasing mucilage may be a plant adaption strategy to actively alter gas diffusion in soil.

    @article{https://doi.org/10.1002/jpln.202000496,
    author = {Haupenthal, Adrian and Brax, Mathilde and Bentz, Jonas and Jungkunst, Hermann F. and Schützenmeister, Klaus and Kroener, Eva},
    title = {Plants control soil gas exchanges possibly via mucilage},
    journal = {Journal of Plant Nutrition and Soil Science},
    keywords = {gas diffusion coefficient, liquid bridges, mucilage, pore connectivity, pore scale simulation, respiration, rhizosphere},
    doi = {https://doi.org/10.1002/jpln.202000496},
    year = {2021},
    url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/jpln.202000496},
    eprint = {https://onlinelibrary.wiley.com/doi/pdf/10.1002/jpln.202000496},
    abstract = {Abstract Background: Gaseous matter exchanges in soil are determined by the connectivity of the pore system which is easily clogged by fresh root exudates. However, it remains unclear how a hydrogel (e.g., mucilage) affects soil pore tortuosity and gas diffusion properties when drying. Aims: The aim of this viewpoint study is to extend the understanding of gas exchange processes in the rhizosphere by (a) relating it to the patterns formed by drying mucilage within pore space and (b) to give a concept of the effect of drying mucilage on soil gas diffusivity using the combination of experimental evidence and simulations. Methods: To describe the effect of mucilage on soil gas exchanges, we performed gas diffusion experiments on dry soil–mucilage samples and took images of glass beads mixed with mucilage to visualize the formation of mucilage after drying, using Environmental Scanning Electron Microscopy. Finally, we set up simulations to characterize the geometric distribution of mucilage within soil during the drying process. Results: Experiments of gas diffusion show that mucilage decreases gas diffusion coefficient in dry soil without significantly altering bulk density and porosity. Electron microscopy indicates that during drying mucilage forms filaments and interconnected structures throughout the pore space reducing gas phase connectivity. The evolution of these geometric structures is explained via pore scale modelling based on identifying the elastic strength of rhizodeposition during soil drying. Conclusion: Our results suggest that releasing mucilage may be a plant adaption strategy to actively alter gas diffusion in soil.}
    }

  • P. Yu, X. He, M. Baer, S. Beirinckx, T. Tian, Y. A. T. Moya, X. Zhang, M. Deichmann, F. P. Frey, V. Bresgen, C. Li, B. S. Razavi, G. Schaaf, N. von Wirén, Z. Su, M. Bucher, K. Tsuda, S. Goormachtig, X. Chen, and F. Hochholdinger, “Plant flavones enrich rhizosphere Oxalobacteraceae to improve maize performance under nitrogen deprivation,” Nature Plants, p. 1–19, 2021. doi:10.1038/s41477-021-00897-y
    [BibTeX]

    {Beneficial interactions between plant roots and rhizosphere microorganisms are pivotal for plant fitness. Nevertheless, the molecular mechanisms controlling the feedback between root architecture and microbial community structure remain elusive in maize. Here, we demonstrate that transcriptomic gradients along the longitudinal root axis associate with specific shifts in rhizosphere microbial diversity. Moreover, we have established that root-derived flavones predominantly promote the enrichment of bacteria of the taxa Oxalobacteraceae in the rhizosphere, which in turn promote maize growth and nitrogen acquisition. Genetic experiments demonstrate that LRT1-mediated lateral root development coordinates the interactions of the root system with flavone-dependent Oxalobacteraceae under nitrogen deprivation. In summary, these experiments reveal the genetic basis of the reciprocal interactions between root architecture and the composition and diversity of specific microbial taxa in the rhizosphere resulting in improved plant performance. These findings may open new avenues towards the breeding of high-yielding and nutrient-efficient crops by exploiting their interaction with beneficial soil microorganisms. The link between rhizosphere microbial community, root architecture and performance in nitrogen-poor soils is comprehensively investigated in maize, and the role of exuded flavone to promote specific beneficial bacterial taxa is characterized.}

    @article{10.1038/s41477-021-00897-y,
    year = {2021},
    title = {{Plant flavones enrich rhizosphere Oxalobacteraceae to improve maize performance under nitrogen deprivation}},
    author = {Yu, Peng and He, Xiaoming and Baer, Marcel and Beirinckx, Stien and Tian, Tian and Moya, Yudelsy A T and Zhang, Xuechen and Deichmann, Marion and Frey, Felix P and Bresgen, Verena and Li, Chunjian and Razavi, Bahar S and Schaaf, Gabriel and Wirén, Nicolaus von and Su, Zhen and Bucher, Marcel and Tsuda, Kenichi and Goormachtig, Sofie and Chen, Xinping and Hochholdinger, Frank},
    journal = {Nature Plants},
    doi = {10.1038/s41477-021-00897-y},
    abstract = {{Beneficial interactions between plant roots and rhizosphere microorganisms are pivotal for plant fitness. Nevertheless, the molecular mechanisms controlling the feedback between root architecture and microbial community structure remain elusive in maize. Here, we demonstrate that transcriptomic gradients along the longitudinal root axis associate with specific shifts in rhizosphere microbial diversity. Moreover, we have established that root-derived flavones predominantly promote the enrichment of bacteria of the taxa Oxalobacteraceae in the rhizosphere, which in turn promote maize growth and nitrogen acquisition. Genetic experiments demonstrate that LRT1-mediated lateral root development coordinates the interactions of the root system with flavone-dependent Oxalobacteraceae under nitrogen deprivation. In summary, these experiments reveal the genetic basis of the reciprocal interactions between root architecture and the composition and diversity of specific microbial taxa in the rhizosphere resulting in improved plant performance. These findings may open new avenues towards the breeding of high-yielding and nutrient-efficient crops by exploiting their interaction with beneficial soil microorganisms. The link between rhizosphere microbial community, root architecture and performance in nitrogen-poor soils is comprehensively investigated in maize, and the role of exuded flavone to promote specific beneficial bacterial taxa is characterized.}},
    pages = {1--19}
    }

  • M. Popović, F. Thomas, S. Papatheodorou, N. Funk, T. Vidal-Calleja, and S. Leutenegger, “Volumetric Occupancy Mapping With Probabilistic Depth Completion for Robotic Navigation,” IEEE Robotics and Automation Letters, 2021.
    [BibTeX]
    @article{Popovic2021,
    author = {Marija Popovi{\'c} and
    Florian Thomas and
    Sotiris Papatheodorou and
    Nils Funk and
    Teresa Vidal-Calleja and
    Stefan Leutenegger},
    title = {{Volumetric Occupancy Mapping With Probabilistic Depth Completion for Robotic Navigation}},
    journal = {{IEEE} Robotics and Automation Letters},
    year = {2021}
    }

  • S. Dadshani, B. Mathew, A. Ballvora, A. S. Mason, and J. Léon, “Detection of breeding signatures in wheat using a linkage disequilibrium-corrected mapping approach,” Scientific Reports, vol. 11, iss. 1, p. 1–12, 2021.
    [BibTeX]
    @article{dadshani2021detection,
    title={Detection of breeding signatures in wheat using a linkage disequilibrium-corrected mapping approach},
    author={Dadshani, Said and Mathew, Boby and Ballvora, Agim and Mason, Annaliese S and L{\'e}on, Jens},
    journal={Scientific Reports},
    volume={11},
    number={1},
    pages={1--12},
    year={2021},
    publisher={Nature Publishing Group}
    }

  • E. Martinsson and H. Hansson, “Adjusting eco-efficiency to greenhouse gas emissions targets at farm level – The case of Swedish dairy farms,” Journal of Environmental Management, vol. 287, p. 112313, 2021. doi:https://doi.org/10.1016/j.jenvman.2021.112313
    [BibTeX] [PDF]

    The purpose of this paper is to adjust the measure of eco-efficiency to account for specific sustainability targets at farm level. We assess eco-efficiency and adjust the scores according to a target of absolute levels of greenhouse gas (GHG) emissions, using Data Envelopment Analysis (DEA) and data from Swedish dairy farms as an illustrative example. In particular, the Swedish target of net-zero emissions in 2045 and vision of a fossil free economy are used to specify the GHG emission target used for assessing the adjusted eco-efficiency scores. We test for possible factors associated with the adjusted and unadjusted eco-efficiency using OLS-regression analysis. The study is based on data from the farm accounting data network (FADN) in year 2016 and considers the environmental pressures nutrients and contribution to global warming. Adjusted as well as unadjusted eco-efficiency scores suggest that Swedish dairy farms are highly inefficient, and that economic value added could increase by 64% (adj) or 67% (unadj) for conventional farms and by 42% (adj) or 41% (unadj) for organic farms at the same level of environmental pressure. Findings further suggest that adjusting the scores towards absolute levels of GHG emissions increases industry average efficiency. Comparing the unadjusted and adjusted efficiency scores using Spearman rank correlation indicates similar efficiency rankings between the unadjusted and adjusted scores. However, findings also indicate that adjusted and unadjusted eco-efficiency scores are associated with different influencing factors, which lends empirical support to the idea that the two types of efficiency scores are conceptually different. Policy recommendations can be made based on insights from the second stage analysis of possible influencing factors. In particular, adjusted eco-efficiency is associated with higher intensity of farming defined as output per livestock unit. Further, adjusted eco-efficiency is associated with a higher number of livestock units in conventional farms and with lower levels of labour per livestock unit in organic farms.

    @article{MARTINSSON2021112313,
    title = {Adjusting eco-efficiency to greenhouse gas emissions targets at farm level – The case of Swedish dairy farms},
    journal = {Journal of Environmental Management},
    volume = {287},
    pages = {112313},
    year = {2021},
    issn = {0301-4797},
    doi = {https://doi.org/10.1016/j.jenvman.2021.112313},
    url = {https://www.sciencedirect.com/science/article/pii/S0301479721003753},
    author = {Elin Martinsson and Helena Hansson},
    keywords = {Common agricultural policy, Eco-efficiency, Livestock farming, Planetary boundaries, Sweden},
    abstract = {The purpose of this paper is to adjust the measure of eco-efficiency to account for specific sustainability targets at farm level. We assess eco-efficiency and adjust the scores according to a target of absolute levels of greenhouse gas (GHG) emissions, using Data Envelopment Analysis (DEA) and data from Swedish dairy farms as an illustrative example. In particular, the Swedish target of net-zero emissions in 2045 and vision of a fossil free economy are used to specify the GHG emission target used for assessing the adjusted eco-efficiency scores. We test for possible factors associated with the adjusted and unadjusted eco-efficiency using OLS-regression analysis. The study is based on data from the farm accounting data network (FADN) in year 2016 and considers the environmental pressures nutrients and contribution to global warming. Adjusted as well as unadjusted eco-efficiency scores suggest that Swedish dairy farms are highly inefficient, and that economic value added could increase by 64% (adj) or 67% (unadj) for conventional farms and by 42% (adj) or 41% (unadj) for organic farms at the same level of environmental pressure. Findings further suggest that adjusting the scores towards absolute levels of GHG emissions increases industry average efficiency. Comparing the unadjusted and adjusted efficiency scores using Spearman rank correlation indicates similar efficiency rankings between the unadjusted and adjusted scores. However, findings also indicate that adjusted and unadjusted eco-efficiency scores are associated with different influencing factors, which lends empirical support to the idea that the two types of efficiency scores are conceptually different. Policy recommendations can be made based on insights from the second stage analysis of possible influencing factors. In particular, adjusted eco-efficiency is associated with higher intensity of farming defined as output per livestock unit. Further, adjusted eco-efficiency is associated with a higher number of livestock units in conventional farms and with lower levels of labour per livestock unit in organic farms.}
    }

  • N. Chebrolu, F. Magistri, T. Läbe, and C. Stachniss, “Registration of Spatio-Temporal Point Clouds of Plants for Phenotyping,” PLOS ONE, 2021.
    [BibTeX] [PDF]
    @article{chebrolu2021plosone,
    author = {N. Chebrolu and F. Magistri and T. L{\"a}be and C. Stachniss},
    title = {{Registration of Spatio-Temporal Point Clouds of Plants for Phenotyping}},
    journal = {PLOS ONE},
    year = 2021,
    url = {https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0247243&type=printable},
    }

  • J. Weyler, A. Milioto, T. Falck, J. Behley, and C. Stachniss, “Joint Plant Instance Detection and Leaf Count Estimation for In-Field Plant Phenotyping,” IEEE Robotics and Automation Letters (RA-L), 2021.
    [BibTeX] [Video]
    @article{weyler2021ral,
    author = {J. Weyler and A. Milioto and T. Falck and J. Behley and C. Stachniss},
    title = {{Joint Plant Instance Detection and Leaf Count Estimation for In-Field Plant Phenotyping}},
    journal = {IEEE Robotics and Automation Letters (RA-L)},
    year = 2021,
    videourl = {https://youtu.be/Is18Rey625I},
    }

  • L. Wiesmann, A. Milioto, X. Chen, C. Stachniss, and J. Behley, “Deep Compression for Dense Point Cloud Maps,” IEEE Robotics and Automation Letters (RA-L), 2021.
    [BibTeX] [PDF]
    @article{wiesmann2021ral,
    author = {L. Wiesmann and A. Milioto and X. Chen and C. Stachniss and J. Behley},
    title = {{Deep Compression for Dense Point Cloud Maps}},
    journal = {IEEE Robotics and Automation Letters (RA-L)},
    year = 2021,
    url = {https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/wiesmann2021ral.pdf},
    }

  • N. Chebrolu, T. Läbe, O. Vysotska, J. Behley, and C. Stachniss, “Adaptive Robust Kernels for Non-Linear Least Squares Problems,” IEEE Robotics and Automation Letters (RA-L), 2021.
    [BibTeX] [PDF]
    @article{chebrolu2021ral,
    author = {N. Chebrolu and T. L\"{a}be and O. Vysotska and J. Behley and C. Stachniss},
    title = {{Adaptive Robust Kernels for Non-Linear Least Squares Problems}},
    journal = {IEEE Robotics and Automation Letters (RA-L)},
    year = 2021,
    url = {https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/chebrolu2021ral.pdf},
    }

  • F. Magistri, N. Chebrolu, J. Behley, and C. Stachniss, “Towards In-Field Phenotyping Exploiting Differentiable Rendering with Self-Consistency Loss,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2021.
    [BibTeX] [PDF] [Video]
    @inproceedings{magistri2021icra,
    author = {F. Magistri and N. Chebrolu and J. Behley and C. Stachniss},
    title = {{Towards In-Field Phenotyping Exploiting Differentiable Rendering with Self-Consistency Loss}},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = 2021,
    videourl = {https://youtu.be/MF2A4ihY2lE},
    url = {https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/magistri2021icra.pdf},
    }

  • I. Vizzo, X. Chen, N. Chebrolu, J. Behley, and C. Stachniss, “Poisson Surface Reconstruction for LiDAR Odometry and Mapping,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2021.
    [BibTeX]
    @inproceedings{vizzo2021icra,
    author = {I. Vizzo and X. Chen and N. Chebrolu and J. Behley and C. Stachniss},
    title = {{Poisson Surface Reconstruction for LiDAR Odometry and Mapping}},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = 2021,
    }

  • X. Chen, I. Vizzo, T. Läbe, J. Behley, and C. Stachniss, “Range Image-based LiDAR Localization for Autonomous Vehicles,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2021.
    [BibTeX]
    @inproceedings{chen2021icra,
    author = {X. Chen and I. Vizzo and T. L{\"a}be and J. Behley and C. Stachniss},
    title = {{Range Image-based LiDAR Localization for Autonomous Vehicles}},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = 2021,
    }

  • A. Reinke, X. Chen, and C. Stachniss, “Simple But Effective Redundant Odometry for Autonomous Vehicles,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2021.
    [BibTeX]
    @inproceedings{reinke2021icra,
    title={{Simple But Effective Redundant Odometry for Autonomous Vehicles}},
    author={A. Reinke and X. Chen and C. Stachniss},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year={2021}
    }

  • J. Behley, A. Milioto, and C. Stachniss, “A Benchmark for LiDAR-based Panoptic Segmentation based on KITTI,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2021.
    [BibTeX]
    @inproceedings{behley2021icra,
    author = {J. Behley and A. Milioto and C. Stachniss},
    title = {{A Benchmark for LiDAR-based Panoptic Segmentation based on KITTI}},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = 2021,
    }

  • C. Carbone, D. Albani, F. Magistri, D. Ognibene, C. Stachniss, G. Kootstra, D. Nardi, and V. Trianni, “Monitoring and Mapping of Crop Fields with UAV Swarms Based on Information Gain,” in Proc. of the Intl. Symp. on Distributed Autonomous Robotic Systems (DARS) , 2021.
    [BibTeX]
    @inproceedings{carbone2021dars,
    author = {C. Carbone and D. Albani and F. Magistri and D. Ognibene and C. Stachniss and G. Kootstra and D. Nardi and V. Trianni},
    title = {{Monitoring and Mapping of Crop Fields with UAV Swarms Based on Information Gain}},
    booktitle = {Proc. of the Intl. Symp. on Distributed Autonomous Robotic Systems (DARS)},
    year = 2021,
    }

  • J. S. Bates, C. Montzka, M. Schmidt, and F. Jonard, “Estimating Canopy Density Parameters Time-Series for Winter Wheat Using UAS Mounted LiDAR,” Remote Sensing, vol. 13, iss. 4, 2021. doi:10.3390/rs13040710
    [BibTeX] [PDF]

    Monitoring of canopy density with related metrics such as leaf area index (LAI) makes a significant contribution to understanding and predicting processes in the soil–plant–atmosphere system and to indicating crop health and potential yield for farm management. Remote sensing methods using optical sensors that rely on spectral reflectance to calculate LAI have become more mainstream due to easy entry and availability. Methods with vegetation indices (VI) based on multispectral reflectance data essentially measure the green area index (GAI) or response to chlorophyll content of the canopy surface and not the entire aboveground biomass that may be present from non-green elements that are key to fully assessing the carbon budget. Methods with light detection and ranging (LiDAR) have started to emerge using gap fraction (GF) to estimate the plant area index (PAI) based on canopy density. These LiDAR methods have the main advantage of being sensitive to both green and non-green plant elements. They have primarily been applied to forest cover with manned airborne LiDAR systems (ALS) and have yet to be used extensively with crops such as winter wheat using LiDAR on unmanned aircraft systems (UAS). This study contributes to a better understanding of the potential of LiDAR as a tool to estimate canopy structure in precision farming. The LiDAR method proved to have a high to moderate correlation in spatial variation to the multispectral method. The LiDAR-derived PAI values closely resemble the SunScan Ceptometer GAI ground measurements taken early in the growing season before major stages of senescence. Later in the growing season, when the canopy density was at its highest, a possible overestimation may have occurred. This was most likely due to the chosen flight parameters not providing the best depictions of canopy density with consideration of the LiDAR’s perspective, as the ground-based destructive measurements provided lower values of PAI. Additionally, a distinction between total LiDAR-derived PAI, multispectral-derived GAI, and brown area index (BAI) is made to show how the active and passive optical sensor methods used in this study can complement each other throughout the growing season.

    @Article{rs13040710,
    AUTHOR = {Bates, Jordan Steven and Montzka, Carsten and Schmidt, Marius and Jonard, François},
    TITLE = {Estimating Canopy Density Parameters Time-Series for Winter Wheat Using UAS Mounted LiDAR},
    JOURNAL = {Remote Sensing},
    VOLUME = {13},
    YEAR = {2021},
    NUMBER = {4},
    ARTICLE-NUMBER = {710},
    URL = {https://www.mdpi.com/2072-4292/13/4/710},
    ISSN = {2072-4292},
    ABSTRACT = {Monitoring of canopy density with related metrics such as leaf area index (LAI) makes a significant contribution to understanding and predicting processes in the soil–plant–atmosphere system and to indicating crop health and potential yield for farm management. Remote sensing methods using optical sensors that rely on spectral reflectance to calculate LAI have become more mainstream due to easy entry and availability. Methods with vegetation indices (VI) based on multispectral reflectance data essentially measure the green area index (GAI) or response to chlorophyll content of the canopy surface and not the entire aboveground biomass that may be present from non-green elements that are key to fully assessing the carbon budget. Methods with light detection and ranging (LiDAR) have started to emerge using gap fraction (GF) to estimate the plant area index (PAI) based on canopy density. These LiDAR methods have the main advantage of being sensitive to both green and non-green plant elements. They have primarily been applied to forest cover with manned airborne LiDAR systems (ALS) and have yet to be used extensively with crops such as winter wheat using LiDAR on unmanned aircraft systems (UAS). This study contributes to a better understanding of the potential of LiDAR as a tool to estimate canopy structure in precision farming. The LiDAR method proved to have a high to moderate correlation in spatial variation to the multispectral method. The LiDAR-derived PAI values closely resemble the SunScan Ceptometer GAI ground measurements taken early in the growing season before major stages of senescence. Later in the growing season, when the canopy density was at its highest, a possible overestimation may have occurred. This was most likely due to the chosen flight parameters not providing the best depictions of canopy density with consideration of the LiDAR’s perspective, as the ground-based destructive measurements provided lower values of PAI. Additionally, a distinction between total LiDAR-derived PAI, multispectral-derived GAI, and brown area index (BAI) is made to show how the active and passive optical sensor methods used in this study can complement each other throughout the growing season.},
    DOI = {10.3390/rs13040710}
    }

  • L. Shang, T. Heckelei, M. K. Gerullis, J. Börner, and S. Rasch, “Adoption and diffusion of digital farming technologies – integrating farm-level evidence and system interaction,” Agricultural Systems, vol. 190, p. 103074, 2021. doi:https://doi.org/10.1016/j.agsy.2021.103074
    [BibTeX] [PDF]
    @article{SHANG2021103074,
    title = {Adoption and diffusion of digital farming technologies - integrating farm-level evidence and system interaction},
    journal = {Agricultural Systems},
    volume = {190},
    pages = {103074},
    year = {2021},
    issn = {0308-521X},
    doi = {https://doi.org/10.1016/j.agsy.2021.103074},
    url = {https://www.sciencedirect.com/science/article/pii/S0308521X21000275},
    author = {Linmei Shang and Thomas Heckelei and Maria K. Gerullis and Jan Börner and Sebastian Rasch},
    }

  • S. Gedicke, A. Bonerath, B. Niedermann, and J. -H. Haunert, “Zoomless Maps: External Labeling Methods for the Interactive Exploration of Dense Point Sets at a Fixed Map Scale,” IEEE Transactions on Visualization and Computer Graphics, vol. 27, iss. 2, pp. 1247-1256, 2021. doi:10.1109/TVCG.2020.3030399
    [BibTeX]
    @ARTICLE{9222088,
    author={S. {Gedicke} and A. {Bonerath} and B. {Niedermann} and J. -H. {Haunert}},
    journal={IEEE Transactions on Visualization and Computer Graphics},
    title={Zoomless Maps: External Labeling Methods for the Interactive Exploration of Dense Point Sets at a Fixed Map Scale},
    year={2021},
    volume={27},
    number={2},
    pages={1247-1256},
    doi={10.1109/TVCG.2020.3030399}}

  • S. Hadir, T. Gaiser, H. Hüging, M. Athmann, D. Pfarr, R. Kemper, F. Ewert, and S. Seidel, “Sugar Beet Shoot and Root Phenotypic Plasticity to Nitrogen, Phosphorus, Potassium and Lime Omission,” Agriculture, vol. 11, iss. 1, 2021. doi:10.3390/agriculture11010021
    [BibTeX] [PDF]

    In low input agriculture, a thorough understanding of the plant-nutrient interactions plays a central role. This study aims to investigate the effects of nitrogen (N), phosphorus (P), and potassium (K) and liming omission on shoot growth as well as on topsoil root biomass, growth and morphology (tuber and fibrous roots) of sugar beet grown under field conditions at the Dikopshof long-term fertilizer experiment (Germany). Classical shoot observation methods were combined with root morphology and link measurements using an image analysis program. Omission of the nutrients N, P and K as well as of liming led to a significant decrease in shoot growth. Tuber yield was lowest for the unfertilized and the K omission treatment. The root shoot ratio was highest in the N deficient treatment. In the K omission treatment, a strategic change from a less herringbone root type (early stage) to a more herringbone root type (late stage), which is more efficient for the acquisition of mobile nutrients, was observed. By contrast, a change from a more herringbone (early stage) to a less herringbone root type (late stage) which is less expensive to produce and maintain was observed in the unfertilized treatment. We conclude that sugar beet alters its root morphology as a nutrient acquisition strategy.

    @Article{agriculture11010021,
    AUTHOR = {Hadir, Sofia and Gaiser, Thomas and Hüging, Hubert and Athmann, Miriam and Pfarr, Daniel and Kemper, Roman and Ewert, Frank and Seidel, Sabine},
    TITLE = {Sugar Beet Shoot and Root Phenotypic Plasticity to Nitrogen, Phosphorus, Potassium and Lime Omission},
    JOURNAL = {Agriculture},
    VOLUME = {11},
    YEAR = {2021},
    NUMBER = {1},
    ARTICLE-NUMBER = {21},
    URL = {https://www.mdpi.com/2077-0472/11/1/21},
    ISSN = {2077-0472},
    ABSTRACT = {In low input agriculture, a thorough understanding of the plant-nutrient interactions plays a central role. This study aims to investigate the effects of nitrogen (N), phosphorus (P), and potassium (K) and liming omission on shoot growth as well as on topsoil root biomass, growth and morphology (tuber and fibrous roots) of sugar beet grown under field conditions at the Dikopshof long-term fertilizer experiment (Germany). Classical shoot observation methods were combined with root morphology and link measurements using an image analysis program. Omission of the nutrients N, P and K as well as of liming led to a significant decrease in shoot growth. Tuber yield was lowest for the unfertilized and the K omission treatment. The root shoot ratio was highest in the N deficient treatment. In the K omission treatment, a strategic change from a less herringbone root type (early stage) to a more herringbone root type (late stage), which is more efficient for the acquisition of mobile nutrients, was observed. By contrast, a change from a more herringbone (early stage) to a less herringbone root type (late stage) which is less expensive to produce and maintain was observed in the unfertilized treatment. We conclude that sugar beet alters its root morphology as a nutrient acquisition strategy.},
    DOI = {10.3390/agriculture11010021}
    }

  • D. Wallach, T. Palosuo, P. Thorburn, Z. Hochman, F. Andrianasolo, S. Asseng, B. Basso, S. Buis, N. Crout, B. Dumont, R. Ferrise, T. Gaiser, S. Gayler, S. Hireman, S. Hoek, H. Horan, G. Hoogenboom, M. Huang, M. Jabloun, P. -E. Jasson, Q. Jing, E. Justes, C. K. Kersebaum, M. Launay, E. Lewan, Q. Luo, B. Maestrini, M. Moriondo, G. Padovan, J. E. Olesen, A. Poyda, E. Priesack, Q. B. Pullens J.W.M, N. Schütze, V. Shelia, A. Souissi, X. Specka, A. K. Srivastava, T. Stella, T. Streck, G. Trombi, E. Wallor, J. Wang, T. H. D. Weber, L. Weihermüller, A. de Wit, T. Wöhling, L. Xiao, C. Zhao, Y. Zhu, and S. J. Seidel, “Multi-model evaluation of phenology prediction for wheat in Australia,” Agricultural and Forest Meteorology, vol. 124, pp. 298-299, 2021. doi:https://doi.org/10.1016/j.agrformet.2020.108289
    [BibTeX]
    @article{WALLACH2021agrformet,
    title = "Multi-model evaluation of phenology prediction for wheat in Australia",
    journal = "Agricultural and Forest Meteorology",
    volume = "124",
    pages = "298-299",
    year = "2021",
    issn = "1161-0301",
    doi = "https://doi.org/10.1016/j.agrformet.2020.108289",
    author = {Wallach, D. and Palosuo, T. and Thorburn, P. and Hochman, Z. and Andrianasolo, F. and Asseng, S. and Basso, B. and Buis, S. and Crout, N. and Dumont, B. and Ferrise, R. and Gaiser, T. and Gayler, S. and Hireman, S. and Hoek, S. and Horan, H. and Hoogenboom, G. and Huang, M. and Jabloun, M. and Jasson, P.-E. and Jing, Q. and Justes, E. and Kersebaum, C.K. and Launay, M. and Lewan, E. and Luo, Q. and Maestrini, B. and Moriondo, M. and Padovan, G. and Olesen, J.E. and Poyda, A. and Priesack, E. and Pullens, J.W.M, Qian, B. and Schütze, N. and Shelia, V. and Souissi, A. and Specka, X. and Srivastava, A.K. and Stella, T. and Streck, T. and Trombi, G. and Wallor, E. and Wang, J. and Weber, T.H.D. and Weihermüller, L. and de Wit, A. and Wöhling, T. and Xiao, L. and Zhao, C. and Zhu, Y. and Seidel, S. J.}
    }

  • D. Wallach, T. Palosuo, P. Thorburn, E. Gourdain, S. Asseng, B. Basso, S. Buis, N. Crout, C. Dibari, B. Dumont, R. Ferrise, T. Gaiser, C. Garcia, S. Gayler, A. Ghahramani, Z. Hochman, S. Hoek, G. Hoogenboom, H. Horan, M. Huang, M. Jabloun, Q. Jing, E. Justes, K. C. Kersebaum, A. Klosterhalfen, M. Launay, Q. Luo, B. Maestrini, H. Mielenz, M. Moriondo, H. Nariman Zadeh, J. E. Olesen, A. Poyda, E. Priesack, J. W. M. Pullens, B. Qian, N. Schütze, V. Shelia, A. Souissi, X. Specka, A. K. Srivastava, T. Stella, T. Streck, G. Trombi, E. Wallor, J. Wang, T. K. D. Weber, L. Weihermüller, A. de Wit, T. Wöhling, L. Xiao, C. Zhao, Y. Zhu, and S. J. Seidel, “How well do crop modeling groups predict wheat phenology, given calibration data from the target population?,” European Journal of Agronomy, vol. 124, p. 126195, 2021. doi:https://doi.org/10.1016/j.eja.2020.126195
    [BibTeX] [PDF]

    Predicting phenology is essential for adapting varieties to different environmental conditions and for crop management. Therefore, it is important to evaluate how well different crop modeling groups can predict phenology. Multiple evaluation studies have been previously published, but it is still difficult to generalize the findings from such studies since they often test some specific aspect of extrapolation to new conditions, or do not test on data that is truly independent of the data used for calibration. In this study, we analyzed the prediction of wheat phenology in Northern France under observed weather and current management, which is a problem of practical importance for wheat management. The results of 27 modeling groups are evaluated, where modeling group encompasses model structure, i.e. the model equations, the calibration method and the values of those parameters not affected by calibration. The data for calibration and evaluation are sampled from the same target population, thus extrapolation is limited. The calibration and evaluation data have neither year nor site in common, to guarantee rigorous evaluation of prediction for new weather and sites. The best modeling groups, and also the mean and median of the simulations, have a mean absolute error (MAE) of about 3 days, which is comparable to the measurement error. Almost all models do better than using average number of days or average sum of degree days to predict phenology. On the other hand, there are important differences between modeling groups, due to model structural differences and to differences between groups using the same model structure, which emphasizes that model structure alone does not completely determine prediction accuracy. In addition to providing information for our specific environments and varieties, these results are a useful contribution to a knowledge base of how well modeling groups can predict phenology, when provided with calibration data from the target population.

    @article{WALLACH2021126195,
    title = "How well do crop modeling groups predict wheat phenology, given calibration data from the target population?",
    journal = "European Journal of Agronomy",
    volume = "124",
    pages = "126195",
    year = "2021",
    issn = "1161-0301",
    doi = "https://doi.org/10.1016/j.eja.2020.126195",
    url = "http://www.sciencedirect.com/science/article/pii/S1161030120302021",
    author = "Daniel Wallach and Taru Palosuo and Peter Thorburn and Emmanuelle Gourdain and Senthold Asseng and Bruno Basso and Samuel Buis and Neil Crout and Camilla Dibari and Benjamin Dumont and Roberto Ferrise and Thomas Gaiser and Cécile Garcia and Sebastian Gayler and Afshin Ghahramani and Zvi Hochman and Steven Hoek and Gerrit Hoogenboom and Heidi Horan and Mingxia Huang and Mohamed Jabloun and Qi Jing and Eric Justes and Kurt Christian Kersebaum and Anne Klosterhalfen and Marie Launay and Qunying Luo and Bernardo Maestrini and Henrike Mielenz and Marco Moriondo and Hasti {Nariman Zadeh} and Jørgen Eivind Olesen and Arne Poyda and Eckart Priesack and Johannes Wilhelmus Maria Pullens and Budong Qian and Niels Schütze and Vakhtang Shelia and Amir Souissi and Xenia Specka and Amit Kumar Srivastava and Tommaso Stella and Thilo Streck and Giacomo Trombi and Evelyn Wallor and Jing Wang and Tobias K.D. Weber and Lutz Weihermüller and Allard {de Wit} and Thomas Wöhling and Liujun Xiao and Chuang Zhao and Yan Zhu and Sabine J. Seidel",
    keywords = "Crop model, Phenology prediction, Model evaluation, Wheat",
    abstract = "Predicting phenology is essential for adapting varieties to different environmental conditions and for crop management. Therefore, it is important to evaluate how well different crop modeling groups can predict phenology. Multiple evaluation studies have been previously published, but it is still difficult to generalize the findings from such studies since they often test some specific aspect of extrapolation to new conditions, or do not test on data that is truly independent of the data used for calibration. In this study, we analyzed the prediction of wheat phenology in Northern France under observed weather and current management, which is a problem of practical importance for wheat management. The results of 27 modeling groups are evaluated, where modeling group encompasses model structure, i.e. the model equations, the calibration method and the values of those parameters not affected by calibration. The data for calibration and evaluation are sampled from the same target population, thus extrapolation is limited. The calibration and evaluation data have neither year nor site in common, to guarantee rigorous evaluation of prediction for new weather and sites. The best modeling groups, and also the mean and median of the simulations, have a mean absolute error (MAE) of about 3 days, which is comparable to the measurement error. Almost all models do better than using average number of days or average sum of degree days to predict phenology. On the other hand, there are important differences between modeling groups, due to model structural differences and to differences between groups using the same model structure, which emphasizes that model structure alone does not completely determine prediction accuracy. In addition to providing information for our specific environments and varieties, these results are a useful contribution to a knowledge base of how well modeling groups can predict phenology, when provided with calibration data from the target population."
    }

  • C. Latka, M. Kuiper, S. Frank, T. Heckelei, P. Havlík, H. Witzke, A. Leip, H. D. Cui, A. Kuijsten, J. M. Geleijnse, and M. van Dijk, “Paying the price for environmentally sustainable and healthy EU diets,” Global Food Security, vol. 28, p. 100437, 2021. doi:https://doi.org/10.1016/j.gfs.2020.100437
    [BibTeX] [PDF]

    We review consumer-side interventions and their effectiveness to support a transition to healthier and more environmentally sustainable diets and identify taxes/subsidies as relevant instruments. To quantify the scope of necessary tax levels to achieve dietary recommendations on EU average, we apply three established economic models. Our business-as-usual food intake projections stress the need for policy intervention to resolve continued divergence from nutrition guidelines. Our findings suggest that food group specific taxes are effective in reaching nutrition and environmental sustainability targets. However, considerable tax levels are required to achieve the targeted consumption shifts, inducing a discussion about alternative policy designs and current model limitations. A coherent policy package is suggested to approach nutrition and sustainability objectives simultaneously.

    @article{LATKA2021100437,
    title = "Paying the price for environmentally sustainable and healthy EU diets",
    journal = "Global Food Security",
    volume = "28",
    pages = "100437",
    year = "2021",
    issn = "2211-9124",
    doi = "https://doi.org/10.1016/j.gfs.2020.100437",
    url = "http://www.sciencedirect.com/science/article/pii/S2211912420300912",
    author = "Catharina Latka and Marijke Kuiper and Stefan Frank and Thomas Heckelei and Petr Havlík and Heinz-Peter Witzke and Adrian Leip and Hao David Cui and Anneleen Kuijsten and Johanna M. Geleijnse and Michiel {van Dijk}",
    abstract = "We review consumer-side interventions and their effectiveness to support a transition to healthier and more environmentally sustainable diets and identify taxes/subsidies as relevant instruments. To quantify the scope of necessary tax levels to achieve dietary recommendations on EU average, we apply three established economic models. Our business-as-usual food intake projections stress the need for policy intervention to resolve continued divergence from nutrition guidelines. Our findings suggest that food group specific taxes are effective in reaching nutrition and environmental sustainability targets. However, considerable tax levels are required to achieve the targeted consumption shifts, inducing a discussion about alternative policy designs and current model limitations. A coherent policy package is suggested to approach nutrition and sustainability objectives simultaneously."
    }

2020

  • H. E. Ahrends, S. Siebert, E. E. Rezaei, S. J. Seidel, H. Hüging, F. Ewert, T. Döring, V. Rueda-Ayala, W. Eugster, and T. Gaiser, “Nutrient supply affects the yield stability of major European crops—a 50 year study,” Environmental Research Letters, vol. 16, iss. 1, p. 14003, 2020. doi:10.1088/1748-9326/abc849
    [BibTeX] [PDF]

    Yield stability is important for food security and a sustainable crop production, especially under changing climatic conditions. It is well known that the variability of yields is linked to changes in meteorological conditions. However, little is known about the long-term effects of agronomic management strategies, such as the supply of important nutrients. We analysed the stability of four major European crops grown between 1955 and 2008 at a long-term fertilization experiment located in Germany. Six fertilizer treatments ranged from no fertilization over the omission of individual macronutrients to complete mineral fertilization with all major macronutrients (nitrogen, phosphorus, potassium and calcium). Yield stability was estimated for each crop × treatment combination using the relative yield deviation in each year from the corresponding (nonlinear) trend value (relative yield anomalies (RYA)). Stability was lowest for potato, followed by sugar beet and winter wheat and highest for winter rye. Stability was highest when soils had received all nutrients with the standard deviation of RYA being two to three times lower than for unfertilized plots. The omission of nitrogen and potassium was associated with a decrease in yield stability and a decrease in the number of simultaneous positive and negative yield anomalies among treatments. Especially in root crops nutrient supply strongly influenced both annual yield anomalies and changes in anomalies over time. During the second half of the observation period yield stability decreased for sugar beet and increased for winter wheat. Potato yields were more stable during the second period, but only under complete nutrient supply. The critical role of potassium supply for yield stability suggests potential links to changes in the water balance during the last decades. Results demonstrate the need to explicitly consider the response of crops to long-term nutrient supply for understanding and predicting changes in yield stability.

    @article{Ahrends_2020,
    doi = {10.1088/1748-9326/abc849},
    url = {https://doi.org/10.1088/1748-9326/abc849},
    year = 2020,
    month = {dec},
    publisher = {{IOP} Publishing},
    volume = {16},
    number = {1},
    pages = {014003},
    author = {Hella Ellen Ahrends and Stefan Siebert and Ehsan Eyshi Rezaei and Sabine Julia Seidel and Hubert Hüging and Frank Ewert and Thomas Döring and Victor Rueda-Ayala and Werner Eugster and Thomas Gaiser},
    title = {Nutrient supply affects the yield stability of major European crops{\textemdash}a 50 year study},
    journal = {Environmental Research Letters},
    abstract = {Yield stability is important for food security and a sustainable crop production, especially under changing climatic conditions. It is well known that the variability of yields is linked to changes in meteorological conditions. However, little is known about the long-term effects of agronomic management strategies, such as the supply of important nutrients. We analysed the stability of four major European crops grown between 1955 and 2008 at a long-term fertilization experiment located in Germany. Six fertilizer treatments ranged from no fertilization over the omission of individual macronutrients to complete mineral fertilization with all major macronutrients (nitrogen, phosphorus, potassium and calcium). Yield stability was estimated for each crop × treatment combination using the relative yield deviation in each year from the corresponding (nonlinear) trend value (relative yield anomalies (RYA)). Stability was lowest for potato, followed by sugar beet and winter wheat and highest for winter rye. Stability was highest when soils had received all nutrients with the standard deviation of RYA being two to three times lower than for unfertilized plots. The omission of nitrogen and potassium was associated with a decrease in yield stability and a decrease in the number of simultaneous positive and negative yield anomalies among treatments. Especially in root crops nutrient supply strongly influenced both annual yield anomalies and changes in anomalies over time. During the second half of the observation period yield stability decreased for sugar beet and increased for winter wheat. Potato yields were more stable during the second period, but only under complete nutrient supply. The critical role of potassium supply for yield stability suggests potential links to changes in the water balance during the last decades. Results demonstrate the need to explicitly consider the response of crops to long-term nutrient supply for understanding and predicting changes in yield stability.}
    }

  • T. Boas, H. Bogena, T. Grünwald, B. Heinesch, D. Ryu, M. Schmidt, H. Vereecken, A. Western, and H. -J. Hendricks-Franssen, “Improving the representation of cropland sites in the Community Land Model (CLM) version 5.0,” Geoscientific Model Development Discussions, vol. 2020, p. 1–37, 2020. doi:10.5194/gmd-2020-241
    [BibTeX] [PDF]
    @Article{gmd-2020-241,
    AUTHOR = {Boas, T. and Bogena, H. and Gr\"unwald, T. and Heinesch, B. and Ryu, D. and Schmidt, M. and Vereecken, H. and Western, A. and Hendricks-Franssen, H.-J.},
    TITLE = {Improving the representation of cropland sites in the
    Community Land Model (CLM) version 5.0},
    JOURNAL = {Geoscientific Model Development Discussions},
    VOLUME = {2020},
    YEAR = {2020},
    PAGES = {1--37},
    URL = {https://gmd.copernicus.org/preprints/gmd-2020-241/},
    DOI = {10.5194/gmd-2020-241}
    }

  • P. Welke, F. Seiffarth, M. Kamp, and S. Wrobel, “HOPS: Probabilistic Subtree Mining for Small and Large Graphs,” in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining , New York, NY, USA, 2020, p. 1275–1284. doi:10.1145/3394486.3403180
    [BibTeX] [PDF]

    Frequent subgraph mining, i.e., the identification of relevant patterns in graph databases, is a well-known data mining problem with high practical relevance, since next to summarizing the data, the resulting patterns can also be used to define powerful domain-specific similarity functions for prediction. In recent years, significant progress has been made towards subgraph mining algorithms that scale to complex graphs by focusing on tree patterns and probabilistically allowing a small amount of incompleteness in the result. Nonetheless, the complexity of the pattern matching component used for deciding subtree isomorphism on arbitrary graphs has significantly limited the scalability of existing approaches. In this paper, we adapt sampling techniques from mathematical combinatorics to the problem of probabilistic subtree mining in arbitrary databases of many small to medium-size graphs or a single large graph. By restricting on tree patterns, we provide an algorithm that approximately counts or decides subtree isomorphism for arbitrary transaction graphs in sub-linear time with one-sided error. Our empirical evaluation on a range of benchmark graph datasets shows that the novel algorithm substantially outperforms state-of-the-art approaches both in the task of approximate counting of embeddings in single large graphs and in probabilistic frequent subtree mining in large databases of small to medium sized graphs.

    @inproceedings{10.1145/3394486.3403180,
    author = {Welke, Pascal and Seiffarth, Florian and Kamp, Michael and Wrobel, Stefan},
    title = {HOPS: Probabilistic Subtree Mining for Small and Large Graphs},
    year = {2020},
    isbn = {9781450379984},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3394486.3403180},
    doi = {10.1145/3394486.3403180},
    abstract = {Frequent subgraph mining, i.e., the identification of relevant patterns in graph databases, is a well-known data mining problem with high practical relevance, since next to summarizing the data, the resulting patterns can also be used to define powerful domain-specific similarity functions for prediction. In recent years, significant progress has been made towards subgraph mining algorithms that scale to complex graphs by focusing on tree patterns and probabilistically allowing a small amount of incompleteness in the result. Nonetheless, the complexity of the pattern matching component used for deciding subtree isomorphism on arbitrary graphs has significantly limited the scalability of existing approaches. In this paper, we adapt sampling techniques from mathematical combinatorics to the problem of probabilistic subtree mining in arbitrary databases of many small to medium-size graphs or a single large graph. By restricting on tree patterns, we provide an algorithm that approximately counts or decides subtree isomorphism for arbitrary transaction graphs in sub-linear time with one-sided error. Our empirical evaluation on a range of benchmark graph datasets shows that the novel algorithm substantially outperforms state-of-the-art approaches both in the task of approximate counting of embeddings in single large graphs and in probabilistic frequent subtree mining in large databases of small to medium sized graphs.},
    booktitle = {Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining},
    pages = {1275–1284},
    numpages = {10},
    location = {Virtual Event, CA, USA},
    series = {KDD '20}
    }

  • A. Bonerath, B. Niedermann, J. Diederich, Y. Orgeig, J. Oehrlein, and J. Haunert, “A Time-Windowed Data Structure for Spatial Density Maps,” in Proceedings of the 28th International Conference on Advances in Geographic Information Systems , New York, NY, USA, 2020, p. 15–24. doi:10.1145/3397536.3422242
    [BibTeX] [PDF]

    The visualization of spatio-temporal data helps researchers understand global processes such as animal migration. In particular, interactively restricting the data to different time windows reveals new insights into the short-term and long-term changes of the research data. Inspired by this use case, we consider the visualization of point data annotated with time stamps. We pick up classical, grid-based density maps as the underlying visualization technique and enhance them with an efficient data structure for arbitrarily specified time-window queries. The running time of the queries is logarithmic in the total number of points and linear in the number of actually colored cells. In experiments on real-world data we show that the data structure answers time-window queries within milliseconds, which supports the interactive exploration of large point sets. Further, the data structure can be used to visualize additional decision problems, e.g., it can answer whether the sum or maximum of additional weights given with the points exceed a certain threshold. We have defined the data structure general enough to also support multiple thresholds expressed by different colors.

    @inproceedings{bhn-twdssdm-20,
    abstract = {The visualization of spatio-temporal data helps researchers understand global processes such as animal migration. In particular, interactively restricting the data to different time windows reveals new insights into the short-term and long-term changes of the research data. Inspired by this use case, we consider the visualization of point data annotated with time stamps. We pick up classical, grid-based density maps as the underlying visualization technique and enhance them with an efficient data structure for arbitrarily specified time-window queries. The running time of the queries is logarithmic in the total number of points and linear in the number of actually colored cells. In experiments on real-world data we show that the data structure answers time-window queries within milliseconds, which supports the interactive exploration of large point sets. Further, the data structure can be used to visualize additional decision problems, e.g., it can answer whether the sum or maximum of additional weights given with the points exceed a certain threshold. We have defined the data structure general enough to also support multiple thresholds expressed by different colors.},
    address = {New York, NY, USA},
    author = {Bonerath, Annika and Niedermann, Benjamin and Diederich, Jim and Orgeig, Yannick and Oehrlein, Johannes and Haunert, Jan-Henrik},
    booktitle = {Proceedings of the 28th International Conference on Advances in Geographic Information Systems},
    doi = {10.1145/3397536.3422242},
    isbn = {9781450380195},
    keywords = {density maps, time-windowed data structure, point set},
    location = {Seattle, WA, USA},
    numpages = {10},
    pages = {15–24},
    publisher = {Association for Computing Machinery},
    series = {SIGSPATIAL '20},
    title = {A Time-Windowed Data Structure for Spatial Density Maps},
    url = {https://doi.org/10.1145/3397536.3422242},
    year = {2020}
    }

  • M. T. de Moraes, Debiasi H., J. C. Franchini, A. A. Mastroberti, R. Levien, D. Leitner, and A. Schnepf, “Soil compaction impacts soybean root growth in an Oxisol from subtropical Brazil,” Soil & Tillage Research, vol. 200, 2020.
    [BibTeX]
    @article{Moraes2020str,
    title = "Soil compaction impacts soybean root growth in an Oxisol from subtropical Brazil",
    journal = "Soil \& Tillage Research",
    volume = "200",
    year = "2020",
    author = "de Moraes, M. T. and Debiasi, H., and Franchini, J. C. and Mastroberti, A. A. and Levien, R. and Leitner, D. and Schnepf, A.",
    }

  • N. Chebrolu, T. Laebe, and C. Stachniss, “Spatio-Temporal Non-Rigid Registration of 3D Point Clouds of Plants,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2020.
    [BibTeX] [PDF] [Video]
    @InProceedings{chebrolu2020icra,
    title = {Spatio-Temporal Non-Rigid Registration of 3D Point Clouds of Plants},
    author = {N. Chebrolu and T. Laebe and C. Stachniss},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = {2020},
    url = {http://www.ipb.uni-bonn.de/pdfs/chebrolu2020icra.pdf},
    videourl = {https://www.youtube.com/watch?v=uGkep_aelBc},
    }

  • A. Ahmadi, L. Nardi, N. Chebrolu, and C. Stachniss, “Visual Servoing-based Navigation for Monitoring Row-Crop Fields,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2020.
    [BibTeX] [PDF] [Code] [Video]
    @InProceedings{ahmadi2020icra,
    title = {Visual Servoing-based Navigation for Monitoring Row-Crop Fields},
    author = {A. Ahmadi and L. Nardi and N. Chebrolu and C. Stachniss},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = {2020},
    url = {http://arxiv.org/pdf/1909.12754},
    codeurl = {https://github.com/PRBonn/visual-crop-row-navigation},
    videourl = {https://youtu.be/0qg6n4sshHk},
    }

  • X. Wu, S. Aravecchia, P. Lottes, C. Stachniss, and C. Pradalier, “Robotic Weed Control Using Automated Weed and Crop Classification,” Journal of Field Robotics, vol. 37, pp. 322-340, 2020.
    [BibTeX] [PDF]
    @Article{wu2020jfr,
    title = {Robotic Weed Control Using Automated Weed and Crop Classification},
    author = {X. Wu and S. Aravecchia and P. Lottes and C. Stachniss and C. Pradalier},
    journal = {Journal of Field Robotics},
    year = {2020},
    volume = {37},
    numer = {2},
    pages = {322-340},
    url = {http://www.ipb.uni-bonn.de/pdfs/wu2020jfr.pdf},
    }

  • L. Nardi and C. Stachniss, “Long-Term Robot Navigation in Indoor Environments Estimating Patterns in Traversability Changes,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2020.
    [BibTeX] [PDF] [Video]
    @InProceedings{nardi2020icra,
    title = {Long-Term Robot Navigation in Indoor Environments Estimating Patterns in Traversability Changes},
    author = {L. Nardi and C. Stachniss},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = {2020},
    url = {http://arxiv.org/pdf/1909.12733},
    videourl = {https://www.youtube.com/watch?v=9lNcA3quzwU},
    }

  • X. Chen, T. Läbe, A. Milioto, T. Röhling, O. Vysotska, A. Haag, J. Behley, and C. Stachniss, “OverlapNet: Loop Closing for LiDAR-based SLAM,” in Proceedings of Robotics: Science and Systems (RSS) , 2020.
    [BibTeX] [PDF] [Code] [Video]
    @inproceedings{chen2020rss,
    author = {X. Chen and T. L\"abe and A. Milioto and T. R\"ohling and O. Vysotska and A. Haag and J. Behley and C. Stachniss},
    title = {{OverlapNet: Loop Closing for LiDAR-based SLAM}},
    booktitle = {Proceedings of Robotics: Science and Systems (RSS)},
    year = {2020},
    codeurl = {https://github.com/PRBonn/OverlapNet/},
    videourl = {https://youtu.be/YTfliBco6aw},
    url = {https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/chen2020rss.pdf},
    }

  • A. Milioto, J. Behley, C. McCool, and C. Stachniss, “LiDAR Panoptic Segmentation for Autonomous Driving.” 2020.
    [BibTeX] [PDF] [Video]
    @inproceedings{milioto2020iros,
    author = {A. Milioto and J. Behley and C. McCool and C. Stachniss},
    title = {{LiDAR Panoptic Segmentation for Autonomous Driving}},
    booktitle = iros,
    year = {2020},
    videourl = {https://www.youtube.com/watch?v=C9CTQSosr9I},
    url = {https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/milioto2020iros.pdf},
    }

  • S. R. Tracy, K. A. Nagel, J. A. Postma, H. Fassbender, A. Wasson, and M. Watt, “Crop Improvement from Phenotyping Roots: Highlights Reveal Expanding Opportunities,” Trends in Plant Science, vol. 25, iss. 1, pp. 105-118, 2020. doi:https://doi.org/10.1016/j.tplants.2019.10.015
    [BibTeX] [PDF]

    Root systems determine the water and nutrients for photosynthesis and harvested products, underpinning agricultural productivity. We highlight 11 programs that integrated root traits into germplasm for breeding, relying on phenotyping. Progress was successful but slow. Today’s phenotyping technologies will speed up root trait improvement. They combine multiple new alleles in germplasm for target environments, in parallel. Roots and shoots are detected simultaneously and nondestructively, seed to seed measures are automated, and field and laboratory technologies are increasingly linked. Available simulation models can aid all phenotyping decisions. This century will see a shift from single root traits to rhizosphere selections that can be managed dynamically on farms and a shift to phenotype-based improvement to accommodate the dynamic complexity of whole crop systems.

    @article{TRACY2020105,
    title = "Crop Improvement from Phenotyping Roots: Highlights Reveal Expanding Opportunities",
    journal = "Trends in Plant Science",
    volume = "25",
    number = "1",
    pages = "105 - 118",
    year = "2020",
    issn = "1360-1385",
    doi = "https://doi.org/10.1016/j.tplants.2019.10.015",
    url = "http://www.sciencedirect.com/science/article/pii/S1360138519302845",
    author = "Saoirse R. Tracy and Kerstin A. Nagel and Johannes A. Postma and Heike Fassbender and Anton Wasson and Michelle Watt",
    keywords = "root architecture, simulation model, combinatorial stresses, rhizosphere, agronomy, soil, breeding, water, climate, imaging",
    abstract = "Root systems determine the water and nutrients for photosynthesis and harvested products, underpinning agricultural productivity. We highlight 11 programs that integrated root traits into germplasm for breeding, relying on phenotyping. Progress was successful but slow. Today’s phenotyping technologies will speed up root trait improvement. They combine multiple new alleles in germplasm for target environments, in parallel. Roots and shoots are detected simultaneously and nondestructively, seed to seed measures are automated, and field and laboratory technologies are increasingly linked. Available simulation models can aid all phenotyping decisions. This century will see a shift from single root traits to rhizosphere selections that can be managed dynamically on farms and a shift to phenotype-based improvement to accommodate the dynamic complexity of whole crop systems."
    }

  • D. Wallach, T. Palosuo, P. Thorburn, Z. Hochman, E. Gourdain, F. Andrianasolo, S. Asseng, B. Basso, S. Buis, N. Crout, C. Dibari, B. Dumont, R. Ferrise, T. Gaiser, C. Garcia, S. Gayler, A. Ghahramani, S. Hiremath, S. Hoek, H. Horan, G. Hoogenboom, M. Huang, M. Jabloun, P. Jansson, Q. Jing, E. Justes, K. C. Kersebaum, A. Klosterhalfen, M. Launay, E. Lewan, Q. Luo, B. Maestrini, H. Mielenz, M. Moriondo, H. N. Zadeh, G. Padovan, J. E. Olesen, A. Poyda, E. Priesack, J. W. M. Pullens, B. Qian, N. Schütze, V. Shelia, A. Souissi, X. Specka, A. K. Srivastava, T. Stella, T. Streck, G. Trombi, E. Wallor, J. Wang, T. K. D. Weber, L. Weihermüller, A. de Wit, T. Wöhling, L. Xiao, C. Zhao, Y. Zhu, and S. J. Seidel, “The chaos in calibrating crop models,” bioRxiv, 2020. doi:10.1101/2020.09.12.294744
    [BibTeX] [PDF]

    Calibration, the estimation of model parameters based on fitting the model to experimental data, is among the first steps in essentially every application of crop models and process models in other fields and has an important impact on simulated values. The goal of this study is to develop a comprehensive list of the decisions involved in calibration and to identify the range of choices made in practice, as groundwork for developing guidelines for crop model calibration starting with phenology. Three groups of decisions are identified; the criterion for choosing the parameter values, the choice of parameters to estimate and numerical aspects of parameter estimation. It is found that in practice there is a large diversity of choices for every decision, even among modeling groups using the same model structure. These findings are relevant to process models in other fields.HighlightsWe documented calibration procedures in two multi-model studiesGroups differ in criteria for best parameters, parameters to estimate and softwareThere are important differences even between groups using the same model structureCompeting Interest StatementThe authors have declared no competing interest.

    @article {Wallach2020.09.12.294744,
    author = {Wallach, Daniel and Palosuo, Taru and Thorburn, Peter and Hochman, Zvi and Gourdain, Emmanuelle and Andrianasolo, Fety and Asseng, Senthold and Basso, Bruno and Buis, Samuel and Crout, Neil and Dibari, Camilla and Dumont, Benjamin and Ferrise, Roberto and Gaiser, Thomas and Garcia, Cecile and Gayler, Sebastian and Ghahramani, Afshin and Hiremath, Santosh and Hoek, Steven and Horan, Heidi and Hoogenboom, Gerrit and Huang, Mingxia and Jabloun, Mohamed and Jansson, Per-Erik and Jing, Qi and Justes, Eric and Kersebaum, Kurt Christian and Klosterhalfen, Anne and Launay, Marie and Lewan, Elisabet and Luo, Qunying and Maestrini, Bernardo and Mielenz, Henrike and Moriondo, Marco and Zadeh, Hasti Nariman and Padovan, Gloria and Olesen, J{\o}rgen Eivind and Poyda, Arne and Priesack, Eckart and Pullens, Johannes Wilhelmus Maria and Qian, Budong and Sch{\"u}tze, Niels and Shelia, Vakhtang and Souissi, Amir and Specka, Xenia and Srivastava, Amit Kumar and Stella, Tommaso and Streck, Thilo and Trombi, Giacomo and Wallor, Evelyn and Wang, Jing and Weber, Tobias K.D. and Weiherm{\"u}ller, Lutz and de Wit, Allard and W{\"o}hling, Thomas and Xiao, Liujun and Zhao, Chuang and Zhu, Yan and Seidel, Sabine J.},
    title = {The chaos in calibrating crop models},
    elocation-id = {2020.09.12.294744},
    year = {2020},
    doi = {10.1101/2020.09.12.294744},
    publisher = {Cold Spring Harbor Laboratory},
    abstract = {Calibration, the estimation of model parameters based on fitting the model to experimental data, is among the first steps in essentially every application of crop models and process models in other fields and has an important impact on simulated values. The goal of this study is to develop a comprehensive list of the decisions involved in calibration and to identify the range of choices made in practice, as groundwork for developing guidelines for crop model calibration starting with phenology. Three groups of decisions are identified; the criterion for choosing the parameter values, the choice of parameters to estimate and numerical aspects of parameter estimation. It is found that in practice there is a large diversity of choices for every decision, even among modeling groups using the same model structure. These findings are relevant to process models in other fields.HighlightsWe documented calibration procedures in two multi-model studiesGroups differ in criteria for best parameters, parameters to estimate and softwareThere are important differences even between groups using the same model structureCompeting Interest StatementThe authors have declared no competing interest.},
    URL = {https://www.biorxiv.org/content/early/2020/09/14/2020.09.12.294744},
    eprint = {https://www.biorxiv.org/content/early/2020/09/14/2020.09.12.294744.full.pdf},
    journal = {bioRxiv}
    }

  • O. Zatsarynna, J. Sawatzky, and J. Gall, “Discovering Latent Classes for Semi-Supervised Semantic Segmentation,” in DAGM German Conference on Pattern Recognition (GCPR) , 2020.
    [BibTeX] [PDF]
    @inproceedings{zatsarynna2020gcpr,
    author = {Zatsarynna, O. and Sawatzky, J. and Gall, J.},
    title = {{Discovering Latent Classes for Semi-Supervised Semantic Segmentation}},
    booktitle = {DAGM German Conference on Pattern Recognition (GCPR)},
    year = 2020,
    url = {http://pages.iai.uni-bonn.de/gall_juergen/download/jgall_latentclasses_gcpr2020.pdf},
    }

  • W. Amelung, D. Bossio, W. de Vries, I. Kögel-Knabner, J. Lehmann, R. Amundson, R. Bol, C. Collins, R. Lal, J. Leifeld, B. Minasny, G. Pan, K. Paustian, C. Rumpel, J. Sanderman, J. W. van Groenigen, S. Mooney, B. van Wesemael, M. Wander, and A. Chabbi, “Towards a global-scale soil climate mitigation strategy,” Nature Communications, vol. 11, 2020. doi:10.1038/s41467-020-18887-7
    [BibTeX] [PDF]

    {Sustainable soil carbon sequestration practices need to be rapidly scaled up and implemented to contribute to climate change mitigation. We highlight that the major potential for carbon sequestration is in cropland soils, especially those with large yield gaps and/or large historic soil organic carbon losses. The implementation of soil carbon sequestration measures requires a diverse set of options, each adapted to local soil conditions and management opportunities, and accounting for site-specific trade-offs. We propose the establishment of a soil information system containing localised information on soil group, degradation status, crop yield gap, and the associated carbon-sequestration potentials, as well as the provision of incentives and policies to translate management options into region- and soil-specific practices.}

    @article{amelung2020,
    author = {W. Amelung and D. Bossio and W. de Vries and I. Kögel-Knabner and J. Lehmann and R. Amundson and R. Bol and C. Collins and R. Lal and J. Leifeld and B. Minasny and G. Pan and K. Paustian and C. Rumpel and J. Sanderman and J. W. van Groenigen and S. Mooney and B. van Wesemael and M. Wander and A. Chabbi},
    title = "{Towards a global-scale soil climate mitigation strategy}",
    journal = {Nature Communications},
    volume = {11},
    year = {2020},
    month = {10},
    abstract = "{Sustainable soil carbon sequestration practices need to be rapidly scaled up and implemented to contribute to climate change mitigation. We highlight that the major potential for carbon sequestration is in cropland soils, especially those with large yield gaps and/or large historic soil organic carbon losses. The implementation of soil carbon sequestration measures requires a diverse set of options, each adapted to local soil conditions and management opportunities, and accounting for site-specific trade-offs. We propose the establishment of a soil information system containing localised information on soil group, degradation status, crop yield gap, and the associated carbon-sequestration potentials, as well as the provision of incentives and policies to translate management options into region- and soil-specific practices.}",
    doi = {10.1038/s41467-020-18887-7},
    url = {https://doi.org/10.1038/s41467-020-18887-7}
    }

  • H. Webber, G. Lischeid, M. Sommer, R. Finger, C. Nendel, T. Gaiser, and F. Ewert, “No perfect storm for crop yield failure in Germany,” Environmental Research Letters, vol. 15, iss. 10, p. 104012, 2020. doi:10.1088/1748-9326/aba2a4
    [BibTeX] [PDF]

    Large-scale crop yield failures are increasingly associated with food price spikes and food insecurity and are a large source of income risk for farmers. While the evidence linking extreme weather to yield failures is clear, consensus on the broader set of weather drivers and conditions responsible for recent yield failures is lacking. We investigate this for the case of four major crops in Germany over the past 20 years using a combination of machine learning and process-based modelling. Our results confirm that years associated with widespread yield failures across crops were generally associated with severe drought, such as in 2018 and to a lesser extent 2003. However, for years with more localized yield failures and large differences in spatial patterns of yield failures between crops, no single driver or combination of drivers was identified. Relatively large residuals of unexplained variation likely indicate the importance of non-weather related factors, such as management (pest, weed and nutrient management and possible interactions with weather) explaining yield failures. Models to inform adaptation planning at farm, market or policy levels are here suggested to require consideration of cumulative resource capture and use, as well as effects of extreme events, the latter largely missing in process-based models. However, increasingly novel combinations of weather events under climate change may limit the extent to which data driven methods can replace process-based models in risk assessments.

    @article{Webber_2020,
    doi = {10.1088/1748-9326/aba2a4},
    url = {https://doi.org/10.1088%2F1748-9326%2Faba2a4},
    year = 2020,
    month = {sep},
    publisher = {{IOP} Publishing},
    volume = {15},
    number = {10},
    pages = {104012},
    author = {Heidi Webber and Gunnar Lischeid and Michael Sommer and Robert Finger and Claas Nendel and Thomas Gaiser and Frank Ewert},
    title = {No perfect storm for crop yield failure in Germany},
    journal = {Environmental Research Letters},
    abstract = {Large-scale crop yield failures are increasingly associated with food price spikes and food insecurity and are a large source of income risk for farmers. While the evidence linking extreme weather to yield failures is clear, consensus on the broader set of weather drivers and conditions responsible for recent yield failures is lacking. We investigate this for the case of four major crops in Germany over the past 20 years using a combination of machine learning and process-based modelling. Our results confirm that years associated with widespread yield failures across crops were generally associated with severe drought, such as in 2018 and to a lesser extent 2003. However, for years with more localized yield failures and large differences in spatial patterns of yield failures between crops, no single driver or combination of drivers was identified. Relatively large residuals of unexplained variation likely indicate the importance of non-weather related factors, such as management (pest, weed and nutrient management and possible interactions with weather) explaining yield failures. Models to inform adaptation planning at farm, market or policy levels are here suggested to require consideration of cumulative resource capture and use, as well as effects of extreme events, the latter largely missing in process-based models. However, increasingly novel combinations of weather events under climate change may limit the extent to which data driven methods can replace process-based models in risk assessments.}
    }

  • J. Yi, L. Krusenbaum, P. Unger, H. Hüging, S. J. Seidel, G. Schaaf, and J. Gall, “Deep Learning for Non-Invasive Diagnosis of Nutrient Deficiencies in Sugar Beet Using RGB Images,” Sensors, vol. 12, 2020. doi:10.3390/s20205893
    [BibTeX] [PDF]

    {In order to enable timely actions to prevent major losses of crops caused by lack of nutrients and, hence, increase the potential yield throughout the growing season while at the same time prevent excess fertilization with detrimental environmental consequences, early, non-invasive, and on-site detection of nutrient deficiency is required. Current non-invasive methods for assessing the nutrient status of crops deal in most cases with nitrogen (N) deficiency only and optical sensors to diagnose N deficiency, such as chlorophyll meters or canopy reflectance sensors, do not monitor N, but instead measure changes in leaf spectral properties that may or may not be caused by N deficiency. In this work, we study how well nutrient deficiency symptoms can be recognized in RGB images of sugar beets. To this end, we collected the Deep Nutrient Deficiency for Sugar Beet (DND-SB) dataset, which contains 5648 images of sugar beets growing on a long-term fertilizer experiment with nutrient deficiency plots comprising N, phosphorous (P), and potassium (K) deficiency, as well as the omission of liming (Ca), full fertilization, and no fertilization at all. We use the dataset to analyse the performance of five convolutional neural networks for recognizing nutrient deficiency symptoms and discuss their limitations.}

    @article{yi2020deep,
    author = {Yi, Jinhui and Krusenbaum, Lukas and Unger, Paula and Hüging, Hubert and Seidel, Sabine J and Schaaf, Gabriel and Gall, Juergen},
    title = "{Deep Learning for Non-Invasive Diagnosis of Nutrient Deficiencies in Sugar Beet Using RGB Images}",
    journal = {Sensors},
    volume = {12},
    year = {2020},
    month = {10},
    abstract = "{In order to enable timely actions to prevent major losses of crops caused by lack of nutrients and, hence, increase the potential yield throughout the growing season while at the same time prevent excess fertilization with detrimental environmental consequences, early, non-invasive, and on-site detection of nutrient deficiency is required. Current non-invasive methods for assessing the nutrient status of crops deal in most cases with nitrogen (N) deficiency only and optical sensors to diagnose N deficiency, such as chlorophyll meters or canopy reflectance sensors, do not monitor N, but instead measure changes in leaf spectral properties that may or may not be caused by N deficiency. In this work, we study how well nutrient deficiency symptoms can be recognized in RGB images of sugar beets. To this end, we collected the Deep Nutrient Deficiency for Sugar Beet (DND-SB) dataset, which contains 5648 images of sugar beets growing on a long-term fertilizer experiment with nutrient deficiency plots comprising N, phosphorous (P), and potassium (K) deficiency, as well as the omission of liming (Ca), full fertilization, and no fertilization at all. We use the dataset to analyse the performance of five convolutional neural networks for recognizing nutrient deficiency symptoms and discuss their limitations.}",
    doi = {10.3390/s20205893},
    url = {https://doi.org/10.3390/s20205893}
    }

  • B. H. Gebrekidan, T. Heckelei, and S. Rasch, “Characterizing Farmers and Farming System in Kilombero Valley Floodplain, Tanzania,” Sustainability, vol. 12, 2020. doi:10.3390/su12177114
    [BibTeX] [PDF]

    {Recognizing the diversity of farmers is crucial for the success of agricultural, rural, or environmental programs and policies aimed at the sustainable use of natural resources. In this study, based on survey data collected in the Kilombero Valley Floodplain (KVF) in Tanzania, we design a typology of farmers to describe the range of farm types and farming systems systematically, and to understand their livelihood and land use behavior. The KVF is the largest, low-altitude, seasonally-flooded, freshwater wetland in East Africa. Despite its values, KVF is a very fragile ecosystem threatened by current and future human interventions. We apply multivariate statistical analysis (a combination of principal component analysis and cluster analysis) to identify farm groups that are homogenous within and heterogeneous between groups. Three farm types were identified: “Monocrop rice producer”, “Diversifier”, and “Agropastoralist”. Monocrop rice producers are the dominant farm types, accounting for 65 percent of the farm households in the valley, characterized by more than 80 percent of the land allocated to rice, showing strong market participation and high utilization of labor. Diversifiers, on the other hand, allocate more land to maize and vegetables. Agropastoralists account for 7 percent of the surveyed farmers and differ from the other two groups by, on average, larger land ownership, a combination of livestock and crop production, and larger household sizes. This typology represents the diversity of farmers in KVF concerning their land use and livelihood strategy, and will allow to target policy interventions. Besides, it may also inform further research about the diverse landscape of floodplain farming, through the classification and interpretation of different socio-economic positions of farm households.}

    @article{gebrekidan2020,
    author = {Gebrekidan, Bisrat Haile and Heckelei, Thomas and Rasch, Sebastian},
    title = "{Characterizing Farmers and Farming System in Kilombero Valley Floodplain, Tanzania}",
    journal = {Sustainability},
    volume = {12},
    year = {2020},
    month = {08},
    abstract = "{Recognizing the diversity of farmers is crucial for the success of agricultural, rural, or environmental programs and policies aimed at the sustainable use of natural resources. In this study, based on survey data collected in the Kilombero Valley Floodplain (KVF) in Tanzania, we design a typology of farmers to describe the range of farm types and farming systems systematically, and to understand their livelihood and land use behavior. The KVF is the largest, low-altitude, seasonally-flooded, freshwater wetland in East Africa. Despite its values, KVF is a very fragile ecosystem threatened by current and future human interventions. We apply multivariate statistical analysis (a combination of principal component analysis and cluster analysis) to identify farm groups that are homogenous within and heterogeneous between groups. Three farm types were identified: “Monocrop rice producer”, “Diversifier”, and “Agropastoralist”. Monocrop rice producers are the dominant farm types, accounting for 65 percent of the farm households in the valley, characterized by more than 80 percent of the land allocated to rice, showing strong market participation and high utilization of labor. Diversifiers, on the other hand, allocate more land to maize and vegetables. Agropastoralists account for 7 percent of the surveyed farmers and differ from the other two groups by, on average, larger land ownership, a combination of livestock and crop production, and larger household sizes. This typology represents the diversity of farmers in KVF concerning their land use and livelihood strategy, and will allow to target policy interventions. Besides, it may also inform further research about the diverse landscape of floodplain farming, through the classification and interpretation of different socio-economic positions of farm households.}",
    doi = {10.3390/su12177114},
    url = {https://doi.org/10.3390/su12177114}
    }

  • T. Zaenker, F. Verdoja, and V. Kyrki, “Hypermap Mapping Framework and its Application to Autonomous Semantic Exploration,” in 2020 IEEE Conference on Multisensor Fusion and Integration , 2020.
    [BibTeX] [PDF]
    @inproceedings{zaenker2020hypermap,
    title={Hypermap Mapping Framework and its Application to Autonomous Semantic Exploration},
    author={Zaenker, Tobias and Verdoja, Francesco and Kyrki, Ville},
    booktitle={2020 IEEE Conference on Multisensor Fusion and Integration},
    year={2020},
    organization={IEEE},
    url = {https://arxiv.org/pdf/1909.09526.pdf}
    }

  • C. Gebauer and M. Bennewitz, “Penalized Bootstrapping for Reinforcement Learning in Robot Control,” in 2nd International Conference on Machine Learning & Applications , 2020.
    [BibTeX] [PDF]
    @inproceedings{gebauer2020penalized,
    title={Penalized Bootstrapping for Reinforcement Learning in Robot Control},
    author={Gebauer, Christopher and Bennewitz, Maren},
    booktitle={2nd International Conference on Machine Learning \& Applications},
    year={2020},
    url = {https://www.hrl.uni-bonn.de/publications/papers/gebauer20deeprl.pdf}
    }

  • P. Regier, L. Gesing, and M. Bennewitz, “Deep Reinforcement Learning for Navigation in Cluttered Environments,” in 2nd International Conference on Machine Learning & Applications , 2020.
    [BibTeX] [PDF]
    @inproceedings{regier2020deep,
    title={Deep Reinforcement Learning for Navigation in Cluttered Environments},
    author={Regier, Peter and Gesing, Lukas and Bennewitz, Maren},
    booktitle={2nd International Conference on Machine Learning \& Applications},
    year={2020},
    url = {https://www.hrl.uni-bonn.de/publications/papers/regier20cmla.pdf}
    }

  • D. Gogoll, P. Lottes, J. Weyler, N. Petrinic, and C. Stachniss, “Unsupervised Domain Adaptation for Transferring Plant Classification Systems to New Field Environments, Crops, and Robots,” in iros , 2020.
    [BibTeX] [PDF] [Video]
    @inproceedings{gogoll2020iros,
    author = {D. Gogoll and P. Lottes and J. Weyler and N. Petrinic and C. Stachniss},
    title = {{Unsupervised Domain Adaptation for Transferring Plant Classification Systems to New Field Environments, Crops, and Robots}},
    booktitle = iros,
    year = {2020},
    url = {http://www.ipb.uni-bonn.de/pdfs/gogoll2020iros.pdf},
    videourl = {https://www.youtube.com/watch?v=6K79Ih6KXTs},
    }

  • F. Magistri, N. Chebrolu, and C. Stachniss, “Segmentation-Based 4D Registration of Plants Point Clouds for Phenotyping,” in iros , 2020.
    [BibTeX] [PDF] [Video]
    @inproceedings{magistri2020iros,
    author = {F. Magistri and N. Chebrolu and C. Stachniss},
    title = {{Segmentation-Based 4D Registration of Plants Point Clouds for Phenotyping}},
    booktitle = iros,
    year = {2020},
    url={https://www.ipb.uni-bonn.de/pdfs/magistri2020iros.pdf},
    videourl = {https://youtu.be/OV39kb5Nqg8},
    }

  • X. Chen, T. Läbe, L. Nardi, J. Behley, and C. Stachniss, “Learning an Overlap-based Observation Model for 3D LiDAR Localization,” in iros , 2020.
    [BibTeX] [PDF] [Video]
    @inproceedings{chen2020iros,
    author = {X. Chen and T. L\"abe and L. Nardi and J. Behley and C. Stachniss},
    title = {{Learning an Overlap-based Observation Model for 3D LiDAR Localization}},
    booktitle = iros,
    year = {2020},
    url={http://www.ipb.uni-bonn.de/pdfs/chen2020iros.pdf},
    videourl = {https://www.youtube.com/watch?v=BozPqy_6YcE},
    }

  • F. Langer, A. Milioto, A. Haag, J. Behley, and C. Stachniss, “Domain Transfer for Semantic Segmentation of LiDAR Data using Deep Neural Networks,” in iros , 2020.
    [BibTeX] [PDF] [Video]
    @inproceedings{langer2020iros,
    author = {F. Langer and A. Milioto and A. Haag and J. Behley and C. Stachniss},
    title = {{Domain Transfer for Semantic Segmentation of LiDAR Data using Deep Neural Networks}},
    booktitle = iros,
    year = {2020},
    url = {http://www.ipb.uni-bonn.de/pdfs/langer2020iros.pdf},
    videourl = {https://youtu.be/6FNGF4hKBD0},
    }

  • R. Sheikh, A. Milioto, P. Lottes, C. Stachniss, M. Bennewitz, and T. Schultz, “Gradient and Log-based Active Learning for Semantic Segmentation of Crop and Weed for Agricultural Robots.” 2020.
    [BibTeX] [PDF] [Video]
    @InProceedings{sheikh2020icra,
    title = {Gradient and Log-based Active Learning for Semantic Segmentation of Crop and Weed for Agricultural Robots},
    author = {R. Sheikh and A. Milioto and P. Lottes and C. Stachniss and M. Bennewitz and T. Schultz},
    booktitle = icra,
    year = {2020},
    url = {http://www.ipb.uni-bonn.de/pdfs/sheikh2020icra.pdf},
    videourl = {https://www.youtube.com/watch?v=NySa59gxFAg},
    }

  • B. Heeren, S. Paulus, H. Goldbach, H. Kuhlmann, A. Mahlein, M. Rumpf, and B. Wirth, “Statistical shape analysis of tap roots: a methodological case study on laser scanned sugar beets,” BMC Bioinformatics, vol. 21, iss. 1, 2020. doi:10.1186/s12859-020-03654-8
    [BibTeX] [PDF]

    {The efficient and robust statistical analysis of the shape of plant organs of different cultivars is an important investigation issue in plant breeding and enables a robust cultivar description within the breeding progress. Laserscanning is a highly accurate and high resolution technique to acquire the 3D shape of plant surfaces. The computation of a shape based principal component analysis (PCA) built on concepts from continuum mechanics has proven to be an effective tool for a qualitative and quantitative shape examination.}

    @article{Heeren2020,
    author = {Heeren, Behrend and Paulus, Stefan and Goldbach, Heiner and Kuhlmann, Heiner and Mahlein, Anne-Katrin and Rumpf, Martin and Wirth, Benedikt},
    title = "{Statistical shape analysis of tap roots: a methodological case study on laser scanned sugar beets}",
    journal = {BMC Bioinformatics},
    volume = {21},
    number = {1},
    year = {2020},
    month = {07},
    abstract = "{The efficient and robust statistical analysis of the shape of plant organs of different cultivars is an important investigation issue in plant breeding and enables a robust cultivar description within the breeding progress. Laserscanning is a highly accurate and high resolution technique to acquire the 3D shape of plant surfaces. The computation of a shape based principal component analysis (PCA) built on concepts from continuum mechanics has proven to be an effective tool for a qualitative and quantitative shape examination.}",
    issn = {1471-2105},
    doi = {10.1186/s12859-020-03654-8},
    url = {https://doi.org/10.1186/s12859-020-03654-8}
    }

  • S. Paulus and A. Mahlein, “Technical workflows for hyperspectral plant image assessment and processing on the greenhouse and laboratory scale,” GigaScience, vol. 9, iss. 8, 2020. doi:10.1093/gigascience/giaa090
    [BibTeX] [PDF]

    {The use of hyperspectral cameras is well established in the field of plant phenotyping, especially as a part of high-throughput routines in greenhouses. Nevertheless, the workflows used differ depending on the applied camera, the plants being imaged, the experience of the users, and the measurement set-up.This review describes a general workflow for the assessment and processing of hyperspectral plant data at greenhouse and laboratory scale. Aiming at a detailed description of possible error sources, a comprehensive literature review of possibilities to overcome these errors and influences is provided. The processing of hyperspectral data of plants starting from the hardware sensor calibration, the software processing steps to overcome sensor inaccuracies, and the preparation for machine learning is shown and described in detail. Furthermore, plant traits extracted from spectral hypercubes are categorized to standardize the terms used when describing hyperspectral traits in plant phenotyping. A scientific data perspective is introduced covering information for canopy, single organs, plant development, and also combined traits coming from spectral and 3D measuring devices.This publication provides a structured overview on implementing hyperspectral imaging into biological studies at greenhouse and laboratory scale. Workflows have been categorized to define a trait-level scale according to their metrological level and the processing complexity. A general workflow is shown to outline procedures and requirements to provide fully calibrated data of the highest quality. This is essential for differentiation of the smallest changes from hyperspectral reflectance of plants, to track and trace hyperspectral development as an answer to biotic or abiotic stresses.}

    @article{10.1093/gigascience/giaa090,
    author = {Paulus, Stefan and Mahlein, Anne-Katrin},
    title = "{Technical workflows for hyperspectral plant image assessment and processing on the greenhouse and laboratory scale}",
    journal = {GigaScience},
    volume = {9},
    number = {8},
    year = {2020},
    month = {08},
    abstract = "{The use of hyperspectral cameras is well established in the field of plant phenotyping, especially as a part of high-throughput routines in greenhouses. Nevertheless, the workflows used differ depending on the applied camera, the plants being imaged, the experience of the users, and the measurement set-up.This review describes a general workflow for the assessment and processing of hyperspectral plant data at greenhouse and laboratory scale. Aiming at a detailed description of possible error sources, a comprehensive literature review of possibilities to overcome these errors and influences is provided. The processing of hyperspectral data of plants starting from the hardware sensor calibration, the software processing steps to overcome sensor inaccuracies, and the preparation for machine learning is shown and described in detail. Furthermore, plant traits extracted from spectral hypercubes are categorized to standardize the terms used when describing hyperspectral traits in plant phenotyping. A scientific data perspective is introduced covering information for canopy, single organs, plant development, and also combined traits coming from spectral and 3D measuring devices.This publication provides a structured overview on implementing hyperspectral imaging into biological studies at greenhouse and laboratory scale. Workflows have been categorized to define a trait-level scale according to their metrological level and the processing complexity. A general workflow is shown to outline procedures and requirements to provide fully calibrated data of the highest quality. This is essential for differentiation of the smallest changes from hyperspectral reflectance of plants, to track and trace hyperspectral development as an answer to biotic or abiotic stresses.}",
    issn = {2047-217X},
    doi = {10.1093/gigascience/giaa090},
    url = {https://doi.org/10.1093/gigascience/giaa090},
    note = {giaa090},
    eprint = {https://academic.oup.com/gigascience/article-pdf/9/8/giaa090/33667602/giaa090.pdf},
    }

  • P. Schramowski, W. Stammer, S. Teso, A. Brugger, F. Herbert, X. Shao, H. Luigs, A. Mahlein, and K. Kersting, “Making deep neural networks right for the right scientific reasons by interacting with their explanations,” Nature Machine Intelligence, vol. 2, 2020. doi:10.1038/s42256-020-0212-3
    [BibTeX] [PDF]

    Deep neural networks have demonstrated excellent performances in many real-world applications. Unfortunately, they may show Clever Hans-like behaviour (making use of confounding factors within datasets) to achieve high performance. In this work we introduce the novel learning setting of explanatory interactive learning and illustrate its benefits on a plant phenotyping research task. Explanatory interactive learning adds the scientist into the training loop, who interactively revises the original model by providing feedback on its explanations. Our experimental results demonstrate that explanatory interactive learning can help to avoid Clever Hans moments in machine learning and encourages (or discourages, if appropriate) trust in the underlying model.

    @article{Schramowski2020,
    title = "Making deep neural networks right for the right scientific reasons by interacting with their explanations",
    journal = "Nature Machine Intelligence",
    volume = "2",
    year = "2020",
    issn = "2522-5839",
    doi = "10.1038/s42256-020-0212-3",
    url = "https://doi.org/10.1038/s42256-020-0212-3",
    author = "Schramowski, Patrick and Stammer, Wolfgang and Teso, Stefano and Brugger, Anna and Herbert, Franziska and Shao, Xiaoting and Luigs, Hans-Georg and Mahlein, Anne-Katrin and Kersting, Kristian",
    abstract = "Deep neural networks have demonstrated excellent performances in many real-world applications. Unfortunately, they may show Clever Hans-like behaviour (making use of confounding factors within datasets) to achieve high performance. In this work we introduce the novel learning setting of explanatory interactive learning and illustrate its benefits on a plant phenotyping research task. Explanatory interactive learning adds the scientist into the training loop, who interactively revises the original model by providing feedback on its explanations. Our experimental results demonstrate that explanatory interactive learning can help to avoid Clever Hans moments in machine learning and encourages (or discourages, if appropriate) trust in the underlying model."
    }

  • M. Langensiepen, M. A. K. Jansen, A. Wingler, B. Demmig-Adams, W. W. Adams, I. C. Dodd, V. Fotopoulos, R. Snowdon, E. Fenollosa, M. C. De Tullio, G. Buck-Sorlin, and S. Munné-Bosch, “Linking integrative plant physiology with agronomy to sustain future plant production,” Environmental and Experimental Botany, vol. 178, p. 104125, 2020. doi:https://doi.org/10.1016/j.envexpbot.2020.104125
    [BibTeX] [PDF]

    Sustainable production of high-quality food is one of today’s major challenges of agriculture. To achieve this goal, a better understanding of plant physiological processes and a more integrated approach with respect to current agronomical practices are needed. In this review, various examples of cooperation between integrative plant physiology and agronomy are discussed, and this demonstrates the complexity of these interrelations. The examples are meant to stimulate discussions on how both research areas can deliver solutions to avoid looming food crises due to population growth and climate change. In the last decades, unprecedented progress has been made in the understanding of how plants grow and develop in a variety of environments and in response to biotic stresses, but appropriate management and interpretation of the resulting complex datasets remains challenging. After providing an historical overview of integrative plant physiology, we discuss possible avenues of integration, involving advances in integrative plant physiology, to sustain plant production in the current post-omics era. Finally, recommendations are provided on how to practice the transdisciplinary mindset required, emphasising a broader approach to sustainable production of high-quality food in the future, whereby all those who are involved are made partners in knowledge generation processes through transdisciplinary cooperation.

    @article{LANGENSIEPEN2020104125,
    title = "Linking integrative plant physiology with agronomy to sustain future plant production",
    journal = "Environmental and Experimental Botany",
    volume = "178",
    pages = "104125",
    year = "2020",
    issn = "0098-8472",
    doi = "https://doi.org/10.1016/j.envexpbot.2020.104125",
    url = "http://www.sciencedirect.com/science/article/pii/S0098847220301519",
    author = "Matthias Langensiepen and Marcel A.K. Jansen and Astrid Wingler and Barbara Demmig-Adams and William W. Adams and Ian C. Dodd and Vasileios Fotopoulos and Rod Snowdon and Erola Fenollosa and Mario C. {De Tullio} and Gerhard Buck-Sorlin and Sergi Munné-Bosch",
    keywords = "Food production, Molecular plant biology, Plant physiology, Agronomy, Sustainability, Transdisciplinarity",
    abstract = "Sustainable production of high-quality food is one of today’s major challenges of agriculture. To achieve this goal, a better understanding of plant physiological processes and a more integrated approach with respect to current agronomical practices are needed. In this review, various examples of cooperation between integrative plant physiology and agronomy are discussed, and this demonstrates the complexity of these interrelations. The examples are meant to stimulate discussions on how both research areas can deliver solutions to avoid looming food crises due to population growth and climate change. In the last decades, unprecedented progress has been made in the understanding of how plants grow and develop in a variety of environments and in response to biotic stresses, but appropriate management and interpretation of the resulting complex datasets remains challenging. After providing an historical overview of integrative plant physiology, we discuss possible avenues of integration, involving advances in integrative plant physiology, to sustain plant production in the current post-omics era. Finally, recommendations are provided on how to practice the transdisciplinary mindset required, emphasising a broader approach to sustainable production of high-quality food in the future, whereby all those who are involved are made partners in knowledge generation processes through transdisciplinary cooperation."
    }

  • J. Bömer, L. Zabawa, P. Sieren, A. Kicherer, L. Klingbeil, U. Rascher, O. Muller, H. Kuhlmann, and R. Roscher, Automatic Differentiation of Damaged and Unharmed Grapes Using RGB Images and Convolutional Neural Networks, 2020.
    [BibTeX]
    @misc{bömer2929,
    title={Automatic Differentiation of Damaged and Unharmed Grapes Using RGB Images and Convolutional Neural Networks},
    author={Bömer, J and Zabawa, L and Sieren, P and Kicherer, A and Klingbeil, L and Rascher, U and Muller, O and Kuhlmann, H and Roscher, R},
    year={2020},
    booktitle={Conference on Computer Vision (ECCV)}
    }

  • J. Quenzel, R. A. Rosu, T. Läbe, C. Stachniss, and S. Behnke, Beyond Photometric Consistency: Gradient-based Dissimilarity for Improving Visual Odometry and Stereo Matching, 2020.
    [BibTeX]
    @misc{quenzel2020photometric,
    title={Beyond Photometric Consistency: Gradient-based Dissimilarity for Improving Visual Odometry and Stereo Matching},
    author={Jan Quenzel and Radu Alexandru Rosu and Thomas Läbe and Cyrill Stachniss and Sven Behnke},
    year={2020},
    eprint={2004.04090},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
    }

  • A. Barreto, S. Paulus, M. Varrelmann, and A. Mahlein, “Hyperspectral imaging of symptoms induced by Rhizoctonia solani in sugar beet: comparison of input data and different machine learning algorithms,” Journal of Plant Diseases and Protection, vol. 127, iss. 4, 2020. doi:10.1007/s41348-020-00344-8
    [BibTeX] [PDF]

    The fungal pathogen Rhizoctonia solani is one of the most important soil-borne diseases in sugar beet production worldwide. Root and crown rot caused by this fungus are traditionally recognized later in the cropping season by rating the above-ground symptoms like wilting and chlorosis on foliage, and dark brown lesions at the base of petioles. The present study was designed to evaluate noninvasive sensors and machine learning for measuring disease incidence and early detection. Eight-weeks-old plants were inoculated with the pathogen in two different concentrations and under controlled conditions. Hyperspectral images in the visible and near-infrared range from leaf were obtained in time-series. One hundred thirty and fifteen spectral features were selected in two levels by using the recursive feature elimination method (RFE) and a clustering approach. Subsequently, five types of machine-learning methods were employed to train four types of spectral data containing reflectance values, vegetation indices, selected variables of the RFE process and selected variables of an RFE-clustering process. The best classifier was obtained from a partial least squares modeling process and required a number of 15 spectral features, which include first and second derivatives of the wavelength spectrum as well as the Ctr3, EVI and PSSRa vegetation index. This investigation proves that under controlled conditions early detection of indirect symptoms caused by Rhizoctonia root rot in sugar-beet plants is possible. Scoring of disease incidence of Rhizoctonia root rot at 10 dai was 3 to 5 times higher with a machine-learning classifier in comparison with the human visual rating.

    @Article{Barreto2020,
    AUTHOR = {Barreto, Abel and Paulus, Stefan and Varrelmann, Mark and Mahlein, Anne-Katrin},
    TITLE = {Hyperspectral imaging of symptoms induced by Rhizoctonia solani in sugar beet: comparison of input data and different machine learning algorithms},
    JOURNAL = {Journal of Plant Diseases and Protection},
    VOLUME = {127},
    YEAR = {2020},
    NUMBER = {4},
    URL = {https://doi.org/10.1007/s41348-020-00344-8},
    ISSN = {1861-3837},
    ABSTRACT = {The fungal pathogen Rhizoctonia solani is one of the most important soil-borne diseases in sugar beet production worldwide. Root and crown rot caused by this fungus are traditionally recognized later in the cropping season by rating the above-ground symptoms like wilting and chlorosis on foliage, and dark brown lesions at the base of petioles. The present study was designed to evaluate noninvasive sensors and machine learning for measuring disease incidence and early detection. Eight-weeks-old plants were inoculated with the pathogen in two different concentrations and under controlled conditions. Hyperspectral images in the visible and near-infrared range from leaf were obtained in time-series. One hundred thirty and fifteen spectral features were selected in two levels by using the recursive feature elimination method (RFE) and a clustering approach. Subsequently, five types of machine-learning methods were employed to train four types of spectral data containing reflectance values, vegetation indices, selected variables of the RFE process and selected variables of an RFE-clustering process. The best classifier was obtained from a partial least squares modeling process and required a number of 15 spectral features, which include first and second derivatives of the wavelength spectrum as well as the Ctr3, EVI and PSSRa vegetation index. This investigation proves that under controlled conditions early detection of indirect symptoms caused by Rhizoctonia root rot in sugar-beet plants is possible. Scoring of disease incidence of Rhizoctonia root rot at 10 dai was 3 to 5 times higher with a machine-learning classifier in comparison with the human visual rating.},
    DOI = {10.1007/s41348-020-00344-8}
    }

  • F. Savian, M. Martini, P. Ermacora, S. Paulus, and A. Mahlein, “Prediction of the Kiwifruit Decline Syndrome in Diseased Orchards by Remote Sensing,” Remote Sensing, vol. 12, iss. 14, 2020. doi:10.3390/rs12142194
    [BibTeX] [PDF]

    Eight years after the first record in Italy, Kiwifruit Decline (KD), a destructive disease causing root rot, has already affected more than 25% of the area under kiwifruit cultivation in Italy. Diseased plants are characterised by severe decay of the fine roots and sudden wilting of the canopy, which is only visible after the season’s first period of heat (July–August). The swiftness of symptom appearance prevents correct timing and positioning for sampling of the disease, and is therefore a barrier to aetiological studies. The aim of this study is to test the feasibility of thermal and multispectral imaging for the detection of KD using an unsupervised classifier. Thus, RGB, multispectral and thermal data from a kiwifruit orchard, with healthy and diseased plants, were acquired simultaneously during two consecutive growing seasons (2017–2018) using an Unmanned Aerial Vehicle (UAV) platform. Data reduction was applied to the clipped areas of the multispectral and thermal data from the 2017 survey. Reduced data were then classified with two unsupervised algorithms, a K-means and a hierarchical method. The plant vigour (canopy size and presence/absence of wilted leaves) and the health shifts exhibited by asymptomatic plants between 2017 and 2018 were evaluated from RGB data via expert assessment and used as the ground truth for cluster interpretation. Multispectral data showed a high correlation with plant vigour, while temperature data demonstrated a good potential use in predicting health shifts, especially in highly vigorous plants that were asymptomatic in 2017 and became symptomatic in 2018. The accuracy of plant vigour assessment was above 73% when using multispectral data, while clustering of the temperature data allowed the prediction of disease outbreak one year in advance, with an accuracy of 71%. Based on our results, the unsupervised clustering of remote sensing data could be a reliable tool for the identification of sampling areas, and can greatly improve aetiological studies of this new disease in kiwifruit.

    @Article{rs12142194,
    AUTHOR = {Savian, Francesco and Martini, Marta and Ermacora, Paolo and Paulus, Stefan and Mahlein, Anne-Katrin},
    TITLE = {Prediction of the Kiwifruit Decline Syndrome in Diseased Orchards by Remote Sensing},
    JOURNAL = {Remote Sensing},
    VOLUME = {12},
    YEAR = {2020},
    NUMBER = {14},
    ARTICLE-NUMBER = {2194},
    URL = {https://www.mdpi.com/2072-4292/12/14/2194},
    ISSN = {2072-4292},
    ABSTRACT = {Eight years after the first record in Italy, Kiwifruit Decline (KD), a destructive disease causing root rot, has already affected more than 25% of the area under kiwifruit cultivation in Italy. Diseased plants are characterised by severe decay of the fine roots and sudden wilting of the canopy, which is only visible after the season’s first period of heat (July–August). The swiftness of symptom appearance prevents correct timing and positioning for sampling of the disease, and is therefore a barrier to aetiological studies. The aim of this study is to test the feasibility of thermal and multispectral imaging for the detection of KD using an unsupervised classifier. Thus, RGB, multispectral and thermal data from a kiwifruit orchard, with healthy and diseased plants, were acquired simultaneously during two consecutive growing seasons (2017–2018) using an Unmanned Aerial Vehicle (UAV) platform. Data reduction was applied to the clipped areas of the multispectral and thermal data from the 2017 survey. Reduced data were then classified with two unsupervised algorithms, a K-means and a hierarchical method. The plant vigour (canopy size and presence/absence of wilted leaves) and the health shifts exhibited by asymptomatic plants between 2017 and 2018 were evaluated from RGB data via expert assessment and used as the ground truth for cluster interpretation. Multispectral data showed a high correlation with plant vigour, while temperature data demonstrated a good potential use in predicting health shifts, especially in highly vigorous plants that were asymptomatic in 2017 and became symptomatic in 2018. The accuracy of plant vigour assessment was above 73% when using multispectral data, while clustering of the temperature data allowed the prediction of disease outbreak one year in advance, with an accuracy of 71%. Based on our results, the unsupervised clustering of remote sensing data could be a reliable tool for the identification of sampling areas, and can greatly improve aetiological studies of this new disease in kiwifruit.},
    DOI = {10.3390/rs12142194}
    }

  • F. Jonard, D. S. Cannière, N. Brüggemann, P. Gentine, S. D. J. Gianotti, G. Lobet, D. G. Miralles, C. Montzka, B. R. Pagán, U. Rascher, and H. Vereecken, “Value of sun-induced chlorophyll fluorescence for quantifying hydrological states and fluxes: Current status and challenges,” Agricultural and Forest Meteorology, vol. 291, p. 108088, 2020. doi:https://doi.org/10.1016/j.agrformet.2020.108088
    [BibTeX] [PDF]

    Predictions of hydrological states and fluxes, especially transpiration, are poorly constrained in hydrological models due to large uncertainties in parameterization and process description. Novel technologies like remote sensing of sun-induced chlorophyll fluorescence (SIF)—which provides information from the photosynthetic apparatus—may help in constraining water cycle components. This paper discusses the nature of the plant physiological basis of the fluorescence signal and analyses the current literature linking hydrological states and fluxes to SIF. Given the connection between photosynthesis and transpiration, through the water use efficiency, SIF may serve as a pertinent constraint for hydrological models. The FLuorescence EXplorer (FLEX) satellite, planned to be launched in 2023, is expected to provide spatially high-resolution measurements of red and far-red SIF complementing the products from existing satellite missions and the high-temporal resolution products from upcoming geostationary missions. This new data stream may allow us to better constrain plant transpiration, assess the impacts of water stress on plants, and infer processes occurring in the root zone through the soil-plant water column. To make optimal use of this data, progress needs to be made in 1) our process representation of spatially aggregated fluorescence signals from spaceborne SIF instruments, 2) integration of fluorescence processes in hydrological models—particularly when paired with other satellite data, 3) quantifying the impact of soil moisture on SIF across scales, and 4) assessment of the accuracy of SIF measurements—especially from space.

    @article{JONARD2020108088,
    title = "Value of sun-induced chlorophyll fluorescence for quantifying hydrological states and fluxes: Current status and challenges",
    journal = "Agricultural and Forest Meteorology",
    volume = "291",
    pages = "108088",
    year = "2020",
    issn = "0168-1923",
    doi = "https://doi.org/10.1016/j.agrformet.2020.108088",
    url = "http://www.sciencedirect.com/science/article/pii/S0168192320301908",
    author = "F. Jonard and S. De Cannière and N. Brüggemann and P. Gentine and D.J. Short Gianotti and G. Lobet and D.G. Miralles and C. Montzka and B.R. Pagán and U. Rascher and H. Vereecken",
    keywords = "Solar-induced chlorophyll fluorescence, Soil water availability, Drought stress, Transpiration, Hydrological processes, Radiative transfer model",
    abstract = "Predictions of hydrological states and fluxes, especially transpiration, are poorly constrained in hydrological models due to large uncertainties in parameterization and process description. Novel technologies like remote sensing of sun-induced chlorophyll fluorescence (SIF)—which provides information from the photosynthetic apparatus—may help in constraining water cycle components. This paper discusses the nature of the plant physiological basis of the fluorescence signal and analyses the current literature linking hydrological states and fluxes to SIF. Given the connection between photosynthesis and transpiration, through the water use efficiency, SIF may serve as a pertinent constraint for hydrological models. The FLuorescence EXplorer (FLEX) satellite, planned to be launched in 2023, is expected to provide spatially high-resolution measurements of red and far-red SIF complementing the products from existing satellite missions and the high-temporal resolution products from upcoming geostationary missions. This new data stream may allow us to better constrain plant transpiration, assess the impacts of water stress on plants, and infer processes occurring in the root zone through the soil-plant water column. To make optimal use of this data, progress needs to be made in 1) our process representation of spatially aggregated fluorescence signals from spaceborne SIF instruments, 2) integration of fluorescence processes in hydrological models—particularly when paired with other satellite data, 3) quantifying the impact of soil moisture on SIF across scales, and 4) assessment of the accuracy of SIF measurements—especially from space."
    }

  • P. Gaugler, V. Gaugler, M. Kamleitner, and G. Schaaf, “Extraction and Quantification of Soluble, Radiolabeled Inositol Polyphosphates from Different Plant Species using SAX-HPLC,” Journal of Visualized Experiments, iss. 160, 2020. doi:10.3791/61495
    [BibTeX] [PDF]
    @article{gaugler_gaugler_kamleitner_schaaf_2020,
    title={Extraction and Quantification of Soluble, Radiolabeled Inositol Polyphosphates from Different Plant Species using SAX-HPLC},
    url={https://www.jove.com/video/61495/extraction-quantification-soluble-radiolabeled-inositol},
    DOI={10.3791/61495},
    number={160},
    journal={Journal of Visualized Experiments},
    author={Philipp Gaugler and Verena Gaugler and Marília Kamleitner and Gabriel Schaaf},
    year={2020},
    month={Jun}
    }

  • P. Schramowski, W. Stammer, S. Teso, A. Brugger, X. Shao, H. Luigs, A. Mahlein, and K. Kersting, Right for the Wrong Scientific Reasons: Revising Deep Networks by Interacting with their Explanations, 2020.
    [BibTeX]
    @misc{schramowski2020right,
    title={Right for the Wrong Scientific Reasons: Revising Deep Networks by Interacting with their Explanations},
    author={Patrick Schramowski and Wolfgang Stammer and Stefano Teso and Anna Brugger and Xiaoting Shao and Hans-Georg Luigs and Anne-Katrin Mahlein and Kristian Kersting},
    year={2020},
    eprint={2001.05371},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
    }

  • C. H. Bock, J. G. A. Barbedo, E. D. M. Ponte, D. Bohnenkamp, and A. Mahlein, “From visual estimates to fully automated sensor-based measurements of plant disease severity: status and challenges for improving accuracy,” Phytopathology Research 2, 2020. doi:https://doi.org/10.1186/s42483-020-00049-8
    [BibTeX] [PDF]

    The severity of plant diseases, traditionally the proportion of the plant tissue exhibiting symptoms, is a key quantitative variable to know for many diseases and is prone to error. Good quality disease severity data should be accurate (close to the true value). Earliest quantification of disease severity was by visual estimates. Sensor-based image analysis including visible spectrum and hyperspectral and multispectral sensors are established technologies that promise to substitute, or complement visual ratings. Indeed, these technologies have measured disease severity accurately under controlled conditions but are yet to demonstrate their full potential for accurate measurement under field conditions. Sensor technology is advancing rapidly, and artificial intelligence may help overcome issues for automating severity measurement under hyper-variable field conditions. The adoption of appropriate scales, training, instruction and aids (standard area diagrams) has contributed to improved accuracy of visual estimates. The apogee of accuracy for visual estimation is likely being approached, and any remaining increases in accuracy are likely to be small. Due to automation and rapidity, sensor-based measurement offers potential advantages compared with visual estimates, but the latter will remain important for years to come. Mobile, automated sensor-based systems will become increasingly common in controlled conditions and, eventually, in the field for measuring plant disease severity for the purpose of research and decision making.

    @article{Bock2020,
    title = "From visual estimates to fully automated sensor-based measurements of plant disease severity: status and challenges for improving accuracy",
    journal = "Phytopathology Research 2",
    year = "2020",
    issn = "2524-4167",
    doi = "https://doi.org/10.1186/s42483-020-00049-8",
    url = "https://phytopatholres.biomedcentral.com/articles/10.1186/s42483-020-00049-8",
    author = "Clive H. Bock and Jayme G. A. Barbedo and Emerson M. Del Ponte and David Bohnenkamp and Anne-Katrin Mahlein",
    abstract = "The severity of plant diseases, traditionally the proportion of the plant tissue exhibiting symptoms, is a key quantitative variable to know for many diseases and is prone to error. Good quality disease severity data should be accurate (close to the true value). Earliest quantification of disease severity was by visual estimates. Sensor-based image analysis including visible spectrum and hyperspectral and multispectral sensors are established technologies that promise to substitute, or complement visual ratings. Indeed, these technologies have measured disease severity accurately under controlled conditions but are yet to demonstrate their full potential for accurate measurement under field conditions. Sensor technology is advancing rapidly, and artificial intelligence may help overcome issues for automating severity measurement under hyper-variable field conditions. The adoption of appropriate scales, training, instruction and aids (standard area diagrams) has contributed to improved accuracy of visual estimates. The apogee of accuracy for visual estimation is likely being approached, and any remaining increases in accuracy are likely to be small. Due to automation and rapidity, sensor-based measurement offers potential advantages compared with visual estimates, but the latter will remain important for years to come. Mobile, automated sensor-based systems will become increasingly common in controlled conditions and, eventually, in the field for measuring plant disease severity for the purpose of research and decision making."
    }

  • B. Müller, F. Hoffmann, T. Heckelei, C. Müller, T. W. Hertel, G. J. Polhill, M. [. Wijk], T. Achterbosch, P. Alexander, C. Brown, D. Kreuer, F. Ewert, J. Ge, J. D. A. Millington, R. Seppelt, P. H. Verburg, and H. Webber, “Modelling food security: Bridging the gap between the micro and the macro scale,” Global Environmental Change, vol. 63, p. 102085, 2020. doi:https://doi.org/10.1016/j.gloenvcha.2020.102085
    [BibTeX] [PDF]

    Achieving food and nutrition security for all in a changing and globalized world remains a critical challenge of utmost importance. The development of solutions benefits from insights derived from modelling and simulating the complex interactions of the agri-food system, which range from global to household scales and transcend disciplinary boundaries. A wide range of models based on various methodologies (from food trade equilibrium to agent-based) seek to integrate direct and indirect drivers of change in land use, environment and socio-economic conditions at different scales. However, modelling such interaction poses fundamental challenges, especially for representing non-linear dynamics and adaptive behaviours. We identify key pieces of the fragmented landscape of food security modelling, and organize achievements and gaps into different contextual domains of food security (production, trade, and consumption) at different spatial scales. Building on in-depth reflection on three core issues of food security – volatility, technology, and transformation – we identify methodological challenges and promising strategies for advancement. We emphasize particular requirements related to the multifaceted and multiscale nature of food security. They include the explicit representation of transient dynamics to allow for path dependency and irreversible consequences, and of household heterogeneity to incorporate inequality issues. To illustrate ways forward we provide good practice examples using meta-modelling techniques, non-equilibrium approaches and behavioural-based modelling endeavours. We argue that further integration of different model types is required to better account for both multi-level agency and cross-scale feedbacks within the food system.

    @article{MULLER2020102085,
    title = "Modelling food security: Bridging the gap between the micro and the macro scale",
    journal = "Global Environmental Change",
    volume = "63",
    pages = "102085",
    year = "2020",
    issn = "0959-3780",
    doi = "https://doi.org/10.1016/j.gloenvcha.2020.102085",
    url = "http://www.sciencedirect.com/science/article/pii/S0959378019307277",
    author = "Birgit Müller and Falk Hoffmann and Thomas Heckelei and Christoph Müller and Thomas W. Hertel and J. Gareth Polhill and Mark [van Wijk] and Thom Achterbosch and Peter Alexander and Calum Brown and David Kreuer and Frank Ewert and Jiaqi Ge and James D.A. Millington and Ralf Seppelt and Peter H. Verburg and Heidi Webber",
    keywords = "Food security, Multi-scale interactions, Model integration, Agent-based models, Economic equilibrium models, Crop models, Social-ecological feedbacks, Land use",
    abstract = "Achieving food and nutrition security for all in a changing and globalized world remains a critical challenge of utmost importance. The development of solutions benefits from insights derived from modelling and simulating the complex interactions of the agri-food system, which range from global to household scales and transcend disciplinary boundaries. A wide range of models based on various methodologies (from food trade equilibrium to agent-based) seek to integrate direct and indirect drivers of change in land use, environment and socio-economic conditions at different scales. However, modelling such interaction poses fundamental challenges, especially for representing non-linear dynamics and adaptive behaviours. We identify key pieces of the fragmented landscape of food security modelling, and organize achievements and gaps into different contextual domains of food security (production, trade, and consumption) at different spatial scales. Building on in-depth reflection on three core issues of food security – volatility, technology, and transformation – we identify methodological challenges and promising strategies for advancement. We emphasize particular requirements related to the multifaceted and multiscale nature of food security. They include the explicit representation of transient dynamics to allow for path dependency and irreversible consequences, and of household heterogeneity to incorporate inequality issues. To illustrate ways forward we provide good practice examples using meta-modelling techniques, non-equilibrium approaches and behavioural-based modelling endeavours. We argue that further integration of different model types is required to better account for both multi-level agency and cross-scale feedbacks within the food system."
    }

  • L. Zabawa, A. Kicherer, L. Klingbeil, R. Töpfer, H. Kuhlmann, and R. Roscher, “Counting of grapevine berries in images via semantic segmentation using convolutional neural networks,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 164, pp. 73-83, 2020. doi:https://doi.org/10.1016/j.isprsjprs.2020.04.002
    [BibTeX] [PDF]

    The extraction of phenotypic traits is often very time and labour intensive. Especially the investigation in viticulture is restricted to an on-site analysis due to the perennial nature of grapevine. Traditionally skilled experts examine small samples and extrapolate the results to a whole plot. Thereby different grapevine varieties and training systems, e.g. vertical shoot positioning (VSP) and semi minimal pruned hedges (SMPH) pose different challenges. In this paper we present an objective framework based on automatic image analysis which works on two different training systems. The images are collected semi automatic by a camera system which is installed in a modified grape harvester. The system produces overlapping images from the sides of the plants. Our framework uses a convolutional neural network to detect single berries in images by performing a semantic segmentation. Each berry is then counted with a connected component algorithm. We compare our results with the Mask-RCNN, a state-of-the-art network for instance segmentation and with a regression approach for counting. The experiments presented in this paper show that we are able to detect green berries in images despite of different training systems. We achieve an accuracy for the berry detection of 94.0% in the VSP and 85.6% in the SMPH.

    @article{ZABAWA202073,
    title = "Counting of grapevine berries in images via semantic segmentation using convolutional neural networks",
    journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
    volume = "164",
    pages = "73 - 83",
    year = "2020",
    issn = "0924-2716",
    doi = "https://doi.org/10.1016/j.isprsjprs.2020.04.002",
    url = "http://www.sciencedirect.com/science/article/pii/S0924271620300939",
    author = "Laura Zabawa and Anna Kicherer and Lasse Klingbeil and Reinhard Töpfer and Heiner Kuhlmann and Ribana Roscher",
    keywords = "Deep learning, Semantic segmentation, Geoinformation, High-throughput analysis, Plant phenotyping, Vitis",
    abstract = "The extraction of phenotypic traits is often very time and labour intensive. Especially the investigation in viticulture is restricted to an on-site analysis due to the perennial nature of grapevine. Traditionally skilled experts examine small samples and extrapolate the results to a whole plot. Thereby different grapevine varieties and training systems, e.g. vertical shoot positioning (VSP) and semi minimal pruned hedges (SMPH) pose different challenges. In this paper we present an objective framework based on automatic image analysis which works on two different training systems. The images are collected semi automatic by a camera system which is installed in a modified grape harvester. The system produces overlapping images from the sides of the plants. Our framework uses a convolutional neural network to detect single berries in images by performing a semantic segmentation. Each berry is then counted with a connected component algorithm. We compare our results with the Mask-RCNN, a state-of-the-art network for instance segmentation and with a regression approach for counting. The experiments presented in this paper show that we are able to detect green berries in images despite of different training systems. We achieve an accuracy for the berry detection of 94.0% in the VSP and 85.6% in the SMPH."
    }

  • A. Bonerath, J. -H. Haunert, and B. Niedermann, “Tight Rectilinear Hulls of Simple Polygons,” in Proceedings of the 36th European Workshop on Computational Geometry (EuroCG’20) , 2020.
    [BibTeX] [PDF]

    A polygon is called C-oriented if the orientations of all its edges stem from a pre-defined set C. The schematization of a polygon is then a C-oriented polygon that describes and simplifies the shape of the input polygon with respect to given hard and soft constraints. We study the case that the C-oriented polygon needs to contain the input polygon such that it is tight in the sense that it cannot be shrunk without starting to overlap with the input polygon; we call this a tight C-hull of the polygon. We restrict the tight C-hull to be a simple polygon. We aim at a tight C-hull that optimally balances the number of bends, the total edge length and the enclosed area. For the case that both polygons are rectilinear, we present a dynamic-programming approach that yields such a tight hull in polynomial time. For arbitrary simple polygons we can use the same approach to obtain approximate tight rectilinear hulls.

    @inproceedings{bhn-trhsp-20,
    abstract = {A polygon is called C-oriented if the orientations of all its edges stem from a pre-defined set C. The schematization of a polygon is then a C-oriented polygon that describes and simplifies the shape of the input polygon with respect to given hard and soft constraints. We study the case that the C-oriented polygon needs to contain the input polygon such that it is tight in the sense that it cannot be shrunk without starting to overlap with the input polygon; we call this a tight C-hull of the polygon. We restrict the tight C-hull to be a simple polygon. We aim at a tight C-hull that optimally balances the number of bends, the total edge length and the enclosed area. For the case that both polygons are rectilinear, we present a dynamic-programming approach that yields such a tight hull in polynomial time. For arbitrary simple polygons we can use the same approach to obtain approximate tight rectilinear hulls.},
    author = {Bonerath, A. and Haunert, J.-H. and Niedermann, B.},
    booktitle = {Proceedings of the 36th European Workshop on Computational Geometry (EuroCG'20)},
    note = {Preprint.},
    title = {{Tight Rectilinear Hulls of Simple Polygons}},
    url = {http://www1.pub.informatik.uni-wuerzburg.de/eurocg2020/data/uploads/eurocg20_proceedings.pdf},
    year = {2020}
    }

  • E. Heinz, C. Holst, H. Kuhlmann, and L. Klingbeil, “Design and Evaluation of a Permanently Installed Plane-Based Calibration Field for Mobile Laser Scanning Systems,” Remote Sensing, vol. 12, iss. 3, 2020. doi:10.3390/rs12030555
    [BibTeX] [PDF]

    Mobile laser scanning has become an established measuring technique that is used for many applications in the fields of mapping, inventory, and monitoring. Due to the increasing operationality of such systems, quality control w.r.t. calibration and evaluation of the systems becomes more and more important and is subject to on-going research. This paper contributes to this topic by using tools from geodetic configuration analysis in order to design and evaluate a plane-based calibration field for determining the lever arm and boresight angles of a 2D laser scanner w.r.t. a GNSS/IMU unit (Global Navigation Satellite System, Inertial Measurement Unit). In this regard, the impact of random, systematic, and gross observation errors on the calibration is analyzed leading to a plane setup that provides accurate and controlled calibration parameters. The designed plane setup is realized in the form of a permanently installed calibration field. The applicability of the calibration field is tested with a real mobile laser scanning system by frequently repeating the calibration. Empirical standard deviations of <1 … 1.5 mm for the lever arm and <0.005 ∘ for the boresight angles are obtained, which was priorly defined to be the goal of the calibration. In order to independently evaluate the mobile laser scanning system after calibration, an evaluation environment is realized consisting of a network of control points as well as TLS (Terrestrial Laser Scanning) reference point clouds. Based on the control points, both the horizontal and vertical accuracy of the system is found to be < 10 mm (root mean square error). This is confirmed by comparisons to the TLS reference point clouds indicating a well calibrated system. Both the calibration field and the evaluation environment are permanently installed and can be used for arbitrary mobile laser scanning systems.

    @Article{rs12030555,
    AUTHOR = {Heinz, Erik and Holst, Christoph and Kuhlmann, Heiner and Klingbeil, Lasse},
    TITLE = {Design and Evaluation of a Permanently Installed Plane-Based Calibration Field for Mobile Laser Scanning Systems},
    JOURNAL = {Remote Sensing},
    VOLUME = {12},
    YEAR = {2020},
    NUMBER = {3},
    ARTICLE-NUMBER = {555},
    URL = {https://www.mdpi.com/2072-4292/12/3/555},
    ISSN = {2072-4292},
    ABSTRACT = {Mobile laser scanning has become an established measuring technique that is used for many applications in the fields of mapping, inventory, and monitoring. Due to the increasing operationality of such systems, quality control w.r.t. calibration and evaluation of the systems becomes more and more important and is subject to on-going research. This paper contributes to this topic by using tools from geodetic configuration analysis in order to design and evaluate a plane-based calibration field for determining the lever arm and boresight angles of a 2D laser scanner w.r.t. a GNSS/IMU unit (Global Navigation Satellite System, Inertial Measurement Unit). In this regard, the impact of random, systematic, and gross observation errors on the calibration is analyzed leading to a plane setup that provides accurate and controlled calibration parameters. The designed plane setup is realized in the form of a permanently installed calibration field. The applicability of the calibration field is tested with a real mobile laser scanning system by frequently repeating the calibration. Empirical standard deviations of <1 ... 1.5 mm for the lever arm and <0.005 ∘ for the boresight angles are obtained, which was priorly defined to be the goal of the calibration. In order to independently evaluate the mobile laser scanning system after calibration, an evaluation environment is realized consisting of a network of control points as well as TLS (Terrestrial Laser Scanning) reference point clouds. Based on the control points, both the horizontal and vertical accuracy of the system is found to be < 10 mm (root mean square error). This is confirmed by comparisons to the TLS reference point clouds indicating a well calibrated system. Both the calibration field and the evaluation environment are permanently installed and can be used for arbitrary mobile laser scanning systems.},
    DOI = {10.3390/rs12030555}
    }

2019

  • F. Seiffarth, T. Horvath, and S. Wrobel, “Maximal Closed Set and Half-Space Separations in Finite Closure Systems,” in ECML/PKDD 2019 and has appeared in the Lecture Notes in Computer Science, Machine Learning and Knowledge Discovery in Databases – European Conference , 2019.
    [BibTeX]
    @inproceedings{seiffarth2019maximal,
    title={Maximal Closed Set and Half-Space Separations in Finite Closure Systems},
    author={Florian Seiffarth and Tamas Horvath and Stefan Wrobel},
    year={2019},
    booktitle = {ECML/PKDD 2019 and has appeared in the Lecture Notes in Computer Science, Machine Learning and Knowledge Discovery in Databases - European Conference},
    }

  • J. Behley, M. Garbade, A. Milioto, J. Quenzel, S. Behnke, C. Stachniss, and J. Gall, “SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences.” 2019.
    [BibTeX] [PDF] [Video]
    @InProceedings{behley2019iccv,
    author = {J. Behley and M. Garbade and A. Milioto and J. Quenzel and S. Behnke and C. Stachniss and J. Gall},
    title = {{SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences}},
    booktitle = iccv,
    year = {2019},
    url = {https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/behley2019iccv.pdf},
    videourl = {http://www.ipb.uni-bonn.de/html/projects/semantic_kitti/videos/teaser.mp4},
    }

  • E. Palazzolo, J. Behley, P. Lottes, P. Giguère, and C. Stachniss, “ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals,” in Proceedings of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS) , 2019.
    [BibTeX] [PDF] [Code] [Video]
    @InProceedings{palazzolo2019iros,
    author = {E. Palazzolo and J. Behley and P. Lottes and P. Gigu\`ere and C. Stachniss},
    title = {{ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals}},
    booktitle = {Proceedings of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS)},
    year = {2019},
    url = {http://www.ipb.uni-bonn.de/pdfs/palazzolo2019iros.pdf},
    codeurl = {https://github.com/PRBonn/refusion},
    videourl = {https://youtu.be/1P9ZfIS5-p4},
    }

  • X. Chen, A. Milioto, E. Palazzolo, P. Giguère, J. Behley, and C. Stachniss, “SuMa++: Efficient LiDAR-based Semantic SLAM,” in Proceedings of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS) , 2019.
    [BibTeX] [PDF] [Code] [Video]
    @inproceedings{chen2019iros,
    author = {X. Chen and A. Milioto and E. Palazzolo and P. Giguère and J. Behley and C. Stachniss},
    title = {{SuMa++: Efficient LiDAR-based Semantic SLAM}},
    booktitle = {Proceedings of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS)},
    year = 2019,
    codeurl = {https://github.com/PRBonn/semantic_suma/},
    videourl = {https://youtu.be/uo3ZuLuFAzk},
    url = {https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/chen2019iros.pdf},
    }

  • A. Milioto, I. Vizzo, J. Behley, and C. Stachniss, “RangeNet++: Fast and Accurate LiDAR Semantic Segmentation,” in Proceedings of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS) , 2019.
    [BibTeX] [PDF] [Code] [Video]
    @inproceedings{milioto2019iros,
    author = {A. Milioto and I. Vizzo and J. Behley and C. Stachniss},
    title = {{RangeNet++: Fast and Accurate LiDAR Semantic Segmentation}},
    booktitle = {Proceedings of the IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS)},
    year = 2019,
    codeurl = {https://github.com/PRBonn/lidar-bonnetal},
    videourl = {https://youtu.be/wuokg7MFZyU},
    url = {https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/milioto2019iros.pdf},
    }

  • F. Yan, O. Vysotska, and C. Stachniss, ” Global Localization on OpenStreetMap Using 4-bit Semantic Descriptors,” in Proceedings of the European Conference on Mobile Robots (ECMR) , 2019.
    [BibTeX] [PDF]
    @InProceedings{yan2019ecmr,
    author = {F. Yan and O. Vysotska and C. Stachniss},
    title = {{ Global Localization on OpenStreetMap Using 4-bit Semantic Descriptors}},
    booktitle = {Proceedings of the European Conference on Mobile Robots (ECMR)},
    year = {2019},
    url = {https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/yan2019ecmr.pdf}
    }

  • R. Schirmer, P. Bieber, and C. Stachniss, “Coverage Path Planning in Belief Space ,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2019.
    [BibTeX] [PDF]
    @InProceedings{schirmer2019icra,
    author = {R. Schirmer and P. Bieber and C. Stachniss},
    title = {{Coverage Path Planning in Belief Space }},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = 2019,
    url = {https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/schirmer2019icra.pdf}
    }

  • K. Huang and C. Stachniss, “Accurate Direct Visual-Laser Odometry with Explicit Occlusion Handling and Plane Detection,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2019.
    [BibTeX] [PDF]
    @InProceedings{huang2019icra,
    author = {K. Huang and C. Stachniss},
    title = {{Accurate Direct Visual-Laser Odometry with Explicit Occlusion Handling and Plane Detection}},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = 2019,
    url = {https://www.ipb.uni-bonn.de/wp-content/papercite-data/pdf/huang2019icra.pdf},
    }

  • R. A. Rosu, P. Schütt, J. Quenzel, and S. Behnke, LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices, 2019.
    [BibTeX]
    @misc{alex2019latticenet,
    title={LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices},
    author={Radu Alexandru Rosu and Peer Schütt and Jan Quenzel and Sven Behnke},
    year={2019},
    eprint={1912.05905},
    archivePrefix={arXiv},
    primaryClass={cs.CV}
    }

  • A. Bonerath, B. Niedermann, and J. -H. Haunert, “Retrieving alpha-Shapes and Schematic Polygonal Approximations for Sets of Points within Queried Temporal Ranges,” in Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems , New York, NY, USA, 2019, p. 249–258. doi:10.1145/3347146.3359087
    [BibTeX] [PDF]

    The interactive exploration of data requires data structures that can be repeatedly queried to obtain simple visualizations of parts of the data. We consider the scenario that the data is a set of points each associated with a time stamp and that the result of each query is visualized by an α-shape, which generalizes the concept of convex hulls. Instead of computing each shape independently, we suggest and analyze a simple data structure that aggregates the α-shapes of all possible queries. Once the data structure is built, it particularly allows us to query single α-shapes without retrieving the actual (possibly large) point set and thus to rapidly produce small previews of the queried data. We discuss the data structure for the original α-shapes as well as for a schematized version of α-shapes, which further simplifies the visualization. We evaluate the data structure on real-world data. The experiments indicate linear memory consumption with respect to the number of points, which makes the data structure applicable in practice, although the size is quadratic for a theoretic worst case example.

    @InProceedings{bhn-rasspa-19,
    author = {Bonerath, A. and Niedermann, B. and Haunert, J.-H.},
    title = {{Retrieving alpha-Shapes and Schematic Polygonal Approximations for Sets of Points within Queried Temporal Ranges}},
    abstract = {The interactive exploration of data requires data structures that can be repeatedly queried to obtain simple visualizations of parts of the data. We consider the scenario that the data is a set of points each associated with a time stamp and that the result of each query is visualized by an α-shape, which generalizes the concept of convex hulls. Instead of computing each shape independently, we suggest and analyze a simple data structure that aggregates the α-shapes of all possible queries. Once the data structure is built, it particularly allows us to query single α-shapes without retrieving the actual (possibly large) point set and thus to rapidly produce small previews of the queried data. We discuss the data structure for the original α-shapes as well as for a schematized version of α-shapes, which further simplifies the visualization. We evaluate the data structure on real-world data. The experiments indicate linear memory consumption with respect to the number of points, which makes the data structure applicable in practice, although the size is quadratic for a theoretic worst case example.},
    booktitle = {Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems},
    series = {SIGSPATIAL '19},
    year = {2019},
    isbn = {978-1-4503-6909-1},
    location = {Chicago, IL, USA},
    pages = {249--258},
    numpages = {10},
    url = {http://doi.acm.org/10.1145/3347146.3359087},
    doi = {10.1145/3347146.3359087},
    acmid = {3359087},
    publisher = {ACM},
    address = {New York, NY, USA},
    keywords = {alpha-shape, data structure, point set, temporal range queries},
    }

  • D. Laha, N. Parvin, A. Hofer, R. F. H. Giehl, N. Fernandez-Rebollo, N. von Wirén, A. Saiardi, H. J. Jessen, and G. Schaaf, “Arabidopsis ITPK1 and ITPK2 Have an Evolutionarily Conserved Phytic Acid Kinase Activity,” ACS Chemical Biology, vol. 14, iss. 10, pp. 2127-2133, 2019. doi:10.1021/acschembio.9b00423
    [BibTeX] [PDF]
    @article{doi:10.1021/acschembio.9b00423,
    author = {Laha, Debabrata and Parvin, Nargis and Hofer, Alexandre and Giehl, Ricardo F. H. and Fernandez-Rebollo, Nicolas and von Wirén, Nicolaus and Saiardi, Adolfo and Jessen, Henning J. and Schaaf, Gabriel},
    title = {Arabidopsis ITPK1 and ITPK2 Have an Evolutionarily Conserved Phytic Acid Kinase Activity},
    journal = {ACS Chemical Biology},
    volume = {14},
    number = {10},
    pages = {2127-2133},
    year = {2019},
    doi = {10.1021/acschembio.9b00423},
    note ={PMID: 31525024},
    url = {https://doi.org/10.1021/acschembio.9b00423},
    eprint = {https://doi.org/10.1021/acschembio.9b00423},
    }

  • H. Storm, K. Baylis, and T. Heckelei, “Machine learning in agricultural and applied economics,” European Review of Agricultural Economics, 2019. doi:10.1093/erae/jbz033
    [BibTeX] [PDF]

    {This review presents machine learning (ML) approaches from an applied economist’s perspective. We first introduce the key ML methods drawing connections to econometric practice. We then identify current limitations of the econometric and simulation model toolbox in applied economics and explore potential solutions afforded by ML. We dive into cases such as inflexible functional forms, unstructured data sources and large numbers of explanatory variables in both prediction and causal analysis, and highlight the challenges of complex simulation models. Finally, we argue that economists have a vital role in addressing the shortcomings of ML when used for quantitative economic analysis.}

    @article{10.1093/erae/jbz033,
    author = {Storm, Hugo and Baylis, Kathy and Heckelei, Thomas},
    title = "{Machine learning in agricultural and applied economics}",
    journal = {European Review of Agricultural Economics},
    year = {2019},
    month = {08},
    abstract = "{This review presents machine learning (ML) approaches from an applied economist’s perspective. We first introduce the key ML methods drawing connections to econometric practice. We then identify current limitations of the econometric and simulation model toolbox in applied economics and explore potential solutions afforded by ML. We dive into cases such as inflexible functional forms, unstructured data sources and large numbers of explanatory variables in both prediction and causal analysis, and highlight the challenges of complex simulation models. Finally, we argue that economists have a vital role in addressing the shortcomings of ML when used for quantitative economic analysis.}",
    issn = {0165-1587},
    doi = {10.1093/erae/jbz033},
    url = {https://doi.org/10.1093/erae/jbz033},
    note = {jbz033},
    eprint = {http://oup.prod.sis.lan/erae/advance-article-pdf/doi/10.1093/erae/jbz033/29194185/jbz033.pdf},
    }

  • A. Mahlein, M. T. Kuska, S. Thomas, M. Wahabzada, J. Behmann, U. Rascher, and K. Kersting, “Quantitative and qualitative phenotyping of disease resistance of crops by hyperspectral sensors: seamless interlocking of phytopathology, sensors, and machine learning is needed,” Current Opinion in Plant Biology, vol. 50, 2019. doi:10.1016/j.pbi.2019.06.007
    [BibTeX] [PDF]
    @article{mahlein2020,
    author = {Mahlein, Anne-Katrin and Kuska, Matheus Thomas and Thomas, Stefan and Wahabzada, Mirwaes and Behmann, Jan and Rascher, Uwe and Kersting, Kristian},
    title = "{Quantitative and qualitative phenotyping of disease resistance of crops by hyperspectral sensors: seamless interlocking of phytopathology, sensors, and machine learning is needed}",
    journal = {Current Opinion in Plant Biology},
    volume = {50},
    year = {2019},
    month = {08},
    doi = {10.1016/j.pbi.2019.06.007},
    url = {https://doi.org/10.1016/j.pbi.2019.06.007}
    }

  • O. Vysotska and C. Stachniss, “Effective Visual Place Recognition Using Multi-Sequence Maps,” IEEE Robotics and Automation Letters (RA-L), 2019.
    [BibTeX] [PDF] [Video]
    @article{vysotska2019ral,
    author = {O. Vysotska and C. Stachniss},
    title = {{Effective Visual Place Recognition Using Multi-Sequence Maps}},
    journal = {IEEE Robotics and Automation Letters (RA-L)},
    year = 2019,
    url = {http://www.ipb.uni-bonn.de/pdfs/vysotska2019ral.pdf},
    videourl = {https://youtu.be/wFU0JoXTH3c},
    }

  • N. Chebrolu, P. Lottes, T. Laebe, and C. Stachniss, “Robot Localization Based on Aerial Images for Precision Agriculture Tasks in Crop Fields,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2019.
    [BibTeX] [PDF] [Video]
    @InProceedings{chebrolu2019icra,
    author = {N. Chebrolu and P. Lottes and T. Laebe and C. Stachniss},
    title = {{Robot Localization Based on Aerial Images for Precision Agriculture Tasks in Crop Fields}},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = 2019,
    url = {http://www.ipb.uni-bonn.de/pdfs/chebrolu2019icra.pdf},
    videourl = {https://youtu.be/TlijLgoRLbc},
    }

  • A. Milioto and C. Stachniss, “Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics using CNNs,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2019.
    [BibTeX] [PDF] [Code] [Video]
    @InProceedings{milioto2019icra,
    author = {A. Milioto and C. Stachniss},
    title = {{Bonnet: An Open-Source Training and Deployment Framework for Semantic Segmentation in Robotics using CNNs}},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = 2019,
    url = {https://arxiv.org/abs/1802.08960},
    codeurl = {https://github.com/Photogrammetry-Robotics-Bonn/bonnet},
    videourl = {https://www.youtube.com/watch?v=tfeFHCq6YJs},
    }

  • A. Milioto, L. Mandtler, and C. Stachniss, “Fast Instance and Semantic Segmentation Exploiting Local Connectivity, Metric Learning, and One-Shot Detection for Robotics,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2019.
    [BibTeX]
    @InProceedings{milioto2019icra-fiass,
    author = {A. Milioto and L. Mandtler and C. Stachniss},
    title = {{Fast Instance and Semantic Segmentation Exploiting Local Connectivity, Metric Learning, and One-Shot Detection for Robotics}},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = 2019,
    }

  • L. Nardi and C. Stachniss, “Uncertainty-Aware Path Planning for Navigation on Road Networks Using Augmented MDPs,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2019.
    [BibTeX] [PDF] [Video]
    @InProceedings{nardi2019icra-uapp,
    author = {L. Nardi and C. Stachniss},
    title = {{Uncertainty-Aware Path Planning for Navigation on Road Networks Using Augmented MDPs}},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = 2019,
    url = {http://www.ipb.uni-bonn.de/pdfs/nardi2019icra-uapp.pdf},
    videourl = {https://youtu.be/3PMSamgYzi4},
    }

  • L. Nardi and C. Stachniss, “Actively Improving Robot Navigation On Different Terrains Using Gaussian Process Mixture Models,” in Proc. of the IEEE Intl. Conf. on Robotics & Automation (ICRA) , 2019.
    [BibTeX] [PDF] [Video]
    @InProceedings{nardi2019icra-airn,
    author = {L. Nardi and C. Stachniss},
    title = {{Actively Improving Robot Navigation On Different Terrains Using Gaussian Process Mixture Models}},
    booktitle = {Proc. of the IEEE Intl. Conf. on Robotics \& Automation (ICRA)},
    year = 2019,
    url = {http://www.ipb.uni-bonn.de/pdfs/nardi2019icra-airn.pdf},
    videourl = {https://youtu.be/DlMbP3u1g2Y},
    }

  • A. Brugger, P. Schramowski, S. Paulus, U. Steiner, K. Kersting, and A. Mahlein, “Spectral signatures in the UV-range can be combined with secondary plant metabolites by deep learning to characterise barley – powdery mildew interaction,” Plant Pathology, vol. n/a, iss. n/a. doi:https://doi.org/10.1111/ppa.13411
    [BibTeX] [PDF]

    Abstract In recent studies, the potential of hyperspectral sensors for the analysis of plant-pathogen interactions was expanded to the ultraviolet range (UV; 200-380 nm) to monitor stress processes in plants. A hyperspectral imaging set-up was established to highlight the influence of early plant-pathogen interactions on secondary plant metabolites. In this study, the plant-pathogen interactions of three different barley lines inoculated with Blumeria graminis f.sp. hordei (Bgh, powdery mildew) were investigated. One susceptible genotype (cv. Ingrid, wild type) and two resistant genotypes (Pallas 01, Mla1 and Mla12 based resistance and Pallas 22, mlo5 based resistance) were used. During the first five days after inoculation (dai) the plant reflectance patterns were recorded and in parallel plant metabolites relevant in host-pathogen interaction were studied. Hyperspectral measurements in the UV-range revealed that a differentiation between barley genotypes inoculated with Bgh is possible and distinct reflectance patterns were recorded for each genotype. The extracted and analyzedanalysed pigments and flavonoids correlated with the spectral data recorded. A classification of non-inoculated and inoculated samples with deep learning revealed that a high performance can be achieved with self-attention networks. The subsequent feature importance identified wavelengths, which were most important for the classification, and these wavelengths were linked to pigments and flavonoids. Hyperspectral imaging in the UV-range allows for a characterisation of different resistance reactions, can be linked to changes of secondary plant metabolites with the advantage of being a non-invasive method and therefore enables a greater understanding of the plants’ reaction to biotic stress as well as resistance reactions.

    @article{https://doi.org/10.1111/ppa.13411,
    author = {Brugger, Anna and Schramowski, Patrick and Paulus, Stefan and Steiner, Ulrike and Kersting, Kristian and Mahlein, Anne-Katrin},
    title = {Spectral signatures in the UV-range can be combined with secondary plant metabolites by deep learning to characterise barley – powdery mildew interaction},
    journal = {Plant Pathology},
    volume = {n/a},
    number = {n/a},
    pages = {},
    keywords = {Blumeria graminis f.sp. hordei, deep learning, Hordeum vulgare, Hyperspectral imaging, secondary plant metabolites, UV-range},
    doi = {https://doi.org/10.1111/ppa.13411},
    url = {https://bsppjournals.onlinelibrary.wiley.com/doi/abs/10.1111/ppa.13411},
    eprint = {https://bsppjournals.onlinelibrary.wiley.com/doi/pdf/10.1111/ppa.13411},
    abstract = {Abstract In recent studies, the potential of hyperspectral sensors for the analysis of plant-pathogen interactions was expanded to the ultraviolet range (UV; 200-380 nm) to monitor stress processes in plants. A hyperspectral imaging set-up was established to highlight the influence of early plant-pathogen interactions on secondary plant metabolites. In this study, the plant-pathogen interactions of three different barley lines inoculated with Blumeria graminis f.sp. hordei (Bgh, powdery mildew) were investigated. One susceptible genotype (cv. Ingrid, wild type) and two resistant genotypes (Pallas 01, Mla1 and Mla12 based resistance and Pallas 22, mlo5 based resistance) were used. During the first five days after inoculation (dai) the plant reflectance patterns were recorded and in parallel plant metabolites relevant in host-pathogen interaction were studied. Hyperspectral measurements in the UV-range revealed that a differentiation between barley genotypes inoculated with Bgh is possible and distinct reflectance patterns were recorded for each genotype. The extracted and analyzedanalysed pigments and flavonoids correlated with the spectral data recorded. A classification of non-inoculated and inoculated samples with deep learning revealed that a high performance can be achieved with self-attention networks. The subsequent feature importance identified wavelengths, which were most important for the classification, and these wavelengths were linked to pigments and flavonoids. Hyperspectral imaging in the UV-range allows for a characterisation of different resistance reactions, can be linked to changes of secondary plant metabolites with the advantage of being a non-invasive method and therefore enables a greater understanding of the plants' reaction to biotic stress as well as resistance reactions.}
    }