PhenoRob – Robotics and Phenotyping for Sustainable Crop Production
How to feed a hungry world in the forthcoming future is an open problem. The world population is increasing as well as the demand for renewable resources from agricultural production. Arable land, however, is limited. The pollution of soil and environment through agrochemicals and fertilizer must be reduced, which is currently of special interest in Central Europe. At the same time, climate change poses additional constraints. The major, hitherto unmet challenge is to increase crop production while reducing the environmental footprint and achieving sustainable crop production.
The main hypothesis of this proposed Cluster of Excellence is that a major shift toward sustainable crop production can be achieved by two specific aims: (1) multi-scale monitoring of plants and the environment using autonomous robotics with automated intervention and big data analytics combined with machine learning; and (2) integrating the developed technical innovations by considering crop farming in a systemic manner.
In this proposed cluster, we will combine recent advances in high-precision monitoring, phenotyping, distributed sensing, and robotics with data sciences, ecosystem and soil research, and crop growth modeling. First, we will systematically monitor all essential aspects of crop farming using sensor networks and mobile ground and aerial robots. This provides spatiotemporally-aligned, detailed, per-plant information, and soil, nutrient, and ecosystem parameters such as weather and biodiversity. These data will enable more effective and sustainable control and management of inputs (crop genetic resources, crop management, soil, and weather conditions, etc.) and outputs (yield, plant growth, phenotypic performance, and environmental impact, etc.) for the whole system comprising soil, crop, and ecosystem. Second, we will develop novel technologies to enable real-time, automated control of weeds, a central limitation to agricultural productivity, and selective spraying and fertilization of individual plants in field stands. This will reduce the environmental footprint by reducing chemical input while minimizing soil degradation and erosion. Third, machine learning and big data sciences applied to recorded, spatiotemporally-aligned crop data can improve our understanding and modeling of plant growth and nutrient and water efficiencies with respect to inputs, and will help to identify complex correlations and outputs. The resulting technology and knowledge will change crop production on all scales. Fourth, in addition to the impacts on management decisions at the farm level, we will investigate the requirements for broad technology uptake, market interactions, and the resulting impacts from upscaling the developed technologies.