The overarching goal of this project is to develop novel, small UAV-based, remote-sensing technologies for rapid diagnoses of soybean crop health based on machine learning and cutting-edge image acquisition techniques. An allied tissue remote sampling approach developed in parallel will bolster confidence in machine learning for crop stress diagnosis and support prescriptive management of crop health. The project aims to design, prototype and test a small UAV attachment for foliar tissue sampling, continue to build and expand the library of high-resolution imagery for soybean crop health diagnosis, refine and improve computational processes and algorithms for image classification, conduct field-scale testing and use it to refine and improve algorithm user-friendliness.
Key Benefactors:
farmers, agronomists, extension agents