Technify-ing Soil Science? Proximal and Remote Sensing

“Big data” has entered agriculture, and now soil science. However, soils present several challenges to the application of AI approaches such as machine learning, notably the ‘small data problem’, expensive data generation, and disparate spatiotemporal scales (i.e., data fusion challenge). As the co-lead on the USDA Artificial Intelligence Institute of AIFARMS and with support from the NSF Smart & Connected Communities (SCC) and NSF Signals in the Soils (SitS) programs, our lab is working with proximal and remote sensing experts, AI scientists, and sensor engineers to overcome these challenges and develop approaches and novel in situ sensors to improve soil management and nutrient use efficiency in crop productions systems. Collaborators include Dr. Kaiyu Guan of UIUC, Dr. Supratik Guha of University of Chicago, and Dr. Roser Matamala of Argonne National Laboratory.