This award was made through the "Signals in the Soil (SitS)" solicitation, a collaborative partnership between the National Science Foundation and the United States Department of Agriculture National Institute of Food and Agriculture (USDA NIFA). High crop productivity in the Midwestern US was achieved by artificially draining wetlands and applying millions of tons of nitrogen (N) and phosphorous (P) fertilizers. However, 40-80% of these N and P nutrient inputs are lost from soils and become pollutants in water bodies and the atmosphere. Given the continuing need to maintain crop production while reducing concerns about environmental pollution, managing soil nutrients in a more sustainable and intelligent manner is a major challenge in this nationally and globally important agricultural region. This project will integrate recent advances in nanotechnology, sensing technology, and machine learning to enable new methods for measuring and managing N and P in croplands to reduce losses to the environment. The outcomes of this project can be used directly by farmers to better manage field application of N and P fertilizers and by local/federal governments and other organizations to pinpoint pollution hotspots and develop strategies for nutrient reduction. By engaging communities, this project further aims to enable undergraduate/graduate students, junior and senior professionals, farmers, and other stakeholders to embrace new-generation technologies to improve farming management practices and environmental stewardship. If successful, the technology developed by this project will improve the food and water security of the nation.

To inform and facilitate sustainable nutrient management in the Midwestern agroecosystems, this project will develop a sensor-model integration framework to reduce the uncertainty in estimating key variables related to soil reactive N and P dynamics. The project will re-purpose a low-cost, graphene-based nanosensor to provide continuous measurement of soil nitrate and phosphate. To facilitate the calculation of pools and fluxes of reactive N and P, the team will develop a sensing-inference system for sub-field hydrological conditions based on the Cosmic Ray Neutron Sensing (CRNS) system and a hydrology model. Calibration and validation of the nanosensor and the CRNS system will be performed in tile-drained sites with already established continuous monitoring for nitrate and phosphate loads as well as soil moisture. Finally, this project will use a state-of-the-art data science paradigm, the Physics-Guided Deep Learning (PGDL), as a sensor-model fusion framework to generalize place-based knowledge about reactive N and P dynamics to principle-based understanding across multiple scales. PGDL represents an innovative way to leverage the power of machine learning and process-based modeling, and, therefore, is expected to significantly advance the ability to predict and manage N and P in U.S. Midwestern agroecosystems. The developed sensors and tools can be applicable to other regions worldwide that face similar balancing issues between the intensification of agricultural production and the maintenance of environmental sustainability.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

Project Start
Project End
Budget Start
Budget End
Support Year
Fiscal Year
Total Cost
Indirect Cost
University of Minnesota Twin Cities
United States
Zip Code