Just how much carbon is in the soil? That’s a tough question to answer at large spatial scales, but understanding soil organic carbon at regional, national, or global scales could help scientists predict overall soil health, crop productivity, and even worldwide carbon cycles.
In a recent study, University of Illinois researchers show new machine-learning methods based on laboratory soil hyperspectral data could supply equally accurate estimates of soil organic carbon. Their study provides a foundation to use airborne and satellite hyperspectral sensing to monitor surface soil organic carbon across large areas.
“Soil organic carbon is a very important component for soil health, as well as for cropland productivity,” says lead study author Sheng Wang, research assistant professor in the Agroecosystem Sustainability Center (ASC) and the Department of Natural Resources and Environmental Sciences (NRES) at U of I. “We did a comprehensive evaluation of machine learning algorithms with a very intensive national soil laboratory spectral database to quantify soil organic carbon.”
Wang and his collaborators leveraged a public soil spectral library from the USDA Natural Resources Conservation Service containing more than 37,500 field-collected records and representing all soil types around the U.S. Like every substance, soil reflects light in unique spectral bands which scientists can interpret to determine chemical makeup.
Says Andrew Margenot, assistant professor in the Department of Crop Sciences and co-author on the study, “We knew some of these models worked, but the novelty is the scale and that we tried the full gamut of machine learning algorithms.”
After selecting the best algorithm based on the soil library, the researchers put it to the test with simulated airborne and spaceborne hyperspectral data. As expected, their model accounted for the “noise” inherent in surface spectral imagery, returning a highly accurate and large-scale view of soil organic carbon.
Chenhui Zhang, an undergraduate student studying computer science at Illinois, also worked on the project as part of an internship with the National Center for Supercomputing Applications’ Students Pushing Innovation (SPIN) program.
“Hyperspectral data can provide rich information on soil properties. Recent advances in machine learning saved us from the nuisance of constructing hand-crafted features while providing high predictive performance for soil carbon,” Zhang says.
The article, “Using soil library hyperspectral reflectance and machine learning to predict soil organic carbon: Assessing potential of airborne and spaceborne optical soil sensing,” is published in Remote Sensing of Environment [DOI: 10.1016/j.rse.2022.112914]. Authors include Sheng Wang, Kaiyu Guan, Chenhui Zhang, DoKyoung Lee, Andrew Margenot, Yufeng Ge, Jian Peng, Wang Zhou, Qu Zhou, and Yizhi Huang.
The research was supported by the U.S. Department of Energy's Advanced Research Projects Agency-Energy (ARPA-E) SMARTFARM and SYMFONI projects, Illinois Discovery Partners Institute (DPI), Institute for Sustainability, Energy, and Environment (iSEE), and College of Agricultural, Consumer and Environmental Sciences Future Interdisciplinary Research Explorations (ACES FIRE), Center for Digital Agriculture (CDA-NCSA), University of Illinois at Urbana-Champaign. This work was also partially funded by the USDA National Institute of Food and Agriculture (NIFA) Artificial Intelligence for Future Agricultural Resilience, Management, and Sustainability grant.