Machine learning to investigate storage and dynamics of soil organic carbon

Department of Hydrology and Atmospheric Sciences
4 pm on Thursday, April 29, 2021
Contact the department for zoom details or to subscribe to the seminar email list
Umakant Mishra
Principal Scientist, Computational Biology & Biophysics, Sandia National Laboratories, Livermore


Soil organic carbon is a determinant of multiple ecosystem services that soils provide to humanity. However, land use and climate change may alter the current soil carbon balance and convert the land surface into a source or sink of atmospheric CO2, altering soil properties and functions. More recently, use of machine learning (ML) approaches has increased in investigations of soil organic carbon (SOC) storage and dynamics. We used ML approaches with large number of soil filed observations and environmental factors data to (1) predict the spatial heterogeneity of northern circumpolar surface SOC stocks, (2) predict decadal changes in continental US surface SOC stocks under future emission scenarios, and (3) develop functional relationships between environmental factors and SOC stocks to benchmark earth system model representations. Our results suggest that ensemble ML approach improves prediction accuracy of surface SOC stocks in comparison to other approaches. The results of decadal and total SOC changes in continental US surface soils, obtained from ensemble ML approach is not in agreement with current CMIP6 simulations. The functional relationships between environmental controllers and SOC stocks that we derived, produced similar prediction accuracy as obtained from the random forest ML approach. In summary, computational approaches can help in quantifying anthropogenic and climatic impacts on SOC and reducing the uncertainty that exists in model projections of future carbon climate feedbacks.


Dr. Umakant Mishra is a Principal Scientist in the Computational Biology & Biophysics unit of the Sandia National Laboratories. He studies land surface spatial heterogeneity, anthropogenic and climatic impacts on soil carbon, and benchmarking earth system models. He serves as a Technical Editor for the Agronomy Journal (American Society of Agronomy publication) and as an Associate Editor in the Vadose Zone Journal (Soil Science Society of America publication). Currently, he is the Chair of the International Soil Science Award Committee of the Soil Science Society of America and a Co-Chair of the Data & Observation Model Link science panel and an Executive Board member of the International Soil Modeling Consortium.