Improving/testing machine learning methods for benchmarking soil carbon dynamics representation of land surface models 

Umakant Mishra stands at the bottom of Mount Everest.
Sandia soil scientist Umakant Mishra starts his hike to the base camp of Mount Everest. (Photo courtesy of Umakant Mishra)

Representation of soil organic carbon (SOC) dynamics in Earth system models (ESM) is a key source of uncertainty in predicting carbon climate feedbacks. The magnitude of this uncertainty can be reduced by accurate representation of environmental controllers of SOC stocks in ESMs. In this study, researchers used data of environmental factors, field SOC observations, ESM projections and ML approaches to identify dominant environmental controllers of SOC stocks and derive functional relationships between environmental factors and SOC stocks. Derived mathematical relationships were derived to benchmark the coupled model intercomparison project phase six ESM representation of SOC stocks, and divergent environmental control representation in ESMs were found in comparison to field observations. Representation of SOC in ESMs can be improved by including additional environmental factors and representing their functional relationships with SOC consistent with observations. This project was highlighted in the Soil Science Society of America


Sandia researchers linked to work

  • Umakant Mishra
  • Sagar Gautam

Sponsored by

Image of LDRD_Icon-01

Associated Publications

Mishra, U., Yeo, K., Adhikari, K., Riley, W. J., Hoffman, F. M., Hudson, C., & Gautam, S. (2022). Empirical relationships between environmental factors and soil organic carbon produce comparable prediction accuracy to machine learning. Soil Science Society of America Journal, 86(6), 1611–1624. https://doi.org/10.1002/saj2.20453  

Gonçalves, D. R., Mishra, U., Wills, S., & Gautam, S. (2021). Regional environmental controllers influence continental scale soil carbon stocks and future Carbon Dynamics. Scientific Reports, 11(1). https://doi.org/10.1038/s41598-021-85992-y