Skip to main content
U.S. flag

An official website of the United States government

Publication Date
1 May 2020

A Causal Inference Model Based on Random Forest to Identify the Effect of Soil Moisture on Precipitation

Understanding the daily soil moisture-precipitation coupling.
Print / PDF
Powerpoint Slide

The daily soil moisture-precipitation (SM-P) coupling over the continental US was investigated using an innovative nonlinear Granger causality framework based on machine learning, time series decomposition, spatial impact modeling, hybrid feature selection method, and nonlinear Granger causality test.


We better quantified the sign and hot spots of SM-P feedback over the US at daily timescale. We created a new SM-P based metric to benchmark the Earth system models, in terms of land-atmosphere hydrology feedbacks.


Soil moisture influences precipitation mainly through its impact on land-atmosphere interactions. Understanding and correctly modeling soil moisture-precipitation (SM-P) coupling is crucial for improving weather forecasting and sub-seasonal to seasonal climate predictions, especially when predicting the persistence and magnitude of drought. However, the sign and spatial structure of SM-P feedback is still being debated in the climate research community, mainly due to the difficulty in establishing causal relationships and the high degree of nonlinearity in land-atmosphere processes. To this end, we developed a causal-inference model based on the Granger causality analysis and a nonlinear machine learning model. This model includes three steps: nonlinear anomaly decomposition, nonlinear Granger causality analysis, and evaluation of the quality of SM-P feedback, which eliminates the nonlinear response of interannual and seasonal variability, the memory effects of climatic factors and isolates the causal relationship of local SM-P feedback. We applied this model by using NCA-LDAS datasets over the US. The results highlight the importance of nonlinear atmosphere responses in land-atmosphere interactions. In addition, the strong feedback over the southwestern US and the Great Plains of the US both highlight the impacts of topographic factors rather than only the sensitivity of evapotranspiration to soil moisture. Furthermore, the SM-P index defined by our framework is used to benchmark Earth system models (ESMs), which provides a new metric for efficiently identifying potential model biases in modeling local land-atmosphere interactions and may help the development of ESMs in improving simulations of water cycle variability and extremes.

Point of Contact
Jiafu Mao
Oak Ridge National Laboratory (ORNL)
Funding Program Area(s)