A Spatial Downscaling Method for Remote Sensing Soil Moisture Based on Random Forest Considering Soil Moisture Memory and Mass Conservation

Remote sensing soil moisture (SM) has been widely used in various earth science studies and applications, but their low resolution limits their usage and downscaling of them is needed. In this study, we proposed a spatial downscaling method for SM based on random forest considering soil moisture memory and mass conservation to improve downscaling performance. The lagged SM was added as a predictor to represent soil moisture memory, in addition to the regular predictors in previous downscaling studies. The Soil Moisture Active Passive (SMAP) SM data of the Pearl River Basin were used to test our downscaling method. The results show that the downscaling model obtained good performance on the test set (R-2 = 0.848, ubRMSE = 0.034 m(3)/m(3) and Bias = 0.008 m(3)/m(3)). The spatial and temporal performance of the RF downscaling model can be improved by adding lagged SM variables. Downscaled data obtained can retain the information of the original SMAP SM data well and show more spatial details, and mass conservation correction is considered to be useful to eliminate systematic bias of the downscaling model. Downscaled SM achieved acceptable performance in in situ validation, though it was inevitably limited by the performance of the original SMAP data. The proposed downscaling method can serve as a powerful tool for the development of high-resolution SM information.

Automated summary

In this study, a spatial downscaling method for soil moisture based on random forest was proposed to improve the downscaling performance by considering soil moisture memory and mass conservation. The downscaling model showed good performance on the test set and the downscaled data retained the information of the original data while displaying more spatial details.