Using machine learning techniques to reconstruct the signal observed by the GRACE mission based on AMSR-E microwave data

This study delves into the synergy between remote sensing and satellite gravimetry, focusing on the utilization of Advanced Microwave Scanning Radiometer (AMSR-E) data for modeling delta Total Water Storage (Delta TWS) values derived from the GRACE mission. Various machine learning algorithms were employed to investigate the concordance between Gravity Recovery and Climate Experiment (GRACE) and AMSR-E observations. Despite the limited correlation in circumpolar permafrost areas, Delta TWS was successfully modeled with an accuracy of a Root Mean Square Error (RMSE) of 3.5 cm. The Amazon region exhibited a notable model error, attributed to significant Delta TWS amplitude; the overall model quality was affirmed by Normalized Root Mean Square Error (NRMSE) and Nash-Sutcliffe Efficiency (NSE) metrics. Importantly, the effectiveness of AMSR-E Soil Moisture (SM) data, encompassing C (frequency of 4-8 GHz) and X (frequency of 8-12 GHz) ranges (similar to 0.04 m and similar to 0.03 m wavelength, respectively) in modeling Delta TWS, even in heavily forested equatorial regions, was demonstrated.

Automated summary

This study explores the synergy between remote sensing and satellite gravimetry by using AMSR-E data to model Delta TWS values from the GRACE mission. Various machine learning algorithms were used to study the consistency between GRACE and AMSR-E observations. Although the correlation in the circumpolar permafrost region is limited, the model is successful with a root mean square error of 3.5 cm for Delta TWS modeling. The Amazon region shows a large model error due to the large amplitude of Delta TWS, but the overall model quality is confirmed by NRMSE and NSE metrics. In addition, the effectiveness of AMSR-E soil moisture data in simulating Delta TWS is demonstrated, even in the heavily forested equatorial region.