Abstract
High-resolution surface soil moisture is essential for advancing various applications. The increased Synthetic Aperture Radar (SAR) missions over the past decade presents an opportunity to obtain large-scale, high-resolution soil moisture data. Machine learning methods are increasingly used for this purpose but they generally suffered from the availability of ground-based observations. The real performance in view of a global product is still unclear. Consequently, commonly used machine learning methods were evaluated in this study in simulated global mapping scenarios with few training data, using a global data set of 209,318 samples from 1021 locations world-wide, and a unique regional dataset with intensive ground and airborne-derived soil moisture from L-band passive microwave observations. Three evaluation scenarios based on the global dataset were involved, with ≤ 5% samples used for training. The target accuracy of 0.06 m3/m3 was only met in the dependent evaluation scenario, where the training and testing samples were randomly split. In the temporal evaluation scenario and spatial evaluation scenario, where training and testing samples came from different time periods or locations, the best models achieved median root mean square errors (RMSEs) of only 0.078 and 0.089 m3/m3 respectively. The evaluation on the regional data set showed consistently worse accuracy statistics (RMSE > 0.1 m3/m3, R<0.41). Moreover, all methods failed to capture the spatial patterns of soil moisture, compared to airborne-derived passive soil moisture maps. These findings therefore suggest that current expectations for SAR-based soil moisture estimation using machine learning may be over-optimistic, requiring more robust approaches for scenarios with sparse ground measurements.
Funding Information
  • National Key Research and Development Program of China (2023YFC3209800)
  • National Natural Science Foundation of China (42101374, 42371369)

This publication has 67 references indexed in Scilit: