Global soil moisture from combined active and passive microwave observations: integrating ASCAT and SMAP observations based on machine learning approaches

Authors: MA, H - French National Institute For Agricultural Research; ZENG, J - Chinese Academy Of Sciences; WIGNERON, J - National Institute For Agricultural Research (INIAP); LI, X - University Of Bordeaux; FU, P - Harrisburg University; KOLASSA, J - National Aeronautics And Space Administration (NASA); Cosh, Michael

Submitted to: Remote Sensing of Environment
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/1/2024
Publication Date: 7/1/2024
Citation: Ma, H., Zeng, J., Wigneron, J., Li, X., Fu, P., Kolassa, J., Cosh, M.H. 2024. Global soil moisture from combined active and passive microwave observations: integrating ASCAT and SMAP observations based on machine learning approaches. Remote Sensing of Environment. 308:114197. https://doi.org/10.1016/j.rse.2024.114197.
DOI: https://doi.org/10.1016/j.rse.2024.114197

Interpretive Summary: Satellites are capable of delivering soil moisture estimates based on singular platform signals, but a multitude of satellites can be combined to produced improved soil moisture products. By combining information from the United States Soil Moisture Active Passive mission and the European Advanced Scatterometer (ASCAT), four machine learning approaches were tested against in situ ground measurements to determine that by combining these two satellite sources, an improved product is available over currently produced operational estimates. These methods also improved the temporal resolution of the potential products.

Technical Abstract: The fusion of active and passive microwave measurements is expected to provide more robust surface soil moisture (SSM) mapping across various environmental conditions compared to the use of a single sensor. Thus, the integration of the newest L-band passive (i.e., Soil Moisture Active Passive, SMAP) and the active (i.e., the Advanced Scatterometer, ASCAT) observations provides an opportunity for SSM mapping with improved accuracy. However, this integration remains underexplored. In this context, the integration of SMAP brightness temperature (TB) and ASCAT backscattering coefficients for global-scale SSM estimation was investigated, by fully considering the potential error sources in conventional radiative transfer models (RTMs) as well as other SSM linked factors. Based on ground measurements from globally distributed dense networks with relieved mismatching issues and the defined spatial/temporal independent evaluation strategies, this study: (i) comprehensively evaluated four classical machine learning approaches, including Random Forest (RF), Long-Short Term Memory (LSTM), Support Vector Machine (SVM), and Cascaded Neural Network (CNN), and chose the best performing RF method to implement the final integration of SSM; (ii) compared the integration retrievals to those made using data from a single sensor (SMAP or ASCAT) with the same machine learning framework, as well as to the official SMAP passive, ASCAT active, and ESA CCI active-passive combined SSM products. The results show the integration retrievals achieve satisfactory performance by obtaining an averaged unbiased root mean squared error (ubRMSE) of 0.042 m3/m3 and a temporal correlation of 0.756, which are superior to machine learning based SSM estimated from a single active or passive sensor, and also outperform the official SMAP, ASCAT, and ESA CCI products. Moreover, the temporal resolution is evidently improved compared to the SMAP and ASCAT SSM products, with a temporal ratio exceeding 60% for most areas across the globe. Therefore, blending active and passive measurements affords a more reliable SSM mapping with increased sampling at the global scale, and could contribute to improved hydro-ecological applications.