Gap Filling of High-Resolution Soil Moisture for SMAP/Sentinel-1: A Two-Layer Machine Learning-Based Framework
Academic Article
Overview
Research
Identity
Additional Document Info
Other
View All
Overview
abstract
AbstractAs the most recent 3km soil moisture product from the Soil Moisture Active Passive (SMAP) mission, the SMAP/Sentinel1 L2_SM_SP product has a unique capability to provide globalscale 3km soil moisture estimates through the fusion of radar and radiometer microwave observations. The spatial and temporal availability of this highresolution soil moisture product depends on concurrent radar and radiometer observations which is significantly restricted by the narrow swath and low revisit schedule of the Sentinel1 radars. To address this issue, this paper presents a novel twolayer machine learningbased framework which predicts the brightness temperature and subsequently the soil moisture at gap areas. The proposed method is able to gapfill soil moisture satisfactorily at areas where the radiometer observations are available while the radar observations are missing. We find that incorporating historical radar backscatter measurements (30day average) into the machine learning framework boosts its predictive performance. The effectiveness of the twolayer framework is validated against regional holdout SMAP/Sentinel1 3km soil moisture estimates at four study areas with distinct climate regimes. Results indicate that our proposed method is able to reconstruct 3km soil moisture at gap areas with high Pearson correlation coefficient (47%/35%/20%/80% improvement of mean R, at Arizona/Oklahoma/Iowa/Arkansas) and low unbiased Root Mean Square Error (20%/10%/7%/26% improvement of mean unbiased root mean square error) when compared to the SMAP 33km soil moisture product. Additional validations against airborne data and in situ data from soil moisture networks are also satisfactory.
