A Machine Learning Data Fusion Model for Soil Moisture Retrieval
This provides a high-resolution soil moisture map at 320m for environmental monitoring, but it is incremental as it builds on existing data fusion methods in remote sensing.
The paper tackles soil moisture estimation by developing a deep learning model that fuses multiple satellite and geophysical data sources, achieving an average per-sensor correlation of 0.727 and ubRMSE of 0.054 for global in-situ data from 2015-2021.
We develop a deep learning based convolutional-regression model that estimates the volumetric soil moisture content in the top ~5 cm of soil. Input predictors include Sentinel-1 (active radar), Sentinel-2 (optical imagery), and SMAP (passive radar) as well as geophysical variables from SoilGrids and modelled soil moisture fields from GLDAS. The model was trained and evaluated on data from ~1300 in-situ sensors globally over the period 2015 - 2021 and obtained an average per-sensor correlation of 0.727 and ubRMSE of 0.054, and can be used to produce a soil moisture map at a nominal 320m resolution. These results are benchmarked against 13 other soil moisture works at different locations, and an ablation study was used to identify important predictors.