A Machine Learning Data Fusion Model for Soil Moisture Retrieval

TL;DR

This paper presents a deep learning model that fuses multiple satellite and geophysical data sources to accurately estimate soil moisture content at a global scale, improving upon existing methods.

Contribution

It introduces a novel convolutional-regression model that integrates diverse satellite and geophysical data for soil moisture retrieval, with extensive validation and benchmarking.

Findings

Correlation of 0.727 between predictions and in-situ measurements

ubRMSE of 0.054 indicating high accuracy

Model produces soil moisture maps at 320m resolution

Abstract

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.