Comparative Assessment of Multimodal Earth Observation Data for Soil Moisture Estimation

TL;DR

This study develops a high-resolution soil moisture estimation framework using multimodal satellite data and machine learning, demonstrating effective methods for farm-level applications across Europe.

Contribution

It introduces a novel high-resolution (10m) soil moisture estimation approach combining Sentinel data, ERA-5 reanalysis, and machine learning, with evaluation of foundation model embeddings.

Findings

Hybrid temporal matching improves R^2 to 0.518.

Foundation model embeddings offer negligible performance gains.

Traditional spectral features with tree-based models are highly effective.

Abstract

Accurate soil moisture (SM) estimation is critical for precision agriculture, water resources management and climate monitoring. Yet, existing satellite SM products are too coarse (>1km) for farm-level applications. We present a high-resolution (10m) SM estimation framework for vegetated areas across Europe, combining Sentinel-1 SAR, Sentinel-2 optical imagery and ERA-5 reanalysis data through machine learning. Using 113 International Soil Moisture Network (ISMN) stations spanning diverse vegetated areas, we compare modality combinations with temporal parameterizations, using spatial cross-validation, to ensure geographic generalization. We also evaluate whether foundation model embeddings from IBM-NASA's Prithvi model improve upon traditional hand-crafted spectral features. Results demonstrate that hybrid temporal matching - Sentinel-2 current-day acquisitions with Sentinel-1 descending orbit - achieves R^2=0.514, with 10-day ERA5 lookback window improving performance to R^2=0.518. Foundation model (Prithvi) embeddings provide negligible improvement over hand-crafted features (R^2=0.515 vs. 0.514), indicating traditional feature engineering remains highly competitive for sparse-data regression tasks. Our findings suggest that domain-specific spectral indices combined with tree-based ensemble methods offer a practical and computationally efficient solution for operational pan-European field-scale soil moisture monitoring.