Deep Learning for Soil Moisture Estimation: Fusing Satellite Data with Optimally-Lagged Meteorological Features

2026-06-19

AI Summary

This study addresses the challenges of atmospheric forcing lag and vertical moisture propagation delay in soil moisture estimation over semi-arid agricultural regions by systematically applying cross-correlation functions (CCF) to quantify optimal time lags (0–30 days) between meteorological variables and multi-layer soil moisture, as well as inter-layer lags (0–15 days). Leveraging these CCF-optimized lagged meteorological features alongside satellite remote sensing and multi-depth in situ observations, the authors develop CNN, LSTM, and hybrid CNN-LSTM models for multi-granularity soil moisture prediction. The hybrid CNN-LSTM model achieves the best performance (R² = 0.930, CVRMSE = 8.0%), with an average R² of 0.535 across seven fields—representing a 1.00 improvement over a satellite-data-only baseline—and substantially enhances the accuracy of soil moisture estimation.

Abstract

Accurate soil moisture estimation in semi-arid agricultural regions requires integrating remote sensing and meteorological information while accounting for the delayed response of soil moisture to atmospheric forcing. This study introduces a Cross-Correlation Function (CCF) methodology to determine optimal temporal lags (0-30 days) between meteorological variables and soil moisture, as well as inter-depth lags (0-15 days) describing vertical moisture propagation from the surface (10 cm) to deeper layers (20-50 cm). The approach was validated across seven agricultural plots in southeastern Spain. Three deep learning architectures, each targeting a distinct prediction granularity, were evaluated under five feature configurations ranging from satellite-only to full satellite-meteorology-depth fusion: a CNN for per-pixel estimation within each plot, an LSTM for frame-level (daily plot-mean) prediction, and a CNN-LSTM hybrid operating on sliding windows with pooled multi-patch training. Models were assessed on held-out data to measure genuine generalisation. Meteorological variables improved performance over the satellite-only baseline, while subsurface depth information proved decisive across all architectures. The per-pixel CNN achieved the strongest single-patch result (R^2 = 0.877, RMSE = 2.28), with a seven-patch average R^2 of 0.535, representing an improvement of +1.00 over the satellite-only baseline. The pooled CNN-LSTM hybrid obtained the highest overall performance (R^2 = 0.930, CVRMSE = 8.0%). These results demonstrate that explicitly modelling atmospheric and vertical subsurface delays substantially improves soil moisture estimation for precision agriculture.

Problem

• soil moisture estimation
• temporal lag
• vertical moisture propagation
• remote sensing
• meteorological variables

Innovation

• Cross-Correlation Function
• Temporal Lag Optimization
• Soil Moisture Estimation
• Deep Learning Fusion
• Vertical Moisture Propagation