Sequence-Aware Deep Learning for Field-Scale Surface Soil Moisture Estimation from Sentinel-1, HLS, and Ancillary Data
Remote Sensing · 05.07.2026 · 18 (13) · 2213
DOI: 10.3390/rs18132213 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 05.07.2026. Verfasst von Elahe Jahan Nejadi und 2 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada, Canadian Space Agency.
Abstract (Originalsprache)
Accurate field-scale surface soil moisture (SSM) measures are important for agricultural water management. Conventional satellite SSM products remain too coarse for within-field applications. Here, we developed sequence-aware deep learning models for growing-season SSM estimation by fusing data from Sentinel-1 C-band SAR, harmonized Landsat-8/Sentinel-2 (HLS), and local ancillary datasets. We assembled a multi-source dataset on Sentinel-1 overpass time for 2016–2024 (May–September), yielding 1469 samples and 65 features per sample, including SAR and optical features, meteorological data, soil texture and bulk density, topography, crop labels, irrigation-likelihood flag, and irregular-time-step encoding. We compared long short-term memory (LSTM) and temporal convolutional neural network (TCN) architectures together with attention-augmented variants, including feature attention (FA), temporal attention (TA), and the combined feature–temporal attention (FTA). Models were trained and tested on seven years of data and were validated based on a temporal generalization using combined data of a wet year (2016) and a dry year (2023). The best model, FTA-TCN, achieved R2 = 0.851, RMSE = 0.024 m3.m−3, and MAE = 0.020 m3.m−3 on the withheld validation years, outperforming the base LSTM (R2 = 0.422; RMSE = 0.053 m3.m−3; MAE = 0.043 m3.m−3) and the base TCN (R2 = 0.746; RMSE = 0.034 m3.m−3; MAE = 0.022 m3.m−3). Shapley additive explanations (SHAP) analysis indicated that antecedent precipitation and short-term rainfall accumulations were dominant forcings, while soil texture, elevation, incidence angle, and vegetation indices modulated SSM variability. Satellite-derived features accounted for ~28.5% of aggregated SHAP importance. Overall, the results show that dual-attention temporal convolution can capture field-scale SSM dynamics across wet and dry seasons when satellite signals are coupled with local soil-meteorological-management context.
Förderung
- Natural Sciences and Engineering Research Council of Canada
- Canadian Space Agency
Zitieren
APA
Nejadi, E. J., Magagi, R., & Goïta, K. (2026). Sequence-Aware Deep Learning for Field-Scale Surface Soil Moisture Estimation from Sentinel-1, HLS, and Ancillary Data. Remote Sensing, 18(13), 2213. https://doi.org/10.3390/rs18132213
Vancouver
Nejadi EJ, Magagi R, Goïta K. Sequence-Aware Deep Learning for Field-Scale Surface Soil Moisture Estimation from Sentinel-1, HLS, and Ancillary Data. Remote Sensing. 2026;18(13):2213. doi:10.3390/rs18132213
BibTeX
@article{Nejadi2026,
author = {Nejadi, Elahe Jahan and Magagi, Ramata and Goïta, Kalifa},
title = {Sequence-Aware Deep Learning for Field-Scale Surface Soil Moisture Estimation from Sentinel-1, HLS, and Ancillary Data},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {13},
pages = {2213},
doi = {10.3390/rs18132213}
}
EUVIMED