A Hybrid Spatio-Temporal Graph Attention (ST D-GAT Framework) for Imputing Missing SBAS-InSAR Deformation Values to Strengthen Landslide Monitoring
Remote Sensing · 28.07.2025 · 17 (15) · 2613
DOI: 10.3390/rs17152613 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 28.07.2025. Verfasst von Hilal Ahmad und 7 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Reservoir-induced landslides threaten infrastructures and downstream communities, making continuous deformation monitoring vital. Time-series InSAR, notably the SBAS algorithm, provides high-precision surface-displacement mapping but suffers from voids due to layover/shadow effects and temporal decorrelation. Existing deep-learning approaches often operate on fixed-size patches or ignore irregular spatio-temporal dependencies, limiting their ability to recover missing pixels. With this objective, a hybrid spatio-temporal Graph Attention (ST-GAT) framework was developed and trained on SBAS-InSAR values using 24 influential features. A unified spatio-temporal graph is constructed, where each node represents a pixel at a specific acquisition time. The nodes are connected via inverse distance spatial edges to their K-nearest neighbors, and they have bidirectional temporal edges to themselves in adjacent acquisitions. The two spatial GAT layers capture terrain-driven influences, while the two temporal GAT layers model annual deformation trends. A compact MLP with per-map bias converts the fused node embeddings into normalized LOS estimates. The SBAS-InSAR results reveal LOS deformation, with 48% of missing pixels and 20% located near the Dasu dam. ST D-GAT reconstructed fully continuous spatio-temporal displacement fields, filling voids at critical sites. The model was validated and achieved an overall R2 (0.907), ρ (0.947), per-map R2 ≥ 0.807 with RMSE ≤ 9.99, and a ROC-AUC of 0.91. It also outperformed the six compared baseline models (IDW, KNN, RF, XGBoost, MLP, simple-NN) in both RMSE and R2. By combining observed LOS values with 24 covariates in the proposed model, it delivers physically consistent gap-filling and enables continuous, high-resolution landslide monitoring in radar-challenged mountainous terrain.
Zitieren
APA
Ahmad, H., Zhang, Y., Rehman, H., Alam, M., Ullah, Z., Shahid, M. A., Khan, M., & Siddique, A. (2025). A Hybrid Spatio-Temporal Graph Attention (ST D-GAT Framework) for Imputing Missing SBAS-InSAR Deformation Values to Strengthen Landslide Monitoring. Remote Sensing, 17(15), 2613. https://doi.org/10.3390/rs17152613
Vancouver
Ahmad H, Zhang Y, Rehman H, Alam M, Ullah Z, Shahid MA, et al. A Hybrid Spatio-Temporal Graph Attention (ST D-GAT Framework) for Imputing Missing SBAS-InSAR Deformation Values to Strengthen Landslide Monitoring. Remote Sensing. 2025;17(15):2613. doi:10.3390/rs17152613
BibTeX
@article{Ahmad2025,
author = {Ahmad, Hilal and Zhang, Yinghua and Rehman, Hafeezur and Alam, Mehtab and Ullah, Zia and Shahid, Muhammad Asfandyar and Khan, Majid and Siddique, Aboubakar},
title = {A Hybrid Spatio-Temporal Graph Attention (ST D-GAT Framework) for Imputing Missing SBAS-InSAR Deformation Values to Strengthen Landslide Monitoring},
journal = {Remote Sensing},
year = {2025},
volume = {17},
number = {15},
pages = {2613},
doi = {10.3390/rs17152613}
}
EUVIMED