CED-LSTM: A Coherence-Conditioned Encoder–Decoder Network for Robust InSAR Time-Series Deformation Extraction in Open-Pit Mines
Remote Sensing · 25.03.2026 · 18 (7) · 984
DOI: 10.3390/rs18070984 ↗Kurz gefasst
Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 25.03.2026. Verfasst von Yanping Wang und 8 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China https://ror.org/01h0zpd94, Beijing Municipal Education Commission https://ror.org/04bpn6s66.
Abstract (Originalsprache)
Systematically characterizing the time series deformation evolution of open-pit mine slopes is key to revealing their potential instability development and supporting subsequent deformation-level classification. Interferometric Synthetic Aperture Radar (InSAR), by enabling measurement of ground deformation at a global scale approximately every ten days, may hold the key to those interactions. However, atmospheric propagation delays still have a significant impact on deformation calculations, and open-pit mine slopes monitored by InSAR often suffer from low coherence. This noise can obscure nonlinear and transient precursory signatures in deformation time series, reducing the identifiability of key temporal patterns required for automated interpretation. Here, we present a Coherence-conditioned Encoder–Decoder Long Short-Term Memory (CED-LSTM) denoising network for deformation time series. We generate a physics-aware synthetic dataset by modeling coherence-dependent measurement noise and temporally correlated atmospheric delays. The network jointly models deformation time series and coherence, using residual learning and adaptive gated composite loss to preserve deformation trends. It is designed to autonomously extract ground deformation signals from noise in InSAR time series without prior knowledge of where deformation occurs or how it evolves. On the synthetic validation set, the network achieved a root mean square error (RMSE) of 2.2 mm across the validation sequences. Applied to three InSAR datasets over an open-pit mine from March 2019 to March 2022, denoising suppresses noise and stabilizes deformation boundaries, enabling extraction of trend and transient indicators and a data-driven deformation-level score. Using quantile-based thresholds, these scores are then used to produce multi-year deformation-level classification maps.
Förderung
- National Natural Science Foundation of China https://ror.org/01h0zpd94
- Beijing Municipal Education Commission https://ror.org/04bpn6s66
Zitieren
APA
Wang, Y., Kong, X., Bai, Z., Li, Y., Lu, Y., Tang, W., Lin, Y., Shen, W., & Cai, G. (2026). CED-LSTM: A Coherence-Conditioned Encoder–Decoder Network for Robust InSAR Time-Series Deformation Extraction in Open-Pit Mines. Remote Sensing, 18(7), 984. https://doi.org/10.3390/rs18070984
Vancouver
Wang Y, Kong X, Bai Z, Li Y, Lu Y, Tang W, et al. CED-LSTM: A Coherence-Conditioned Encoder–Decoder Network for Robust InSAR Time-Series Deformation Extraction in Open-Pit Mines. Remote Sensing. 2026;18(7):984. doi:10.3390/rs18070984
BibTeX
@article{Wang2026,
author = {Wang, Yanping and Kong, Xiangbo and Bai, Zechao and Li, Yang and Lu, Yao and Tang, Weikai and Lin, Yun and Shen, Wenjie and Cai, Guanjun},
title = {CED-LSTM: A Coherence-Conditioned Encoder–Decoder Network for Robust InSAR Time-Series Deformation Extraction in Open-Pit Mines},
journal = {Remote Sensing},
year = {2026},
volume = {18},
number = {7},
pages = {984},
doi = {10.3390/rs18070984}
}
EUVIMED