Enhancing 4‐D Landslide Monitoring and Block Interaction Analysis With a Novel Kalman‐Filter‐Based InSAR Approach DOI
Wanji Zheng, Jun Hu, Zhong Lu

и другие.

Journal of Geophysical Research Earth Surface, Год журнала: 2024, Номер 129(11)

Опубликована: Окт. 31, 2024

Abstract In recent years, Synthetic Aperture Radar Interferometry (InSAR) has become widely utilized for slow‐moving landslide monitoring due to its high resolution, accuracy, and extensive coverage. By integrating data from various orbits/platforms sources, one‐dimensional (1‐D) line‐of‐sight (LOS) InSAR measurements can be explored infer three‐dimensional (3‐D) movements. However, inconsistencies in observation times among different orbits sources pose challenges accurately capturing dynamic 3‐D movements over time (referred as 4‐D). this study, we propose a novel method, termed KFI‐4D that incorporates spatiotemporal constraints into the traditional Kalman filter. This enhancement transforms underdetermined problem of 4‐D movement acquisition parameter estimation problem, enabling precise The method was evaluated using both synthetic sets real Hooskanaden landslide, demonstrating an improvement exceeding 50% root mean square errors (RMSEs) compared conventional methods. Additionally, high‐resolution characteristics InSAR‐derived allow analysis strain invariants, providing insights block interactions dynamics. Our findings reveal invariants effectively indicate distribution activity blocks slip surfaces well their response triggers. Notably, abnormal signals identified prior catastrophic event at suggest potential early warning landslides. future integration advanced satellites, such NISAR, ALOS4 PALSAR3, Sentinel‐1C, is expected further enhance method's capabilities, improving temporal resolution monitoring.

Язык: Английский

Measuring hydrological alterations and landscape patterns for sustainable development through ecosystem connectivity in Hastinapur Wildlife Sanctuary, India DOI
Sonali Kundu, Narendra Kumar Rana, Barnali Kundu

и другие.

Journal of Environmental Sciences, Год журнала: 2025, Номер unknown

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0
Integration of interpretable machine learning and MT-InSAR for dynamic enhancement of landslide susceptibility in the Three Gorges Reservoir Area DOI Creative Commons
Fancheng Zhao, Fasheng Miao, Yiping Wu

и другие.

Journal of Rock Mechanics and Geotechnical Engineering, Год журнала: 2025, Номер unknown

Опубликована: Май 1, 2025

Язык: Английский

Процитировано

0
Understanding the triggering mechanism and deformation characteristics of a reactivated landslide in the Baihetan Reservoir DOI

Xingtao Beng,

Guangcheng Zhang, Linkang Wang

и другие.

Natural Hazards, Год журнала: 2025, Номер unknown

Опубликована: Май 25, 2025

Язык: Английский

Процитировано

0
Research and analysis of the TCN-Multihead-Attention prediction model of landslide deformation in the Three Gorges Reservoir area, China DOI Creative Commons
Huan Chen, Yixuan Li, Y. Liu

и другие.

Frontiers in Earth Science, Год журнала: 2025, Номер 13

Опубликована: Июнь 3, 2025

Landslide deformation prediction is a crucial task in geotechnical engineering and disaster prevention. Developing an accurate reliable landslide displacement model vital for effective warning systems. This paper proposes TCN-Multihead-Attention based on temporal convolutional networks (TCNs). We collected 8 years of monitoring data from the Huangniba Dengkan Three Gorges Reservoir area, including surface (horizontal elevation), rainfall, reservoir levels. A comprehensive analysis was conducted to assess effects levels, elevation horizontal displacement. Utilizing multi-input single-output characteristics long-period time series dataset, we developed deformation. Model evaluation demonstrated that coefficient determination (R 2 ) test set reached 0.995, with MAPE RMSE at only 0.482 7.180, respectively, indicating high accuracy. Additionally, other models single TCN, Attention-based Transformer, RNN-based LSTM, hybrid CNN-BiLSTM comparison. Compared existing models, integrates dilated causal convolutions TCN multi-head attention effectively fuse nonlinear interactions multi-source environmental factors, capture long-term evolutionary trends, accurately identify local mutation patterns, demonstrating superior reliability forecasting regions.

Язык: Английский

Процитировано

0
Enhancing 4‐D Landslide Monitoring and Block Interaction Analysis With a Novel Kalman‐Filter‐Based InSAR Approach DOI
Wanji Zheng, Jun Hu, Zhong Lu

и другие.

Journal of Geophysical Research Earth Surface, Год журнала: 2024, Номер 129(11)

Опубликована: Окт. 31, 2024

Abstract In recent years, Synthetic Aperture Radar Interferometry (InSAR) has become widely utilized for slow‐moving landslide monitoring due to its high resolution, accuracy, and extensive coverage. By integrating data from various orbits/platforms sources, one‐dimensional (1‐D) line‐of‐sight (LOS) InSAR measurements can be explored infer three‐dimensional (3‐D) movements. However, inconsistencies in observation times among different orbits sources pose challenges accurately capturing dynamic 3‐D movements over time (referred as 4‐D). this study, we propose a novel method, termed KFI‐4D that incorporates spatiotemporal constraints into the traditional Kalman filter. This enhancement transforms underdetermined problem of 4‐D movement acquisition parameter estimation problem, enabling precise The method was evaluated using both synthetic sets real Hooskanaden landslide, demonstrating an improvement exceeding 50% root mean square errors (RMSEs) compared conventional methods. Additionally, high‐resolution characteristics InSAR‐derived allow analysis strain invariants, providing insights block interactions dynamics. Our findings reveal invariants effectively indicate distribution activity blocks slip surfaces well their response triggers. Notably, abnormal signals identified prior catastrophic event at suggest potential early warning landslides. future integration advanced satellites, such NISAR, ALOS4 PALSAR3, Sentinel‐1C, is expected further enhance method's capabilities, improving temporal resolution monitoring.

Язык: Английский

Процитировано

2