A TCN-LACA-GRU Model for Interpretable Surface Subsidence Prediction with Rainfall Lag Effects

Xiaohui Hu; Jiali Wang; Xiaojing Tang; Zhenxi Hu; Xiaolin Ma; Xiwen Chen

doi:10.47297/taposatWSP2633-456901.20260703

PDF
导出
分享
收藏
专辑

A TCN-LACA-GRU Model for Interpretable Surface Subsidence Prediction with Rainfall Lag Effects

7卷第3期

浏览量: 0 Downloads: 4

A TCN-LACA-GRU Model for Interpretable Surface Subsidence Prediction with Rainfall Lag Effects
A TCN-LACA-GRU Model for Interpretable Surface Subsidence Prediction with Rainfall Lag Effects
School of Data Science and Engineering, South China Normal University, Shanwei, Guangdong, 516000, China
2026年7卷第3期页码：5-9
纸质出版：2026-03-30
DOI：10.47297/taposatWSP2633-456901.20260703
Accepted：

Scan QR Code

Xiaohui Hu, Jiali Wang, Xiaojing Tang, Zhenxi Hu, Xiaolin Ma & Xiwen Chen. (2026). A TCN-LACA-GRU Model for Interpretable Surface Subsidence Prediction with Rainfall Lag Effects. 科技理论与实践（英文版）, 7(3), 5-9.

Hu Xiaohui,Wang Jiali,Tang Xiaojing,et al.A TCN-LACA-GRU Model for Interpretable Surface Subsidence Prediction with Rainfall Lag Effects[J].Theory and Practice of Science and Technology,2026,07(03):5-9.
Xiaohui Hu, Jiali Wang, Xiaojing Tang, Zhenxi Hu, Xiaolin Ma & Xiwen Chen. (2026). A TCN-LACA-GRU Model for Interpretable Surface Subsidence Prediction with Rainfall Lag Effects. 科技理论与实践（英文版）, 7(3), 5-9. DOI： 10.47297/taposatWSP2633-456901.20260703.

Hu Xiaohui,Wang Jiali,Tang Xiaojing,et al.A TCN-LACA-GRU Model for Interpretable Surface Subsidence Prediction with Rainfall Lag Effects[J].Theory and Practice of Science and Technology,2026,07(03):5-9. DOI： 10.47297/taposatWSP2633-456901.20260703.

摘要

Abstract

Surface subsidence poses a persistent hazard in coastal and reclaimed areas

where long-term ground deformation can jeopardize buildings

roads

pipelines

and other infrastructure. In these environments

precipitation serves as a significant external driver

as rainfall infiltration can modify groundwater conditions

pore-water pressure

and soil consolidation. However

the impact of rainfall on deformation is seldom immediate; it is typically nonlinear

cumulative

and delayed

complicating accurate predictions. Traditional statistical methods and many data-driven models often overlook rainfall or treat it merely as a secondary input

thereby constraining both predictive performance and physical interpretability. To address this limitation

this study introduces a TCN-LACA-GRU framework for short-term multi-step surface subsidence prediction. The model employs a Temporal Convolutional Network to extract local rainfall features

a Lag-Aware Cross-Attention module to account for the varying influence of antecedent rainfall on current deformation

and a GRU predictor to forecast future subsidence values. This methodology is applied to the Shanwei campus of South China Normal University

utilizing Sentinel-1 deformation observations and NOAA precipitation data from the Shanwei station. Results demonstrate that the proposed model significantly outperforms traditional baselines and achieves accuracy comparable to the best pure sequence deep-learning model. Notably

the attention weights reveal that the effects of rainfall are concentrated in earlier periods rather than at the current time step

aligning with the delayed infiltration and consolidation processes. The framework therefore provides both strong predictive performance and a more interpretable understanding of rainfall-driven subsidence evolution.

关键词

Keywords

references

BERARDINO Paolo, FORNARO Gianfranco, LANARI Riccardo, et al. A new algorithm for surface deformation monitoring based on small baseline differential SAR interferograms[J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(11): 2375-2383.

FERRETTI Alessandro, PRATI Claudio, ROCCA Fabio. Permanent scatterers in SAR interferometry[J]. IEEE Transactions on Geoscience and Remote Sensing, 2001, 39(1): 8-20.

WANG Fuqiang, LIU Quanming, LI Ruiping, et al. Surface Deformation Monitoring and Prediction of InSAR-Hybrid Deep Learning Model for Subsidence Funnels[J]. Remote Sensing, 2025, 17(17): 2972.

ZHANG Zhihua, LIN Qiang, YAN Haowen, et al. Ground subsidence monitoring and prediction based on InSAR and CNN-BiGRU-Attention[J]. Engineering Geology, 2025, 357: 108336.

ZHU Mingfei, YU Xuexiang, TAN Hao, et al. High-precision monitoring and prediction of mining area surface subsidence using SBAS-InSAR and CNN-BiGRU-attention model[J]. Scientific Reports, 2024, 14: 28968.

CUI Haiwei, LV Weicai, HAN Yuchen, et al. A hybrid SBAS-InSAR and LSTM-Transformer approach for predicting mining-induced surface subsidence[J]. Open Geosciences, 2026, 18(1): 20250930.

ZHANG Jiayi, GAO Jian, GAO Fanzong. Time series land subsidence monitoring and prediction based on SBAS-InSAR and GeoTemporal transformer model[J]. Earth Science Informatics, 2024, 17: 5899-5911.

ZHOU Chao, YE Mingyuan, XIA Zhuge, et al. An interpretable attention-based deep learning method for landslide prediction based on multi-temporal InSAR time series[J]. Remote Sensing of Environment, 2025, 318: 114580.

ZHANG Jinlai, KOU Pinglang, TAO Yuxiang, et al. Urban ground subsidence monitoring and prediction using time-series InSAR and machine learning approaches[J]. Environmental Earth Sciences, 2024, 83: 473.

Luo Yiyuan, Xu Qiang, Jiang Yanan, et al. A Large-Scale Land Subsidence Prediction Method Based on Time-Series InSAR and Machine Learning[J]. Earth Science, 2024, 49(05): 1736-1745.

BAI Shaojie, KOLTER J Zico, KOLTUN Vladlen. An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling[EB/OL]. (2018-03-04).