Earthformer_MSTSP: A Dynamic Simulation-Based Model for Mining Subsidence Prediction Using InSAR Observations
Open Access
- 13 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 1641-1659
Abstract
Mining-induced subsidence is a complex deformation process influenced by both human activities and natural factors, making accurate prediction essential. Conventional methods face challenges in spatial modeling, deformation interpretation, and computational efficiency. Although deep learning (DL) offers strong nonlinear modeling capabilities and avoids complex physical parameter constraints, its application to mining subsidence prediction remains limited. This study introduces a new prediction framework, Earthformer_MSTSP, and a Gaussian-based dynamic simulation method (MSDS_G) for generating training data. The synthesized dataset is trained using a Cuboid Attention.based hierarchical codec architecture. Using SBASInSAR displacement time series from the Datong mine as input, Earthformer_MSTSP achieves an MSE of 0.45 m and a 3.7% relative error in maximum subsidence, improving prediction accuracy by 74% over the Weibull model and 82% over LSTM. A transferability test in the Changwu mine shows that the model trained with MSDS_G effectively preserves the spatial deformation patterns, as verified by Moran.s I. Additionally, subsidence-rate-based early warning analysis and the impact of mining speed are explored, providing multiple indicators for hazard mitigation.Keywords
Funding Information
- Shaanxi Province Geoscience Big Data and Geohazard Prevention Innovation Team
- Generic Technical Development Platform of Shaanxi Province for Imaging Geodesy (2024ZG-GXPT-07)
- ESA-MOST China DRAGON-6 project (95355)
- Fundamental Research Funds for the Central Universities (300102261108)
- Fundamental Research Funds for the Central Universities (300102261308)
- Fundamental Research Funds for the Central Universities (300102264302)
This publication has 22 references indexed in Scilit:
- ConTraNet: A hybrid network for improving the classification of EEG and EMG signals with limited training dataComputers in Biology and Medicine, 2023
- Research on Gas Outburst Prediction Model Based on Multiple Strategy Fusion Improved Snake Optimization Algorithm With Temporal Convolutional NetworkIEEE Access, 2022
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows2021
- The Application of Convolutional Neural Networks to Detect Slow, Sustained Deformation in InSAR Time SeriesGeophysical Research Letters, 2019
- Surface subsidence prediction method of backfill-strip mining in coal miningBulletin of Engineering Geology and the Environment, 2019
- Time function model of dynamic surface subsidence assessment of grout-injected overburden of a coal mineInternational Journal of Rock Mechanics and Mining Sciences, 2018
- Modeling and analysis of mining subsidence disaster chains based on stochastic Petri netsNatural Hazards, 2018
- Locating and defining underground goaf caused by coal mining from space-borne SAR interferometryISPRS Journal of Photogrammetry and Remote Sensing, 2018
- Model for calculating the parameter of the Knothe time function based on angle of full subsidenceInternational Journal of Rock Mechanics and Mining Sciences, 2015
- Modifications of the Weibull distribution: A reviewReliability Engineering & System Safety, 2014