DACLnet: A Dual-Attention-Mechanism CNN-LSTM Network for the Accurate Prediction of Nonlinear InSAR Deformation
Open Access
- 5 July 2024
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 16 (13) , 2474
Abstract
Nonlinear deformation is a dynamically changing pattern of multiple surface deformations caused by groundwater overexploitation, underground coal mining, landslides, urban construction, etc., which are often accompanied by severe damage to surface structures or lead to major geological disasters; therefore, the high-precision monitoring and prediction of nonlinear surface deformation is significant. Traditional deep learning methods encounter challenges such as long-term dependencies or difficulty capturing complex spatiotemporal patterns when predicting nonlinear deformations. In this study, we developed a dual-attention-mechanism CNN-LSTM network model (DACLnet) to monitor and accurately predict nonlinear surface deformations precisely. Using advanced time series InSAR results as input, the DACLnet integrates the spatial feature extraction capability of a convolutional neural network (CNN), the advantages of the time series learning of a long short-term memory (LSTM) network, and the enhanced focusing effect of the dual-attention mechanism on crucial information, significantly improving the prediction accuracy of nonlinear surface deformations. The groundwater overexploitation area of the Turpan Basin, China, is selected to test the nonlinear deformation prediction effect of the proposed DACLnet. The results demonstrate that the DACLnet accurately captures developmental trends in historical surface deformations and effectively predicts surface deformations for the next two months in the study area. Compared to traditional LSTM and CNN-LSTM methods, the root mean square error (RMSE) of the DACLnet improved by 85.09% and 68.57%, respectively. These research results can provide crucial technical support for the early warning and prevention of geological disasters and can serve as an effective alternative tool for short-term ground subsidence prediction in areas lacking hydrogeological and other related data.Keywords
Funding Information
- China University of Geosciences (Beijing) University Student Innovation and Entrepreneurship Training Program (2652023069, 42174026)
- Fundamental Research Funds for the Central Universities (2652023069, 42174026)
- National Natural Science Foundation of China (2652023069, 42174026)
This publication has 49 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
- InSAR-based landslide detection method with the assistance of C-indexLandslides, 2023
- An energy‐frequency parameter for earthquake ground motion intensity measureEarthquake Engineering & Structural Dynamics, 2022
- Geological disaster monitoring and early warning system based on big data analysisArabian Journal of Geosciences, 2020
- Fusing adjacent-track InSAR datasets to densify the temporal resolution of time-series 3-D displacement estimation over mining areas with a prior deformation model and a generalized weighting least-squares methodJournal of Geodesy, 2020
- Linear discontinuous deformations created on the surface as an effect of underground mining and local geological conditions-case studyBulletin of Engineering Geology and the Environment, 2019
- Main frequency band of blast vibration signal based on wavelet packet transformApplied Mathematical Modelling, 2019
- Generalizing the Convolution Operator in Convolutional Neural NetworksNeural Processing Letters, 2019
- Deformation analysis of a burst red mud reservoir using combined descending and ascending pass ENVISAT ASAR dataNatural Hazards, 2012
- Geochemical characterization of aromatic hydrocarbons in crude oils from the Tarim, Qaidam and Turpan Basins, NW ChinaPetroleum Science, 2010