HLSTM: Heterogeneous Long Short-Term Memory Network for Large-Scale InSAR Ground Subsidence Prediction

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing 2021, Vol.14, p.8679-8688
• Main Authors: Liu, Qinghao, Zhang, Yonghong, Wei, Jujie, Wu, Hongan, Deng, Min
• Format: Article
• Language: English
• Subjects: Clustering; Data models; Deep learning; Geological hazards; Geology; Heterogeneity; Image acquisition; Indexes; Interferometric synthetic aperture radar; interferometric synthetic aperture radar (InSAR); Long short-term memory; long short-term memory (LSTM); Mitigation; Patchiness; Predictions; Predictive models; SAR (radar); Spatial heterogeneity; Strain; Subsidence; subsidence prediction; Time series analysis; Training
• ISSN: 1939-1404; 2151-1535
• DOI: 10.1109/JSTARS.2021.3106666

Accurate prediction of ground subsidence is of great significance for the prevention and mitigation of this type of geological disaster. It is still a challenge when wide area is concerned. In this article, a heterogeneous long short-term memory (HLSTM) network is proposed for large-scale ground subsidence prediction based on interferometric synthetic aperture radar (InSAR) data. First, the study area is divided into homogeneous subregions through spatial clustering of InSAR-derived subsidence velocity. Second, a specific LSTM model is constructed to capture complex nonlinear temporal correlations embedded in InSAR-derived subsidence time series for each subregion. Essentially both spatial heterogeneity and temporal correlation are incorporated into the HLSTM prediction. In the experiment part, the HLSTM predictor is validated using a subsidence monitoring result from 80 Sentinel-1 images acquired over Cangzhou, China, from 2017 to 2019. The HLSTM result shows the highest prediction accuracy through comparisons with the results from other seven methods.