HLSTM: Heterogeneous Long Short-Term Memory Network for Large-Scale InSAR Ground Subsidence Prediction
Qinghao Liu, Yonghong Zhang, Jujie Wei, Hongan Wu, Min Deng
Abstract
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 study, a heterogeneous long short-term memory (HLSTM) network is proposed for large-scale ground subsidence prediction based on InSAR data. Firstly, the study area is divided into homogeneous subregions through spatial clustering of InSAR-derived subsidence velocity. Secondly, 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 between 2017 to 2019. The HLSTM result shows the highest prediction accuracy through comparisons with the results from other seven methods.