Prediction of InSAR deformation time-series using improved LSTM deep learning model

Mining-induced subsidence is one of the major concerns of mining industry/mine owners, statutory bodies, and environmental organisations. Therefore, mine subsidence monitoring and prediction is of utmost importance for its effective management. In the present study, a modified LSTM model is developed to predict the InSAR deformation time series. The modified LSTM model may also be extended for prediction based on time-series data in general. Further, to check the developed model's performance, InSAR deformation time-series results obtained from 26 TSX/TDX datasets of Mine-A in Khetri Copper Belt, India, are used as an input. Further obtained results from mLSTM have been compared with the other two models, namely RNN and LSTM. Efficiency comparison results reveal that RNN, LSTM, and modified LSTM over the applied single reference PSI-derived deformation time-series result are 82.6%, 97.54%, and 98.57%, respectively. It also reveals that the RMS error of RNN, LSTM, and modified LSTM over the applied single reference PSI-derived deformation time-series result are 6.58 mm/year, 5.34 mm/year and 4.22 mm/year, respectively. In addition, the study reveals that the prediction of the mLSTM model, compared to RNN and LSTM, is quite close to the observed/measured deformation velocity values obtained from a single reference PSI-derived result. Furthermore, prediction for the next five years using mLSTM shows that the maximum value of the deformation is -20.87 mm/year and a minimum of 4.99 mm/year. Predictions for the next five years show that most of the area is stable, but points around the plant area have shown some deformation.