Abstract: Regarding the safety issues caused by subsidence due to mining,this study takes the Heidaigou coal mine in Ordos city,Inner Mongolia as an example.Using SBAS-InSAR technology,it obtained monitoring results of deformation in the internal dumping site in the study area from August 2021 to April 2023,and employed both the LSTM neural network model and an improved LSTM-ARIMA model to conduct time series predictions of slope feature points in the mine's internal dumping site.The research results indicate that: ①The annual average deformation rate of the internal dumping site at Heidaigou coal mine from August 2021 to April 2023 ranged from -458.76 to 4.44 mm/a.Cross-validation using PS-InSAR technology showed a coherence coefficient of 0.86 for homologous points between the two methods.②Analysis of the deformation results revealed that the displacement on the eastern slope was greater than that on the western slope.Further analysis of the causes of subsidence found that heavy rainfall accelerates deformation.③The LSTM-ARIMA model optimized with the ARIMA model demonstrated better stability in time series prediction compared to LSTM alone and showed higher prediction accuracy,with R² values all above 0.85.The study provides strong technical support and theoretical reference for precise monitoring,risk warning,and scientific control of mine dumping sites.

Key words: SBAS-InSAR, dump, deformation monitoring, LSTM-ARIMA model