Abstract: Hancheng city,a city born out of coal,is rich in mineral resources and has diverse geological structures and ecological environments.It is also prone to frequent geological disasters.Monitoring and analyzing the surface stability of the entire region over the past few years is of great significance.Currently,research on Hancheng primarily focuses on short-term studies of local mining areas,with insufficient attention paid to monitoring and predicting surface stability across the entire region.In this study,we utilize advanced time-series InSAR technology and deep learning algorithms to process the SAR dataset from the Sentinel-1 satellite that covers the entire Hancheng from 2019 to 2023,to obtain the surface deformation of the whole Hancheng and predict its future development trend.It will also conduct a focused analysis on the surface instability caused by typical mining activities in the area.The results indicate that deformation areas are highly correlated with geological conditions and human activities in terms of spatiotemporal distribution.The local deformation rate exceeds -50 mm/a,and the maximum cumulative settlement reaches approximately 250 mm.The established deep learning model performs well in deformation fitting and prediction for the study area.The mean absolute error,root mean squared error,and mean absolute percentage error are 0.30,1.08,and 11.76 cm,respectively.The research results can provide methodological references and data support for the census and prevention of surface instability and geological disasters in Hancheng city.

Key words: Hancheng city, time-series InSAR, deep learning, deformation monitoring, deformation prediction