 This paper proposes a new method for predicting surface subsidence caused by coal mining using interferometric synthetic aperture radar, NSER, technology combined with long short-term memory, LSTM, algorithms. The study area is the Shigui coal field in Ningxia Province, China, where time series ground subsidence data were collected from March 9, 2015 to June 7, 2016. The results showed that the proposed approach can accurately predict mine subsidence, with maximum absolute errors of less than 2 cm and maximum relative errors of less than 6%. This demonstrates that combining NSER technology with the LSTM algorithm is an effective and robust approach for predicting mine subsidence. This article was authored by Fei Ma, Lijuan Sui, and Wei Lian.