关键词: SBAS-InSAR, DS-InSAR, LSTM, 输电通道, 形变监测

Abstract: This paper combines SBAS-InSAR and DS-InSAR technologies to monitor and predict the deformation of the extra-high voltage transmission corridor in Wufeng county, aiming to improve the safety of the transmission line and the disaster warning capability. Firstly,combining these two techniques, a multi-scale deformation monitoring model is established, which provides finer data support for risk assessment of transmission lines. Then, this paper introduces a long short-term memory (LSTM) neural network model for time series prediction of ground subsidence trends. By training and testing the Sentinel-1A satellite data from October 2023 to October 2024, the LSTM model shows high prediction accuracy, with the maximum absolute error of 3.28 mm, the minimum absolute error of 0.13 mm, and the root-mean-square error (RMSE) of 1.32 mm, which verifies the validity and reliability of the model in ground deformation prediction. The study shows that the LSTM model is able to capture the long-term trend of subsidence changes and provide strong support for the maintenance of transmission corridors and disaster warning.

Key words: SBAS-InSAR, DS-InSAR, LSTM, voltage transmission channels, deformation monitoring