Analysis and Prediction of Land Surface Subsidence Along Kunming Metro Based on InSAR
Current researches on the ground subsidence of metro network mainly focus on large cities such as Beijing,Shanghai,Guang-zhou and Shenzhen,but has few of them on systematic research on the ground subsidence of metro network in complex geological areas in west-ern China.Based on PS-InSAR technology,this paper obtains the monitoring results of ground subsidence along Kunming metro during 2018-2022,and then establishes the LSTM surface subsidence prediction model according to it.Moreover,future prediction for typical areas was made.The results show that the surface subsidence rate is positively correlated with the geological complexity to some extent.LSTM surface subsidence prediction model has high accuracy.In the process of prediction,it is found that this kind of model is not suitable for long-term forecast,for long-term forecast results will appear periodic oscillation,resulting in model failure.Although the LSTM model is only suitable for short-term prediction,its prediction results can be used as auxiliary decision-making and early warning.
NETL
NSTL
万方数据
