Land Subsidence Time Series Prediction Method Based on LSTM-AMSGD

Abstract Accurate prediction of geological subsidence is great importance for hazard risk assessment. Various existing models do not take into account the time correlation between subsidence, and effect lacks practical significance. In this paper, an LSTM-AMSGD-based land method proposed. Firstly, high-precision series inversion results large-area surface deformation are obtained by small baseline interference technique with multiple principal image coherent targets. Secondly, a recurrent neural network (LSTM-AMSGD) used as architecture. The final cumulative error within 0.3 mm, single-step more than 400,000 observation points can be completed in 126s. Therefore, LSTM-AMSGD model paper effective subsidence.