自然资源遥感2025，Vol.37Issue(5)：141-151,11.DOI:10.6046/zrzyyg.2024299
利用C-LSTM的时序InSAR地表形变趋势分析及预测方法
Trend analysis and prediction method of ground deformation using TS-InSAR-based combination-long short-term memory
摘要
Abstract
Time-series interferometric synthetic aperture radar(TS-InSAR)technology has been widely used in ground deformation monitoring and prediction.However,current research remains insufficient in the correlation and temporal lag between groundwater and ground deformation.Moreover,InSAR-based prediction models for ground deformation mostly rely on a single InSAR data,which limits the prediction accuracy and generalization ability of the models.To address these challenges,this study proposed a combination-long short-term memory(C-LSTM)model that integrates groundwater level,rainfall,and InSAR deformation data.This model was employed to evaluate the prediction and accuracy of single-factor and multi-factor models,respectively.The results revealed a temporal lag between ground deformation and changes in groundwater level.The optimal feature combination,obtained through model training using groundwater and rainfall data,exhibited significant improvements in prediction accuracy compared to single-factor predictions,with the coefficient of determination(R2)increasing by 2.45%,1.52%,4.16%,8.08%,5.08%,and 1.45%respectively.The model enhances the prediction accuracy of ground deformation by incorporating model feature combinations with high correlation with ground deformation.关键词
时序InSAR/地表形变/相关性分析/C-LSTMKey words
time-series interferometric synthetic aperture radar(TS-InSAR)/ground deformation/correlation a-nalysis/combination-long short-term memory(C-LSTM)分类
信息技术与安全科学引用本文复制引用
文艺,张玲,孔含泉,万祥星,葛大庆,刘斌..利用C-LSTM的时序InSAR地表形变趋势分析及预测方法[J].自然资源遥感,2025,37(5):141-151,11.基金项目
中国自然资源航空物探遥感中心青年创新基金"多维观测下滑坡InSAR时序监测与形变分解方法"(编号:2023YFL26)和国家重点研发计划项目"广域重大地质灾害隐患综合遥感识别技术研发"(编号:2021YFC3000400)共同资助. （编号:2023YFL26）
