摘要
为探究曹妃甸沿海区的地表沉降情况,本文使用永久散射体合成孔径雷达干涉测量(PS-InSAR)和短基线合成孔径雷达干涉测量(SBAS-InSAR)技术对2017—2022年的63景Sentinel-1A数据进行反演,得到了沿海区的地表沉降速率及分布,再对两种技术的反演结果进行交叉验证及分析引起沉降的原因,同时利用反向传播(BP)神经网络和长短期记忆(LSTM)网络模型分别对特征点的时序沉降量进行预测分析及精度对比,主要得到以下几点结论:①两种技术反演结果具有较高一致性,线性相关达0.98;②研究区最大沉降速率为-49 mm/a,最大累计沉降量为231.4 mm,地质条件脆弱、长期过度开采地下水、大规模的建设和工程扰动是造成该地沉降发生的主要原因;③经对比分析,长短期记忆(LSTM)网络模型的预测效果更适合于时序形变数据的预测,预测结果也更为接近实际形变值。
In order to explore the surface subsidence in the coastal area of Caofeidian,permanent scatterer Synthetic Aperture radar interferometry(PS-InSAR)and short baseline synthetic aperture radar interferometry(SBAS-InSAR)were used to inversion 63 Sentinel-1A data from 2017 to 2022.The surface subsidence rate and distribution in coastal areas are obtained.Then the inversion results of the two technologies are cross-verified and the causes of subsidence are analyzed.At the same time,the back propagation(BP)neural network and the long and short term memory(LSTM)network model are used to predict and analyze the temporal subsidence amount of feature points and compare the accuracy.①The inversion results of the two techniques have a high consistency,with a linear correlation of 0.98;②The maximum subsidence rate of the study area is-49 mm/a,and the maximum cumulative subsidence is 231.4 mm.The main reasons for the subsidence are fragile geological conditions,long-term over-exploitation of groundwater,large-scale construction and engineering disturbance.③Through comparative analysis,the prediction effect of long and short term memory(LSTM)network model is more suitable for the prediction of time series deformation data,and the predicted result is more close to the actual deformation value.
作者
蔡文
刘向铜
曹秋香
CAI Wen;LIU Xiangtong;CAO Qiuxiang(School of Surveying and Geoinformation Engineering,East China University of Technology,Nanchang Jiangxi 330013,China;Key Laboratory of Mine Environmental Monitoring and Improving around Poyang Lake of Ministry of Natural Resources,East China University of Technology,Nanchang Jiangxi 330013,China;School of Earth Sciences,East China University of Technology,Nanchang Jiangxi 330013,China)
出处
《北京测绘》
2023年第8期1135-1140,共6页
Beijing Surveying and Mapping
基金
国家自然科学基金(42062013)
江西省教育厅(GJJ200726)
江西省哲学社会科学重点研究基地(21JDJC01)
江西省防震减灾与工程地质灾害探测工程研究中心开放基金(SDGD202004)
