ConvLSTM神经网络的时序InSAR地面沉降时空预测

何毅, 姚圣, 陈毅, 闫浩文, 张立峰

何毅, 姚圣, 陈毅, 闫浩文, 张立峰. ConvLSTM神经网络的时序InSAR地面沉降时空预测[J]. 武汉大学学报 ( 信息科学版). DOI: 10.13203/j.whugis20220657
引用本文: 何毅, 姚圣, 陈毅, 闫浩文, 张立峰. ConvLSTM神经网络的时序InSAR地面沉降时空预测[J]. 武汉大学学报 ( 信息科学版). DOI: 10.13203/j.whugis20220657
HE Yi, YAO Sheng, CHEN Yi, YAN Haowen, ZHANG Lifeng. Spatio-temporal prediction of time-series InSAR Land subsidence based on ConvLSTM neural network[J]. Geomatics and Information Science of Wuhan University. DOI: 10.13203/j.whugis20220657
Citation: HE Yi, YAO Sheng, CHEN Yi, YAN Haowen, ZHANG Lifeng. Spatio-temporal prediction of time-series InSAR Land subsidence based on ConvLSTM neural network[J]. Geomatics and Information Science of Wuhan University. DOI: 10.13203/j.whugis20220657

ConvLSTM神经网络的时序InSAR地面沉降时空预测

基金项目: 

自然资源部:城市国土资源监测与模拟重点实验室开放基金资助项目(编号:KF-2021-06-014);甘肃省自然科学基金(编号:20JR10RA249);兰州交通大学“天佑青年托举人才计划”基金项目(编号:1520260109);兰州交通大学优秀平台(编号:201806)

详细信息
    作者简介:

    何毅,教授,主要从事生态遥感和地质灾害等方面研究。heyi@mail.lzjtu.cn

    通讯作者:

    陈毅,硕士。cy_rser@163.com

  • 中图分类号: P237

Spatio-temporal prediction of time-series InSAR Land subsidence based on ConvLSTM neural network

  • Abstract:

    Objective:  Existing spatio-temporal prediction methods of land subsidence have some problems, such as poor ability to capture time-series features and ignoring spatial neighborhood features, which lead to poor reliability of spatio-temporal prediction of land subsidence.   Method:  In this study, a spatio-temporal prediction of land subsidence based on convolutional long short-term memory (ConvLSTM) neural network is proposed, which can capture time-series features and spatial neighborhood features. Beijing Capital International Airport (BCIA) was selected as the experimental area. Firstly, based on Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR), Sentinel-1A images were used to obtain the spatio-temporal InSAR data of land subsidence at BCIA, and then a ConvLSTM model was constructed to predict the land subsidence in the next year. Permanent scatters InSAR (PS-InSAR), SBAS-InSAR and benchmark results were used to cross-verify the reliability of time-series InSAR results. Time-series InSAR land subsidence data were segmented by sliding windows to form a many-to-one data set model. Combined with wavelet transform and evaluation indexes to determine the optimal time step of the prediction model, the ConvLSTM spatiotemporal prediction model of time-series InSAR land subsidence was established.   Results:  The R2 of the predicted and real results reached 0.997. Meanwhile, the performance of the model was further evaluated based on the image evaluation index structural similarity (SSIM) and multi-scale structural similarity (MS-SSIM), and the SSIM and MS-SSIM reached 0.914 and 0.975, respectively.   Conclusion:  In addition, support vector regression (SVR), multilayer perceptron (MLP), convolutional neural network, CNN) and the Long-Term Memory neural network (LSTM) model were compared and analyzed, and each index revealed that the model proposed in this paper was optimal. The ConvLSTM spatial-temporal prediction model was used to predict that the maximum cumulative subsidence at BCIA will reach 157 mm by November 2022. This study can provide key technical support for the early prevention of urban land subsidence.

  • [1] Cao Qun, Chen Bei Bei, Gong Hui Li, et al. Monitoring of land subsidence in Beijing-TianjinHebei Urban by combination of SBAS and IPTA. Journal of Nanjing University (Natural Science),2019,55(03):381-391. (曹群,陈蓓蓓, 宫辉力, 等. 基于SBAS和IPTA技术的京津冀地区地面沉降监测. 南京大学学报(自然科学),2019,55(03):381-391)
    [2]

    He Y, Chen Y D, Wang W H, et al. TS-InSAR analysis for monitoring ground deformation in Lanzhou New District, the loess Plateau of China, from 2017 to 2019. Advances in Space Research,2020,67(4)

    [3]

    Wang W, He Y, Zhang L, et al. Analysis of surface deformation and driving forces in Lanzhou. Open Geosciences,2020,12(1):1127- 1145

    [4] Chen You Dong, He Yi, Zhang Li Feng, et al. Research on Ground Deformation Monitoring Technique of Jointing Ascending and Descending Sentinel-1A. Hydrographic Surveying and Charting,2020,40(04):59-64(陈有东, 何毅, 张立峰, 等. 联合升降轨Sentinel-1A的地表形变监测技术研究. 海洋测绘,2020,40(04):59-64)
    [5] Wang Wen Hui, He Yi, Zhang Li Feng, et al. Ground deformation monitoring and driving force analysis of the main city area in Lanzhou based on PS-InSAR and GeoDetector. Journal of Lanzhou university (natural sciences), 2021, 57(03):382-388+394(王文辉, 何毅, 张立峰, 等. 2021. 基于PS-InSAR和GeoDetector的兰州主城区地表变形监测与驱动力分析. 兰州大学学报(自然科学版), 57(03):382-388+394)
    [6] Yang Cheng Sheng, Zhang Qin, Zhao Chao Ying, et al. Small Baseline Bubset InSAR Technology Used in Datong Basin Ground Subsidence, Fissure and Fault Zone Monitoring[J].Geomatics and Information Science of Wuhan University, 2014, 39(8):945-950.(杨成生, 张勤, 赵超英, 等. 短基线集InSAR技术用于大同盆地地面沉降、地裂缝及断裂活动监测[J]. 武汉大学学报(信息科学版), 2014, 39(8):945-950)
    [7] Yang Meng Shi, Liao Ming Sheng, Shi Xu Guo, et al. Land Subsidence Monitoring by Joint Estimation of Multi-platform Time Series InSAR Observations[J]. Geomatics and Information Science of Wuhan University, 2017, 42(6):797- 802.(杨梦诗, 廖明生, 史绪国, 等. 联合多平台InSAR数据集精确估计地表沉降速率场[J]. 武汉大学学报(信息科学版),2017,42(6):797-802)
    [8] Li Yong Shen, Zhang Jing Fa, Li Zheng Hong, et al. Land Subsidence in Beijing City from InSAR Time Series Analysis with Small Baseline Subset[J]. Geomatics and Information Science of Wuhan University, 2013, 38(11):1374-1377.(李永生, 张景发, 李振洪, 等. 利用短基线集干涉测量时序分析方法监测北京市地面沉降[J]. 武汉大学学报(信息科学版),2013,38(11):1374-1377)
    [9] Lin Hui, Ma Pei Feng, Wang Wei Xi. Urban Infrastructure Health Monitoring with Spaceborne Multi-temporal Synthetic Aperture Radar Interferometry. Acta Geodaetica et Cartographica Sinica,2017,46(10):1421-1433(林珲, 马培峰, 王伟玺.监测城市基础设施健康的星载MT-InSAR方法介绍. 测绘学报.2017,46(10):1421-1433)
    [10]

    Berardino P, Fornaro G, Lanari R, et al. A new algorithm for surface deformation monitoring based on small baseline differential SAR interferograms. IEEE Transaction on Geoscience & Remote Sensing,2002,40(11):2375-2383

    [11]

    Yang C, Zhang Q, Zhao C, et al. Monitoring land subsidence and fault deformation using the small baseline subset InSAR technique:A case study in the Datong Basin, China. Journal of Geodynamics,2014,75:34-40

    [12]

    Ye S, Luo Y, Wu J, et al. Three-dimensional numerical modeling of land subsidence in Shanghai, China. Hydrogeology Journal,2016,24(03):695-709

    [13]

    Tang Y, Cui Z, Wang J, et al. Application of grey theory-based model to prediction of land subsidence due to engineering environment in Shanghai. Environmental Geology,2008,55(03):583-593.

    [14] Fan Ze Lin and Zhang Yong Hong. Summary of the application of intelligent algorithms in the prediction of ground subsidence. Surveying and Spatial Geographic Information,2019,42(05):193-8. (范泽琳, 张永红. 智能算法在地面沉降预测中的应用综述. 测绘与空间地理信息. 2019,42(05):193-8)
    [15] Pan Hong Yu, Zhao Yun Hong, Zhang Wei Dong, et al. Prediction of surface subsidence with improved BP neural network based on Adaboost.Coal Science And Technology,2019, 47(02):161-167(潘红宇, 赵云红, 张卫东, 等. 2019. 基于Adaboost的改进BP神经网络地表沉陷预测.煤炭科学技术, 47(02):161-167)
    [16] Peng Li Shun, Cai Run, Liu Jin Bo, et al. Settlement Prediction of Highway Subgrades Based on Genetic Optimization Neural Network. China Earthquake Engineering Journal,2019,41(01):124-130+207(彭立顺, 蔡润, 刘进波, 等. 基于遗传优化神经网络的高速公路路基沉降量预测. 地震工程学报,2019,41(01):124-130+207)
    [17]

    Hochreiter S, Schmidhuber J. Long Short-Term Memory. Neural Computation,1997,9:1735-1780

    [18]

    Radman A, Akhoondzadeh M, Hosseiny B. Integrating InSAR and deep-learning for modeling and predicting subsidence over the adjacent area of Lake Urmia, Iran. GIScience & Remote Sensing,2021,58(08):1413-1433

    [19]

    Chen Y, He, Y, Zhang L F, et al. Prediction of InSAR deformation time-series using a long short-term memory neural network. International Journal of Remote Sensing,2021,42:6919-6942

    [20] Liu Qing Hao, Zhang Yong Hong, et al. Time series prediction method of large-scale surface subsidence based on deep learning. Acta Geodaetica et Cartographica Sinica,2021,46(3):396-404(刘青豪, 张永红, 邓敏, 等.大范围地表沉降时序深度学习预测法. 测绘学报,2021,46(3):396-404)
    [21] Chen Yi, He Yi, Zhang Li Feng, et al. Surface deformation prediction based on TS-InSAR technology and long short-term memory networks. National Remote Sensing Bulletin,2022,26(7):1326-1341(陈毅, 何毅, 张立峰,等.长短时记忆网络TS-InSAR地表形变预测. 遥感学报,2022,26(7):1326-1341)
    [22] Cheng Cheng. Research and application of equipment remaining life prediction algorithm based on deep learning[D]. Beijing:Beijing University of Chemical Technology,2020. (程成. 基于深度学习的设备剩余寿命预测算法研究及其应用[D]. 北京:北京化工大学, 2020)
    [23]

    Ma P F, Zhang F, Lin H. Prediction of InSAR time-series deformation using deep convolutional neural networks. Remote Sensing Letters,2020,11(2):137-145

    [24]

    Sun J, Wauthier C, Stephens K, et al. Automatic detection of volcanic surface deformation using deep learning. Journal of Geophysical Research:Solid Earth,2020,125, e2020JB019840.

    [25]

    He Y, Zhao Z A, Yang W, et al. A unified network of information considering superimposed landslide factors sequence and pixel spatial neighbourhood for landslide susceptibility mapping. International Journal of Applied Earth Observation and Geoinformation,2021,104(18):102508

    [26]

    Shi X, Chen Z, Wang H, et al. Convolutional LSTM Network:A Machine Learning Approach for Precipitation Nowcasting. Advances in Neural Information Processing Systems,2015,802-810

    [27] Yu X Y. Improved SBAS technology for land deformation detection and groundwater application[D]. Hu Nan:Central South University, 2012. (俞晓莹. 改进的SBAS地表形变监测及地下水应用研究[D],湖南:中南大学,2012)
    [28]

    Moré J J. The Levenberg-Marquardt algorithm:implementation and theory. Numerical analysis. Berlin, Heidelberg:Springer:105-116,1978.

    [29]

    Wang Z, Bovik A, Sheikh H, et al. Image Quality Assessment:From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing,2004,13(04):600-612

    [30] Zhao Yan, Meng Li Ru, Wang Shi Gang, et al. lmproved PSNR evaluation method consistent with human visual perception. Journal of Jilin University(Engineering and Technology Edition),2015,45(01):309-313(赵岩, 孟丽茹, 王世刚, 等. 符合人眼视觉感知特性的改进PSNR评价方法. 吉林大学学报(工学版),2015,45(01):309-313)
    [31]

    Zhu L, Gong H L, Li X, et al. Land subsidence due to groundwater withdrawal in the northern Beijing plain, China. Engineering Geology,2015,193:243-255

    [32]

    Gao M, Gong H, Chen B, et al. InSAR timeseries investigation of long-term ground displacement at Beijing Capital International Airport, China. Tectonophysics,2016,691:271- 281

    [33]

    Dai K, Liu G, Li Z, et al. Monitoring highway stability in permafrost regions with X-band temporary scatterers stacking InSAR[J]. Sensors,2018,18(6):1876.

    [34]

    Gao M, Gong H, Li X, et al. Land subsidence and ground fissures in Beijing capital international airport (bcia):Evidence from quasi-ps insar analysis[J]. Remote Sensing,2019,11(12):1466.

    [35]

    Dai K, Shi X, Gou J, et al. Diagnosing subsidence Geohazard at Beijing capital international airport, from high-resolution SAR interferometry[J]. Sustainability,2020,12(6):2269.

计量
  • 文章访问数:  657
  • HTML全文浏览量:  65
  • PDF下载量:  157
  • 被引次数: 0
出版历程
  • 收稿日期:  2023-06-03
  • 网络出版日期:  2023-07-05

目录

    /

    返回文章
    返回