AM-LSTM网络的北京平原东部地面沉降模拟
Land subsidence simulation in the east of Beijing plain based on the AM-LSTM Network
- 2022年26卷第7期 页码：1302-1314
纸质出版日期： 2022-07-07
DOI： 10.11834/jrs.20211297
扫 描 看 全 文
浏览全部资源
扫码关注微信
摘要
基于传统数值方法构建的地面沉降模拟预测模型需要大量的水文地质数据和实测数据，对于地质条件复杂地区的形变模拟预测难度大。本文基于PS-InSAR技术获取的北京平原东部地区的地面沉降信息，综合考虑不同层位地下水水位对沉降的影响，采用基于注意力机制的长短时记忆网络（AM-LSTM）对不同沉降发育地区典型位置处的地面沉降进行模拟。结果表明：（1）研究区地面沉降空间差异性明显，2010年11月—2016年8月最大沉降速率约153 mm/a，累计沉降量达到1063 mm，位于朝阳区三间房乡附近；（2）基于AM-LSTM模型的模拟精度优于传统LSTM模型，本次模拟精度最高提升了22%；（3）AM-LSTM模型注意力权重表明，第二承压含水层水位对地面沉降贡献最大。本次研究能够为地面沉降防控提供可靠的技术支撑。
Abstract
The simulation and prediction model of land subsidence based on traditional numerical methods requires a large amount of hydrogeological and measured data
and predicting the deformation in areas with complex geological conditions is difficult. In this study
on the basis of land subsidence information obtained by permanent scatterers–interferometry synthetic aperture radar (PS-InSAR) technology in the east of the Beijing plain and in consideration of the influence of groundwater level in different layers on subsidence
the long-term and short-term memory network (AM-LSTM) based on an attention mechanism is used to simulate the land subsidence at typical locations in different subsidence areas. Results show the following points. (1) The spatial difference of land subsidence in the study area is obvious. From October 2010 to August 2016
the maximum subsidence rate is about 153 mm/a
and the cumulative subsidence is 1063 mm. The area is located near Sanjianfang Township in Chaoyang District. (2) The simulation accuracy of the AM-LSTM model is better than that of the traditional LSTM model
and the accuracy of this simulation reaches 22%. (3) The attention weight of the AM-LSTM model indicates that the water level of the second confined aquifer contributes the most to land subsidence. These research findings can provide a reliable model for the prevention and control of land subsidence.
关键词
遥感地面沉降AM-LSTM模拟预测不同层位地下水水位注意力权重
Keywords
remote sensingland subsidenceAM-LSTMsimulation and predictiongroundwater level of different layersattention weight
references
Bahdanau D, Cho K and Bengio Y. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473
Bai L, Zhang Y J, Guo L L and Zhang T. 2015. Experimental research on effect of Biot coefficient on settlement formation//Proceedings of the 2015 National Engineering Geology Academic Annual Conference. Beijing: Science Press: 278-283
白林, 张延军, 郭亮亮, 张通. 2015. 岩石Biot系数对地层沉降量影响规律研究//2015年全国工程地质学术年会论文集. 北京: 科学出版社: 278-283
Cai D J, Yue J P, Chang W and Yang L. 2010. Application of wavelet neural network model in land subsidence monitoring based on genetic algorithm. Bulletin of Surveying and Mapping, 8: 34-36, 57
蔡东健, 岳建平, 成微, 杨柳. 2010. 基于遗传算法的小波神经网络模型及其在地面沉降监控中的应用. 测绘通报, 8: 34-36, 57
Chen B B, Gong H L, Chen Y, Li X J, Zhou C F, Lei K C, Zhu L, Duan L and Zhao X X. 2020. Land subsidence and its relation with groundwater aquifers in Beijing Plain of China. Science of the Total Environment, 735: 139111 [DOI: 10.1016/J.SCITOTENV.2020.139111http://dx.doi.org/10.1016/J.SCITOTENV.2020.139111]
Cheng S, Sui B B, Shen Y and Wang T. 2015. Prediction of mining ground settlement based on BP neural network. Geomatics and Spatial Information Technology, 38(3): 18-20
成枢, 隋冰冰, 沈毅, 王涛. 2015. 基于BP神经网络的矿区地表沉降预测研究. 测绘与空间地理信息, 38(3): 18-20 [DOI: 10.3969/j.issn.1672-5867.2015.03.007http://dx.doi.org/10.3969/j.issn.1672-5867.2015.03.007]
Di Francesco R. 2013. Exact solution of terzaghi’s consolidation equation and extension to two/three-dimensional cases. Applied Mathematics, 4(4): 713-717 [DOI: 10.4236/am.2013.44099http://dx.doi.org/10.4236/am.2013.44099]
Ding Y K, Zhu Y L, Feng J, Zhang P C and Cheng Z R. 2020. Interpretable spatio-temporal attention LSTM model for flood forecasting. Neurocomputing, 403: 348-359 [DOI: 10.1016/j.neucom.2020.04.110http://dx.doi.org/10.1016/j.neucom.2020.04.110]
Fan S S, Guo H P, Zhu J Y and Li W P. 2013. Application of linear regression model for land subsidence prediction in Beijing plain. The Chinese Journal of Geological Hazard and Control, 24(1): 70-74
范珊珊, 郭海朋, 朱菊艳, 李文鹏. 2013. 线性回归模型在北京平原地面沉降预测中的应用. 中国地质灾害与防治学报, 24(1): 70-74 [DOI: 10.16031/j.cnki.issn.1003-8035.2013.01.016http://dx.doi.org/10.16031/j.cnki.issn.1003-8035.2013.01.016]
Ferretti A, Prati C and Rocca F. 2000. Nonlinear subsidence rate estimation using permanent scatterers in differential SAR interferometry. IEEE Transactions on Geoscience and Remote Sensing, 38(5): 2202-2212 [DOI: 10.1109/36.868878http://dx.doi.org/10.1109/36.868878]
Greff K, Srivastava R K, Koutník J, Steunebrink B R and Schmidhuber J. 2017. LSTM: a search space odyssey. IEEE Transactions on Neural Networks and Learning Systems, 28(10): 2222-2232 [DOI: 10.1109/TNNLS.2016.2582924http://dx.doi.org/10.1109/TNNLS.2016.2582924]
Gu L Q, Wu Y J and Peng J H. 2020. An Attention-based GRU model for stock predicting. Systems Engineering, 38(5): 134-140
谷丽琼, 吴运杰, 逄金辉. 2020. 基于Attention机制的GRU股票预测模型. 系统工程, 38(5): 134-140
Guo L, Gong H L, Zhu F, Zhu L, Zhang Z X, Zhou C F, Gao M L and Sun Y K. 2019. Analysis of the spatiotemporal variation in land subsidence on the Beijing Plain, China. Remote Sensing, 11(10): 1170 [DOI: 10.3390/rs11101170http://dx.doi.org/10.3390/rs11101170]
Guo X M, Gong H L, Zhu F, Guo L and Shen Y Y. 2013. Prediction of land subsidence using the GM (1, 1) model based on a matrix: a case study of the Beijing plain. Hydrogeology and Engineering Geology, 40(6): 101-105, 116
郭小萌, 宫辉力, 朱锋, 郭琳, 沈媛媛. 2013. 基于矩阵的GM(1,1)模型预测地面沉降——以北京市平原区为例. 水文地质工程地质, 40(6): 101-105, 116 [DOI: 10.16030/j.cnki.issn.1000-3665.2013.06.021http://dx.doi.org/10.16030/j.cnki.issn.1000-3665.2013.06.021]
Hochreiter S and Schmidhuber J. 1997. Long short-term memory. Neural Computation, 9(8): 1735-1780 [DOI: 10.1162/neco.1997.9.8.1735http://dx.doi.org/10.1162/neco.1997.9.8.1735]
Jia S M, Tian F and Qi G. 2019. Urban “chronic disease”: the origin and comprehensive control countermeasures of land subsidence. City and Disaster Reduction, (3): 22-27
贾三满, 田芳, 齐干. 2019. 城市“慢性病”——地面沉降成因及综合防控对策. 城市与减灾, (3): 22-27 [DOI: 10.3969/j.issn.1671-0495.2019.03.007http://dx.doi.org/10.3969/j.issn.1671-0495.2019.03.007]
Jiang Y, Tian F, Luo Y, Wang R and Yang Y. 2015. Research on the relationship between groundwater level and layered subsidence in typical regions of Beijing. South-to-North Water Transfers and Water Science and Technology, 13(1): 95-99
姜媛, 田芳, 罗勇, 王荣, 杨艳. 2015. 北京典型地区分层地面沉降与地下水位变化关系. 南水北调与水利科技, 13(1): 95-99 [DOI: 10.13476/j.cnki.nsbdqk.2015.01.022http://dx.doi.org/10.13476/j.cnki.nsbdqk.2015.01.022]
Kingma D P and Ba J. 2014. Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980
Lei K C, Luo Y, Chen B B, Guo G X and Zhou Y. 2016. Distribution characteristics and influence factors of land subsidence in Beijing area. Geology in China, 43(6): 2216-2228
雷坤超, 罗勇, 陈蓓蓓, 郭高轩, 周毅. 2016. 北京平原区地面沉降分布特征及影响因素. 中国地质, 43(6): 2216-2228 [DOI: 10.12029/gc20160628http://dx.doi.org/10.12029/gc20160628]
Li H J, Zhu L, Dai Z X, Gong H L, Guo T, Guo G X, Wang J B and Teatini P. 2021. Spatiotemporal modeling of land subsidence using a geographically weighted deep learning method based on PS-InSAR. Science of the Total Environment, 799: 149244 [DOI: 10.1016/j.scitotenv.2021.149244http://dx.doi.org/10.1016/j.scitotenv.2021.149244]
Li H J, Zhu L, Gong H L, Sun H R and Yu J. 2020. Land subsidence modelling using a long short-term memory algorithm based on time-series datasets. Proceedings of IAHS, 382: 505-510 [DOI: 10.5194/piahs-382-505-2020http://dx.doi.org/10.5194/piahs-382-505-2020]
Li L B, Gong X N, Gan X L, Cheng K and Hou Y M. 2020. Prediction of maximum ground settlement induced by shield tunneling based on recurrent neural network. China Civil Engineering Journal, 53(S1): 13-19
李洛宾, 龚晓南, 甘晓露, 程康, 侯永茂. 2020. 基于循环神经网络的盾构隧道引发地面最大沉降预测. 土木工程学报, 53(S1): 13-19 [DOI: 10.15951/j.tmgcxb.2020.s1.003http://dx.doi.org/10.15951/j.tmgcxb.2020.s1.003]
Liang Y X, Ke S Y, Zhang J B, Yi X W and Zheng Y. 2018. GeoMAN: multi-level attention networks for geo-sensory time series prediction//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. Stockholm: IJCAI.org: 3428-3434 [DOI: 10.24963/ijcai.2018/476http://dx.doi.org/10.24963/ijcai.2018/476]
Lin Y Z. 2000. The grey forecasting method used in ground surface subsidence measurement. Journal of Shandong University of Science and Technology (Natural Science), 19(3): 108-110
林跃忠. 2000. 地面沉降量的灰色预测方法. 山东科技大学学报(自然科学版), 19(3): 108-110 [DOI: 10.16452/j.cnki.sdkjzk.2000.03.033http://dx.doi.org/10.16452/j.cnki.sdkjzk.2000.03.033]
Lin Z F, Cheng L L and Huang G H. 2020. Electricity consumption prediction based on LSTM with attention mechanism. IEEJ Transactions on Electrical and Electronic Engineering, 15(4): 556-562 [DOI: 10.1002/tee.23088http://dx.doi.org/10.1002/tee.23088]
Liu D R, Lee S J, Huang Y and Chiu C J. 2020. Air pollution forecasting based on attention-based LSTM neural network and ensemble learning. Expert Systems, 37(3): e12511 [DOI: 10.1111/exsy.12511http://dx.doi.org/10.1111/exsy.12511]
Liu Q H, Zhang Y H, Deng M, Wu H A, Kang Y H and Wei J J. 2021. Time series prediction method of large-scale surface subsidence based on deep learning. Acta Geodaetica et Cartographica Sinica, 50(3): 396-404
刘青豪, 张永红, 邓敏, 吴宏安, 康永辉, 魏钜杰. 2021. 大范围地表沉降时序深度学习预测法. 测绘学报, 50(3): 396-404
Luo Z J, Zhang X and Tian X W. 2018. Prediction and early warning of Cangzhou land subsidence disaster. Journal of Engineering Geology, 26(2): 365-373
骆祖江, 张鑫, 田小伟. 2018. 沧州市地面沉降灾害预测预警. 工程地质学报, 26(2): 365-373 [DOI: 10.13544/j.cnki.jeg.2017-097http://dx.doi.org/10.13544/j.cnki.jeg.2017-097]
Lyu C Z and An D D. 2021. Application of grey prediction model on land subsidence. Geomatics and Spatial Information Technology, 44(3): 73-75
吕传振, 安动动. 2021. 灰色预测模型在地面沉降中的应用. 测绘与空间地理信息, 44(3): 73-75 [DOI: 10.3969/j.issn.1672-5867.2021.03.019http://dx.doi.org/10.3969/j.issn.1672-5867.2021.03.019]
Lyu M Y, Ke Y H, Guo L, Li X J, Zhu L, Gong H L and Constantinos C. 2020. Change in regional land subsidence in Beijing after south-to-north water diversion project observed using satellite radar interferometry. GIScience and Remote Sensing, 57(1): 1450-150 [DOI: 10.1080/15481603.2019.1676973http://dx.doi.org/10.1080/15481603.2019.1676973]
Mnih V, Heess N, Graves A and Kavukcuoglu K. 2014. Recurrent models of visual attention//Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal: MIT Press: 2204-2212
Ng A H M, Ge L L, Li X J and Zhang K. 2012. Monitoring ground deformation in Beijing, China with persistent scatterer SAR interferometry. Journal of Geodesy, 86(6): 375-392 [DOI: 10.1007/s00190-011-0525-4http://dx.doi.org/10.1007/s00190-011-0525-4]
Prechelt L. 1998. Automatic early stopping using cross validation: quantifying the criteria. Neural Networks, 11(4): 761-767 [DOI: 10.1016/S0893-6080(98)00010-0http://dx.doi.org/10.1016/S0893-6080(98)00010-0]
Rogers J D and Chung J W. 2016. Applying Terzaghi's method of slope characterization to the recognition of Holocene land slippage. Geomorphology, 265: 24-44 [DOI: 10.1016/j.geomorph.2016.04.020http://dx.doi.org/10.1016/j.geomorph.2016.04.020]
Soltau H, Liao H and Sak H. 2016. Neural speech recognizer: acoustic-to-word LSTM model for large vocabulary speech recognition//Proceedings of the 18th Annual Conference of the International Speech Communication Association. Stockholm: ISCA: 3707-3711 [DOI: 10.21437/Interspeech.2017-1566http://dx.doi.org/10.21437/Interspeech.2017-1566]
Tan Y, Niu X F and Wang M C. 2016. Application of radial basis function neural networks in settlement predictive model. Science of Surveying and Mapping, 41(4): 33-36
谭洋, 牛雪峰, 王明常. 2016. 径向基神经网络在沉降预测中的应用. 测绘科学, 41(4): 33-36 [DOI: 10.16251/j.cnki.1009-2307.2016.04.008http://dx.doi.org/10.16251/j.cnki.1009-2307.2016.04.008]
Tsotsos J K, Culhane S M, Wai W Y K, Lai Y Z, Davis N and Nuflo F. 1995. Modeling visual attention via selective tuning. Artificial Intelligence, 78(1/2): 507-545 [DOI: 10.1016/0004-3702(95)00025-9http://dx.doi.org/10.1016/0004-3702(95)00025-9]
Vinyals O, Toshev A, Bengio S and Erhan D. 2015. Show and tell: a neural image caption generator//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston: IEEE [DOI: 10.1109/CVPR.2015.7298935http://dx.doi.org/10.1109/CVPR.2015.7298935]
Wang Y Y, Guo Y H, Hu S Q, Li Y, Wang J Z, Liu X S and Wang L. 2019. Ground deformation analysis using InSAR and backpropagation prediction with influencing factors in Erhai Region, China. Sustainability, 11(10): 2853 [DOI: 10.3390/su11102853http://dx.doi.org/10.3390/su11102853]
Wang Z Z and Qian W M. 2006. Application on land subsidence forecast by RBF network. Ground Water, 28(2): 84-87
王忠忠, 钱为民. 2006. 径向基神经网络在地面沉降预测中的应用. 地下水, 28(2): 84-87 [DOI: 10.3969/j.issn.1004-1184.2006.02.033http://dx.doi.org/10.3969/j.issn.1004-1184.2006.02.033]
Wu J C and Lu L. 2011.Uncertainty analysis for groundwater modeling. Journal of Nanjing University (Natural Sciences), 47(3): 227-234
吴吉春, 陆乐. 2011. 地下水模拟不确定性分析. 南京大学学报(自然科学版), 47(3): 227-234 [DOI: 10.13232/j.cnki.jnju.2011.03.009http://dx.doi.org/10.13232/j.cnki.jnju.2011.03.009]
Yan H L and Ma D H. 2020. Application of Time series-Markov composite Model in the deformation monitoring of building settlement. Journal of Qinghai University, 38(5): 86-91
闫宏亮, 马得花. 2020. 时间序列—马尔科夫组合模型在建筑物沉降变形监测中的应用. 青海大学学报, 38(5): 86-91 [DOI: 10.13901/j.cnki.qhwxxbzk.2020.05.013http://dx.doi.org/10.13901/j.cnki.qhwxxbzk.2020.05.013]
Yang Y, Zheng F D, Liu L C, Wang S F and Wang R. 2013. Study on the correlation between groundwater level and ground subsidence in Beijing plain areas. Geotechnical Investigation and Surveying, 41(8): 44-48
杨勇, 郑凡东, 刘立才, 王素芬, 王荣. 2013. 北京平原区地下水水位与地面沉降关系研究. 工程勘察, 41(8): 44-48
Yue Z H, Shen T, Mao X and Ma W J. 2020. Study on prediction method of land subsidence based on recurrent neural network. Science of Surveying and Mapping, 45(12): 145-152
岳振华, 沈涛, 毛曦, 马维军. 2020. 循环神经网络的地面沉降预测方法. 测绘科学, 45(12): 145-152 [DOI: 10.16251/j.cnki.1009-2307.2020.12.022http://dx.doi.org/10.16251/j.cnki.1009-2307.2020.12.022]
Zhao F Y. 2016. Application of wavelet neural network in the monitoring of tunnel settlement. Science of Surveying and Mapping, 41(12): 283-287
赵凤阳. 2016. 小波神经网络在隧道施工沉降预测中的应用. 测绘科学, 41(12): 283-287 [DOI: 10.16251/j.cnki.1009-2307.2016.12.056http://dx.doi.org/10.16251/j.cnki.1009-2307.2016.12.056]
Zheng X X, Wu Q, Hou Y S and Ying Y F. 2002. Some frontier problems on land subsidence research. Acta Geoscientia Sinica, 23(3): 279-282
郑铣鑫, 武强, 侯艳声, 应玉飞. 2002. 关于城市地面沉降研究的几个前沿问题. 地球学报, 23(3): 279-282 [DOI: 10.3321/j.issn:1006-3021.2002.03.017http://dx.doi.org/10.3321/j.issn:1006-3021.2002.03.017]
Zhou C D, Gong H L, Zhang Y Q, Warner T A and Wang C. 2018. Spatiotemporal evolution of land subsidence in the Beijing Plain 2003—2015 using persistent scatterer interferometry (PSI) with multi-source SAR data. Remote Sensing, 10(4): 552 [DOI: 10.3390/rs10040552http://dx.doi.org/10.3390/rs10040552]
Zhou C F, Gong H L, Chen B B, Li X J, Li J W, Wang X, Gao M L, Si Y, Guo L, Shi M and Duan G Y. 2019. Quantifying the contribution of multiple factors to land subsidence in the Beijing Plain, China with machine learning technology. Geomorphology, 335: 48-61[DOI: 10.1016/j.geomorph.2019.03.017http://dx.doi.org/10.1016/j.geomorph.2019.03.017]
Zhou F D, Zhao C S and Gao W D. 2011. Application of BP neural network model to ground subsidence of mining water area. Science of Surveying and Mapping, 36(6): 233-234, 240
周复旦, 赵长胜, 高卫东. 2011. BP神经网络模型在采水地面沉降中的应用研究. 测绘科学, 36(6): 233-234, 240 [DOI: 10.16251/j.cnki.1009-2307.2011.06.025http://dx.doi.org/10.16251/j.cnki.1009-2307.2011.06.025]
Zhou Y, Luo Y, Guo G X, Luo Y, Lei K C and Wang R. 2016. A study of the characteristics of land subsidence and the main control factors in the alluvial plain: a case study of Beijing plain. Geological Bulletin of China, 35(12): 2100-2110
周毅, 罗郧, 郭高轩, 罗勇, 雷坤超, 王荣. 2016. 冲洪积平原地面沉降特征及主控因素——以北京平原为例. 地质通报, 35(12): 2100-2110 [DOI: 10.3969/j.issn.1671-2552.2016.12.018http://dx.doi.org/10.3969/j.issn.1671-2552.2016.12.018]
Zhu L, Gong H L, Chen Y, Wang S F, Ke Y H, Guo G X, Li X J, Chen B B, Wang H G and Teatini P. 2020. Effects of Water Diversion Project on groundwater system and land subsidence in Beijing, China. Engineering Geology, 276: 105763 [DOI: 10.1016/j.enggeo.2020.105763http://dx.doi.org/10.1016/j.enggeo.2020.105763]
Zhu L, Gong H L, Li X J, Li Y Y, SU X S and Guo G X. 2013. Comprehensive analysis and artificial intelligent simulation of land subsidence of Beijing, China. Chinese Geographical Science, 23(2): 237-248 [DOI: 10.1007/s11769-013-0589-6http://dx.doi.org/10.1007/s11769-013-0589-6]
Zhu L, Gong H L, Li X J, Wang R, Chen B B, Dai Z X and Teatini P. 2015. Land subsidence due to groundwater withdrawal in the northern Beijing plain, China. Engineering Geology, 193: 243-255 [DOI: 10.1016/j.enggeo.2015.04.020http://dx.doi.org/10.1016/j.enggeo.2015.04.020]
Zuo J J, Gong H L, Chen B B, Liu K S, Zhou C F and Ke Y H. 2019. Time-series evolution patterns of land subsidence in the Eastern Beijing Plain, China. Remote Sensing, 11(5): 539 [DOI: 10.3390/rs11050539http://dx.doi.org/10.3390/rs11050539]
文章被引用时，请邮件提醒。
提交
相关作者
暂无数据
相关机构
中国科学院空天信息创新研究院
北京师范大学 遥感科学国家重点实验室
北京师范大学 地理科学学部 北京市陆表遥感数据产品工程技术研究中心
北京师范大学 地理科学学部 遥感科学与工程研究院
青海师范大学 高原科学与可持续发展研究院
选择翻译语言
- 地址：北京市海淀区北四环西路19号 《遥感学报》编辑部 邮编：100190
- 联系电话：010-58887052 Email：nrsb@aircas.ac.cn
- 技术支持由北京北大方正电子有限公司提供 京ICP备20021838号-9
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
0
回到顶部