摘要
城市轨道交通建设和运营造成的地铁沿线及周边区域的地表沉降,给地铁的安全运营带来极大的隐患,甚至造成严重的经济损失和不良的社会影响.本文以西安市地铁沿线地面形变现象为研究对象,利用覆盖西安市2017—2021年的44景Sentinel-1A影像数据,采用SBAS-InSAR方法获取地铁网络沿线的地表形变信息,并基于SVR模型和LSTM模型对典型地铁站点地面沉降进行预测分析.研究发现:(1)西安市地铁沿线呈现不同程度的地表形变现象,抬升区域主要集中在鱼化寨地区、电子城地区、西安城墙的南部,抬升速率最大为25 mm/a;(2)2号线的南部、5号线的东西两段以及9号线的东段是沉降发生的主要路段,且5号线沿线整体不均匀沉降现象较为严重,最大沉降速率为32 mm/a,最大累积沉降量达130 mm;(3)通过不同预测模型实验对比,发现LSTM模型精度较高,预测结果显示2、5、9号线典型沉降区域未来四个月以每月约2.3 mm的最大速率继续沉降,需对典型沉降段进行持续监测.
The construction and operation of urban rail transit has caused surface subsidence along and around the subway,and the occurrence of surface subsidence will cause hidden dangers to people's lives and properties.In order to understand the phenomenon of land subsidence along the subway in Xi'an,this paper uses the SBAS-InSAR method to obtain the surface deformation information along the subway network based on the Sentinel-1A image data of 44 scenes covering Xi'an from 2017 to 2021,and based on the SVR model and LSTM model to analyze Prediction and comparative analysis of ground subsidence in typical subway stations.The research found that:(1)There are different degrees of subsidence along the Xi'an subway line,and the uplift areas are mainly concentrated in the Yuhuazhai area,the Electronic City area,and the southern part of the Xi'an city wall,with an maximum uplift rate of 25 mm/a;(2)The southern part of Line 2,the east and west sections of Line 5 and the east section of Line 9 are the main road sections where settlement occurs,and the overall uneven settlement along Line 5 is relatively serious,with a maximum settlementrateof32 mm/a and a maximum cumulative settlement of 130 mm;(3)Through the comparison of model experiments,it is found that the accuracy of the LSTM model is relatively high.The prediction results show that the area around Matengkong Station-Qinglongsi Station of Line 5 will continue to subside at a rate of about 2.3 mm per month in the next four months.
作者
卫达宁
王世杰
WEI DaNing;WANG ShiJie(Faculty of Geomatics,Lanzhou Jiaotong University,Lanzhou 730070,China;Nation-Local Joint Engineering Research Center of Technologies and Applications for National Geographic State Monitoring,Lanzhou 730070,China;Gansu Provincial Engineering Laboratory for National Geographic State Monitoring,Lanzhou 730070,China;Academician Expert Workstation of Gansu Dayu Jiuzhou Space Information Technology Co.,Ltd.,Lanzhou 730050,China)
出处
《地球物理学进展》
CSCD
北大核心
2024年第2期498-509,共12页
Progress in Geophysics
基金
国家自然科学基金项目(41861061)
兰州交通大学天佑创新团队(TY202001)联合资助。