摘要
我国西部黄土高原地区土质疏松,沟壑纵横,开采损害特征明显,准确预计开采引起的地表移动和变形趋势有助于为矿区灾害提供预警信息。文中以陕西彬长矿区某工作面为例,利用2007年7月—2008年1月的5幅SAR影像对矿区地面进行监测,将合成孔径雷达干涉测量(InSAR)技术得到的监测成果作为训练样本,与网格搜索算法(GS)优化支持向量机回归(SVR)参数算法结合,对矿区的形变点进行沉降预计。结果表明:InSAR技术获取矿区的沉降量可以满足矿区地表沉陷监测预计,结合GS-SVR预计模型可以实现矿区形变点的沉陷预计,预测精度符合工程的应用需求。
In China,the western loess plateau region,soil loose and ravines crossbar have caused significantly mining damage characteristics.Accurately predicting the trend of surface movement and deformation caused by mining can provide the basis for mining management.This paper,taking one of the working face in Bin-Chang mining area in Shaanxi as an example,uses InSAR technology to monitor the surface of mining area and to achieve the deformation field in the line of sight after unwrapping.The grid search algorithm is used to optimize the SVR parameters,predicting the subsidence mining area.The result shows that the InSAR technology can provide the same accuracy result,which can be used for mining surface subsidence predicting.
作者
马飞
隋立春
姚顽强
汤伏全
MA Fei;SUI Lichun;YAO Wanqiang;TANG Fuquan(School of Geological Engineering and Geomatics,Chang＇ an University,Xi＇ an 710054,China;College of Geomatics,Xi＇ an University of Science and Technology,Xi＇ an 710054,China;National Administration of Surveying,Mapping and Geoinformation,Engineering research center of Geographic National Conditions Monitoring,Xi＇ an 710054,China)
出处
《测绘工程》
CSCD
2018年第7期10-14,共5页
Engineering of Surveying and Mapping
基金
国家自然科学基金资助项目(41372330
51674195)
关键词
矿区开采沉陷
沉陷预计
支持向量机回归
网格搜索
mining subsidence
subsidence prediction
support vector regression （SVR）
grid
