基于PSInSAR的水溶矿区沉降预测  

Subsidence Prediction of Water-soluble Mining Area Based on PSInSAR

作　　者：刘佳斌 徐卓揆[1,2] 何伟 LIU Jiabin;XU Zhuokui;HE Wei

机构地区：[1]长沙理工大学交通运输工程学院,湖南长沙410114 [2]长沙理工大学公路地质灾变预警空间信息技术湖南省工程实验室,湖南长沙410114

出　　处：《地理空间信息》2020年第7期103-105,130,I0007,共5页Geospatial Information

基　　金：湖南省教育厅科研资助项目(13B129);长沙理工大学公路地质灾变预警空间信息技术湖南省工程实验室开放基金资助项目(kfj180602)。

摘　　要：针对水溶矿区地表沉降监测与预测中传统大地测量监测手段所获结果空间分辨率较低的问题,利用PSInSAR进行了水溶矿区地表沉降监测;基于PSInSAR监测结果,分别采用GM(1,1)灰色模型、BP神经网络模型和多项式拟合模型进行沉降预测;以均方误差和相关系数为精度的衡量标准,将预测结果与实际结果进行对比,分析了3种模型的预测精度。结果表明,针对某水溶性矿山,基于PSInSAR数据构建的GM(1,1)灰色模型预测精度最高,可通过该方法为矿区的开采提供良好的高空间分辨率的短期预测。In view of the low spatial resolution of the results obtained by traditional geodetic surveying method in the surface subsidence monitoring and prediction in water-soluble mining area,we used PSInSAR to monitor surface subsidence in water-soluble mining area at first.And then,we predicted the subsidence based on GM(1,1)grey model,BP neural network model and polynomial fitting model.Finally,taking the mean square error and correlation coefficient as the criterias for accuracy,we compared the predicted results with the actual results,and analyzed the prediction accuracy of the three models.The results show that the GM(1,1)grey model constructed with PSInSAR data in a given water-soluble mine has the highest prediction accuracy.Using this method,we can provide a good short-term prediction with high spatial resolution for the mining of mining area.

关 键 词：PSINSAR 沉降预测 GM(1 1)灰色模型 BP神经网络模型 多项式拟合模型 

分 类 号：P258[天文地球—测绘科学与技术]