基于光学卫星影像的同震形变提取技术及形变梯度的地学意义  

Coseismic Deformation Extraction Method and Geodynamic Significances of Displacement Gradients Based on Optical Imagery

作　　者：黄宇 刘小利[1,2] 莫昕宇 邓德贝尔 阮巧喆 贾治革 HUANG Yu;LIU Xiaoli;MO Xinyu;DENG Debei’er;RUAN Qiaozhe;JIA Zhige(Institute of Seismology,CEA,40 Hongshance Road,Wuhan 430071,China;Hubei Earthquake Agency,48 Hongshance Road,Wuhan 430071,China)

机构地区：[1]中国地震局地震研究所,武汉市430071 [2]湖北省地震局,武汉市430071

出　　处：《大地测量与地球动力学》2024年第5期485-490,共6页Journal of Geodesy and Geodynamics

基　　金：中国地震局地震研究所和应急管理部国家自然灾害防治研究院基本科研业务费(IS20226325);中国地震局地震科技星火计划(XH22003C);武汉引力与固体潮国家野外科学观测研究站开放基金(WHYW202201)。

摘　　要：介绍光学同震形变提取的关键技术、优化流程和主流软件包的差异性,并基于光学同震形变场推导具有地学意义的位移梯度、旋度、膨胀量、剪切应变等算子;以2021年青海玛多M W7.4地震为例,检验基于Sentinel-2光学影像的同震形变场提取优化流程以及算子的地学意义。结果表明,对亚像素相关性匹配结果的后处理可有效消除轨道误差、条带误差、场地和传感器因素导致的白噪声和加性噪声,突出形变细节,更加客观地描述同震形变的空间分布特征。This paper introduces the key technology,refined process,and differences in mainstream software packages for optical coseismic deformation extraction.Geoscientific operators such as displacement gradient,curl,dilatation,and shear strain are derived based on the optical coseismic deformation field.Taking the M W7.4 earthquake in Maduo,Qinghai province in 2021 as an example,we test the refined process of coseismic deformation extraction based on Sentinel-2 optical images.The results indicate post-processing of subpixel correlation matching results can effectively eliminate white noise and additive noise caused by orbit error,strip error,scenes and sensor factors,highlight deformation details,and more objectively describe the coseismic deformation spatial distribution.

关 键 词：同震形变 光学影像 位移梯度 SOBEL算子 2021年玛多地震 

分 类 号：P315[天文地球—地震学] P313[天文地球—固体地球物理学]