多因子约束的自适应四叉树InSAR数据降采样方法  

Adaptive quadtree downsampling method for InSAR data based on multifactor constraints

作　　者：莫昕宇 贾治革[1,2] 黄宇 邓德贝尔 刘俊涛 阮巧喆 刘小利 MO Xinyu;JIA Zhige;HUANG Yu;DENG Debeier;LIU Juntao;RUAN Qiaozhe;LIU Xiaoli(Institute of Seismology,CEA,Wuhan 430071,Hubei,China;Key Laboratory of Earthquake Geodesy,CEA,Wuhan 430071,Hubei,China)

机构地区：[1]中国地震局地震研究所,湖北武汉430071 [2]中国地震局地震大地测量重点实验室,湖北武汉430071

出　　处：《地震工程学报》2025年第3期680-689,708,共11页China Earthquake Engineering Journal

基　　金：中国地震局地震研究所所长基金(IS20226325);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：InSAR形变场的数据压缩有助于提高同震滑动分布模型和发震构造参数的反演效率,但如何在剔除噪声和冗余信息与保留更多全局性和局部性关键形变特征之间取得平衡,对传统压缩方法是一个挑战。为此,文章提出一种由方差、形变梯度和相干性共同约束的多因子四叉树降采样方法,用于InSAR同震形变场的降采样处理,利用显著性和相干系数为因子自适应赋权,选取3个复杂性不同的强震事件对方法的有效性和鲁棒性进行验证。相较于已有方法,多因子四叉树降采样法在3个震例中均保持较平衡的采样率和较低的均方根误差,且采样结果在三维滑动分布反演中能更好地揭示断层的滑动分布,降低模型的残差。结果表明,该方法能保持较低的采样率和更好的鲁棒性,可有效剔除低相干性点,对关键性形变细节保留度较高,且对形变的线性分布约束更强。Data compression of interferometric synthetic aperture radar(InSAR)deformation fields significantly enhances the inversion efficiency of coseismic slip distribution models and seismogenic structure parameters.However,traditional compression methods face challenges in balancing the removal of noise/redundant information and the preservation of global/local key deformation features.This study proposes a multifactor quadtree downsampling method constrained by variance,deformation gradient,and coherence for the downsampling processing of the InSAR coseismic deformation field.Significance and coherence coefficients were used to adaptively weigh various factors,and three strong earthquake events with different complexities were selected to verify the effectiveness and robustness of the method.Compared with existing methods,the multifactor quadtree downsampling method maintained balanced sampling rates and lower root mean square error across all cases,and the sampling results improved the resolution of fault slip distributions in three-dimensional slip inversions while reducing model residuals.The results suggest that the proposed method demonstrates low sampling rates,robust performance,effective elimination of low-coherence points,high retention of critical deformation details,and enhanced constraints on the linear distribution of deformation.

关 键 词：INSAR 同震形变 四叉树降采样 形变梯度 相干性 

分 类 号：P319.56[天文地球—固体地球物理学]