基于双通道掩码交互的地震初至拾取方法  

Seismic first break picking using dual-channel mask interaction

作　　者：张旭 张剑 石翠翠 邓飞[3] 凡正才 ZHANG Xu;ZHANG Jian;SHI CuiCui;DENG Fei;FAN ZhengCai(Sinopec Geophysical Corporation Shengli Branch,Dongying 257100,China;R&D Center of Science and Technology,Sinopec Geophysical Corporation,Nanjing 211112,China;College of Computer Science and Cyber Security,Chengdu University of Technology,Chengdu 610059,China)

机构地区：[1]中石化石油工程地球物理有限公司胜利分公司,东营257100 [2]中石化石油工程地球物理有限公司科技研发中心,南京211112 [3]成都理工大学计算机与网络安全学院,成都610059

出　　处：《地球物理学进展》2025年第1期131-142,共12页Progress in Geophysics

基　　金：中石化石油工程地球物理有限公司科研项目“可控震源地震采集工程设计软件研发与应用”(SGC-2023-09)资助.

摘　　要：现有基于图像语义分割网络的地震初至拾取方法通常采用两种标签标定与初至判定方式,一是将地震信号划分为初至前与初至后,通过掩码分割来拾取初至;二是将地震信号划分为初至时刻与非初至时刻,通过提取每道置信度最高点来实现初至拾取.前者由于掩码边缘模糊问题,存在局部区域连续性的初至错误拾取现象;后者因为正负样本比例悬殊,容易导致网络难以拟合,无法适用于初至波型复杂且尺寸较大的地震单炮中.基于此,提出一种双通道掩码交互的地震初至拾取方法,通过宽带状初至范围掩码来保证网络的初至特征识别能力,通过线状优选初至掩码来增强网络的初至精确拾取能力,有效避免现有方法的不足.理论实验表明,该方法具有较好的抗噪性,通过在低噪声水平数据中训练后可泛化至更高噪声水平数据中.将该方法应用于实测资料中时,较现有方法取得了更高初至拾取精度,拾取误差为0 ms的道数占比高达75.9%,分别较STUNet、SegNet和Res-Unet提升了7.1%、26.8%和15.6%,大幅提升了高质量地震初至拾取的效率.同时该方式采用轻量化网络模型,推理效率高,易于工程部署,具有实际应用价值.Deep learning applied to seismic First Break(FB)picking has been developed for many years,and numerous researchers have used Image Semantic Segmentation Networks(ISSNs)for multi-channel FB picking.The existing seismic FB picking method based on ISSNs usually adopts two label calibration and FB determination methods,one is to divide the seismic signal into pre-FB and post-FB,and pick up the FB through mask segmentation;the other is to divide the seismic signal into FB and non-FB,and pick up the FB by extracting the highest confidence point of each trace.The former suffers from FB false pickup with localized regional continuity due to the mask edge blurring problem;The latter,because of the large proportion of positive and negative samples,tends to make the network hard fitting and cannot be applied to data with complex FB waveforms and large size.Based on this,a dual-channel mask interaction seismic FBs picking method is proposed,which ensures the network's FBs feature recognition ability by banded FBs range mask,and enhances the network's FBs accurate picking ability by linear preferred FBs mask,which effectively avoids the shortcomings of the existing methods.Theoretical experiments show that the method has good noise resistance and can be generalized to higher noise level data by training in low noise level data.When the method is applied to the field data,it achieves higher FB picking accuracy than the existing methods,and the number of traces with picking error of 0 ms is as high as 75.9%,which is 7.1%,26.8%,and 15.6%higher than that of STUNet,SegNet,and Res-Unet,respectively,and greatly improves the efficiency of high-quality seismic FB picking.Meanwhile,the approach adopts a lightweight network model with high inference efficiency and easy engineering deployment,which has practical application value.

关 键 词：深度学习 初至拾取 图像语义分割 双通道掩码 轻量化 

分 类 号：P631[天文地球—地质矿产勘探]