利用双路卷积神经网络的速度自动拾取方法  

Automatic velocity picking using dual-path convolutional neural network

作　　者：赵亮[1,2] 孙小东 李振春[1,2] 秦宁[3] 王九拴[4] 杨静 ZHAO Liang;SUN Xiaodong;LI Zhenchun;QIN Ning;WANG Jiushuan;YANG Jing(State Key Laboratory of Deep Oil and Gas,China University of Petroleum(East China),Qingdao,Shandong 266580,China;China University of Petroleum(EastChina),Qingdao,Shandong 266580,China;Geophysical Research Institute,Shengli Oilfield Branch Co.,SINOPEC,Dongying,Shandong 257022,China;Data Processing Center,BGP Inc.,CNPC,Zhuozhou,Hebei 072751,China)

机构地区：[1]深层油气全国重点实验室(中国石油大学(华东)),山东青岛266580 [2]中国石油大学(华东)地球科学与技术学院,山东青岛266580 [3]中国石化胜利油田物探研究院,山东东营257022 [4]东方地球物理公司研究院处理中心,河北涿州072751

出　　处：《石油地球物理勘探》2024年第6期1206-1216,共11页Oil Geophysical Prospecting

基　　金：中央高校基本科研业务费专项“多模态神经网络速度场智能构建方法研究”(24CX02010A);中国石油大学(华东)深层油气全国重点实验室;山东省泰山产业领军人才课题(tscx202312059);山东省自然科学基金面上项目(ZR2020MD048);中石油BGP项目"盐穴储库复杂介质地震响应规律及表征方法"(2023DJ8307)联合资助。

摘　　要：人工拾取速度谱是地震资料常规处理中速度分析的主要手段,此方法既耗时、耗力,又限制了大规模三维地震资料处理的效率和准确性。为此,提出了一种利用双路卷积神经网络的速度谱自动拾取方法。首先,采用卷积神经网络结合注意力机制作为主网络,从速度谱数据中提取能量团的特征并实现速度的自动拾取;其次,训练主网络在输出时间—速度序列之前,通过特征融合和特征转换将速度与另一个卷积神经网络(辅网络)输入的未校正CMP道集的隐藏表征进行信息融合,重构成校正后的CMP道集;最后,通过辅网络模拟CMP道集动校正的过程,利用动校正优化速度拾取的精度。模型和实际资料测试结果表明,在加入辅助神经网络引入动校正信息后,文中方法比单一的卷积神经网络在速度拾取方面具有更高的精度。In conventional seismic data processing,velocity analysis relies heavily on manually picking the velocity spectrum.However,this method is time-consuming,labor-intensive,and restricts the efficiency and accuracy of large-scale 3D seismic data processing.To address this issue,this paper propose an automatic velo-city spectrum picking method using a dual-path convolutional neural network(DCNN).Firstly,this paper utilize a convolutional neural network combined with an attention mechanism as the main network,extract the features of energy clusters from velocity spectrum data,and realize the automatic picking of velocity.Secondly,this paper train a main neural network to integrate the information of velocity and the hidden representation of the uncorrected CMP gather input by another convolutional neural network(auxiliary network)through feature fusion and feature transformation before outputting the time-velocity sequence,reconstructing the corrected CMP gather.Finally,the process of CMP gather dynamic correction is simulated through the auxiliary nework,and the accuracy of speed picking is optimized using dynamic correction.Model and real data tests dem-onstrate that,after incorporating dynamic correction information through the auxiliary neural network,the proposed velocity spectrum picking method achieves a higher accuracy than a single CNN in velocity picking.

关 键 词：双路卷积神经网络 主神经网络 辅神经网络 CMP道集 优化拾取 

分 类 号：P631[天文地球—地质矿产勘探]