基于3D U-Net++卷积神经网络的断层识别方法及应用  

Fault recognition method and application based on 3D U-Net++convolution neural network

作　　者：李卿武 王兴建 张永恒[1] 文雪梅 陈阳 王崇名 廖万平 LI Qingwu;WANG Xingjian;ZHANG Yongheng;WEN Xuemei;CHEN Yang;WANG Chongming;LIAO Wanping(School of Geophysics,Chengdu University of Technology,Chengdu 610059,China;State Key Laboratory of Oil and Gas Reservoir Geology and Development Engineering,Chengdu University of Technology,Chengdu 610059,China)

机构地区：[1]成都理工大学地球物理学院,成都610059 [2]成都理工大学油气藏地质及开发工程国家重点实验室,成都610059

出　　处：《物探化探计算技术》2024年第3期284-291,共8页Computing Techniques For Geophysical and Geochemical Exploration

摘　　要：断层解释是地震资料解释的基础与关键,准确合理的断层识别对油气开采有着至关重要的作用。随着油田对断层解释精度需求的日益提高,单纯通过基于人工的如相干体、曲率等属性的传统断层解释方法,其精度已无法满足要求。笔者在U-Net卷积神经网络模型的基础上进行改进,得出了一种自动断层识别方法,能够从任意三维地震图像中自动提取断层。文中该模型在足量样本集训练下,对两区块的实际地震数据进行自动断层识别,将识别结果进行分析对比。实验结果表明,该模型能够对任意三维地震数据进行自动断层识别,基于3D U-Net++网络模型的断层识别结果相比于传统U-Net网络识别结果准确性有明显提高,对潜山内部的小断层识别也表现出良好的效果,明显提高了常规、复杂断层识别的工作效率。Fault interpretation is the basis and key to seismic data interpretation,and accurate and reasonable fault identification plays a vital role in oil and gas exploitation.With the increasing demand of oil fields for fault interpretation accuracy,the accuracy of traditional fault interpretation methods based solely on artificial attributes such as coherence,curvature,etc.,cannot meet the requirements.Based on the U-Net convolution neural network model,this paper proposes an automatic fault recognition method,which can automatically extract faults from any 3D seismic image.In this paper,the model carries out automatic fault identification on the actual seismic data of two blocks under the training of sufficient sample sets and analyzes and compares the identification results.The experimental results show that the model can automatically recognize faults from arbitrary 3D seismic data,and the fault recognition results based on the 3D U-Net++network model have significantly improved the accuracy of the recognition results compared with the traditional U-Net network.It also shows a good effect on the recognition of minor faults inside the buried hill and significantly improves the efficiency of conventional and complex fault recognition.

关 键 词：断层识别 三维地震数据 卷积神经网络 3D U-Net++ 

分 类 号：P631.4[天文地球—地质矿产勘探]