田亚军^1,2,,
高静怀^1,2,,,
王大兴^3,4,
陈道雨^1,2
1. 西安交通大学信息与通信工程学院, 西安 710049
2. 海洋石油勘探国家工程实验室, 西安 710049
3. 中国石油长庆油田公司勘探开发研究院, 西安 710018
4. 低渗透油气田勘探开发国家工程实验室, 西安 710018

基金项目: 国家重点研发计划重点项目(2018YFC0603501，2020YFA0713403，2020YFA0713400)资助


详细信息

作者简介: 田亚军, 男, 1992年生, 西安交通大学信息与通信工程学院在读博士研究生, 主要从事宽方位地震数据处理及地震储层预测等方面的研究工作.E-mail: xj_tyj@stu.xjtu.edu.cn

通讯作者: 高静怀, 男, 1960年生, 教授, 博士生导师, 1997年于西安交通大学获博士学位, 主要从事复杂介质中地震波传播及地震资料处理的理论与方法等研究.E-mail: jhgao@mail.xjtu.edu.cn

中图分类号: P631

收稿日期:2020-05-05
修回日期:2021-03-12
上线日期:2021-08-10

Removing strong seismic reflection based on the deep neural network

TIAN YaJun^1,2,,
GAO JingHuai^1,2,,,
WANG DaXing^3,4,
CHEN DaoYu^1,2
1. School of Information and Communications Engineering, Xi'an Jiaotong University, Xi'an 710049, China
2. National Engineering Laboratory for Offshore Oil Exploration, Xi'an 710049, China
3. Exploration and Development Research Institute of PetroChina Changqing Oilfield Company, Xi'an 710018, China
4. National Engineering Laboratory for Exploration and Development of Low-Permeability Oil and Gas Fields, Xi'an 710018, China


More Information

Corresponding author: GAO JingHuai,E-mail:jhgao@mail.xjtu.edu.cn

MSC: P631

--> Received Date: 05 May 2020
Revised Date: 12 March 2021
Available Online: 10 August 2021


摘要
摘要:在储层预测工作中，储层弱反射信号淹没在强反射信号之中的情况非常常见，这不利于精确识别和描述储层结构.本文提出了一种基于深度神经网络的强反射剥离方法，用于辅助储层弱反射信号的检测工作.该方法在卷积模型的框架下将强反射预测问题分解为地震子波预测与强反射预测两个子优化问题，并采用AIDNN与U-Net两个深度神经网络分别求解.通过训练直接得到地震数据与强反射之间的映射关系，避免了经验性调参过程，计算速度快，适用于海量地震数据处理.模型数据和实际资料试算结果表明，本文方法能够预测并剥离地震数据中的强反射且保真保幅性好；在该方法的基础上进行的储层砂体展布预测工作取得了良好效果.
关键词: 深度学习/
地震强反射/
储层预测

Abstract:In reservoir prediction, it is often encountered that the weak reflection signal is submerged in the strong reflection, which is disadvantageous to accurately identify and describe reservoir structure. In this study, we propose a method to remove the strong seismic reflection using the deep neural networks to help detect weak reflection signals of reservoirs. In the framework of the convolution model, the proposed method first decomposes the strong reflection prediction problem into two optimization sub-problems: seismic wavelet prediction and strong reflection prediction, which are solved by AIDNN and U-Net, respectively. The mapping relationship between seismic data and strong reflection can be established directly through training, which avoids the artificial empirical parameter adjustment, and is fast in the calculation and suitable for massive seismic data processing. Tests on synthetic and real data show that the proposed method can predict and remove strong seismic reflection with good amplitude preservation and fidelity. Base on this approach we predict the distribution of sand bodies in reservoirs and achieve good results.
Key words:Deep learning/
Strong seismic reflection/
Reservoir prediction



PDF全文下载地址:

http://www.geophy.cn/data/article/export-pdf?id=9edea6e1-811b-4642-b5c2-f04cd852dd71