arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2409.07930physics.geo-phcs.AI
收藏

一种用于地震数据分离的卷积神经网络方法

A convolutional neural network approach to deblending seismic data

University of Oslo(奥斯陆大学);CGG(CGG公司);Lundin Norway AS(伦丁挪威公司)

Jing Sun, Sigmund Slang, Thomas Elboth, Thomas Larsen Greiner, Steven McDonald, Leiv-J Gelius

AI总结:

针对传统地震数据分离方法计算量大、步骤繁琐的问题,提出基于CNN的数据驱动分离方法,通过域变换优化噪声特征,在超2万野外数据样本训练后可近乎实时完成分离,效果媲美传统算法且具备鲁棒性与自适应性。

摘要:

出于经济和效率方面的考量,地震数据的混合采集正变得越来越普遍。传统地震数据分离方法通常计算量巨大,且一般包含多个处理步骤,此外参数设置也并非易事。基于机器学习的处理方法有望大幅缩短处理时间,并改变地震数据分离的实施方式。\n我们提出了一种数据驱动的基于深度学习的快速高效地震数据分离方法。首先将混合数据从共炮域排序到共通道域,将混合噪声的特征从相干同相轴转化为非相干分布。我们针对地震数据的特殊特性设计了一个卷积神经网络(CNN),其分离效果可与传统工业级地震分离算法的结果相媲美。为保证结果的真实性,混合过程通过数值方式完成,且仅使用野外地震数据,训练样本量超过20000个。在网络完成训练和验证后,地震数据分离可近乎实时完成。实验还表明,初始信噪比(SNR)是控制最终分离结果质量的主要因素。我们还验证了该网络的鲁棒性和自适应性:使用训练好的模型,首先对来自不同地质区域、延迟时间设置略有差异的新数据集进行分离,其次对数据上部存在混合噪声的炮集进行分离,均取得了良好效果。

英文摘要:

For economic and efficiency reasons, blended acquisition of seismic data is becoming more and more commonplace. Seismic deblending methods are always computationally demanding and normally consist of multiple processing steps. Besides, the parameter setting is not always trivial. Machine learning-based processing has the potential to significantly reduce processing time and to change the way seismic deblending is carried out. We present a data-driven deep learning-based method for fast and efficient seismic deblending. The blended data are sorted from the common source to the common channel domain to transform the character of the blending noise from coherent events to incoherent distributions. A convolutional neural network (CNN) is designed according to the special character of seismic data, and performs deblending with comparable results to those obtained with conventional industry deblending algorithms. To ensure authenticity, the blending was done numerically and only field seismic data were employed, including more than 20000 training examples. After training and validation of the network, seismic deblending can be performed in near real time. Experiments also show that the initial signal to noise ratio (SNR) is the major factor controlling the quality of the final deblended result. The network is also demonstrated to be robust and adaptive by using the trained model to firstly deblend a new data set from a different geological area with a slightly different delay time setting, and secondly deblend shots with blending noise in the top part of the data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑