arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.02750physics.geo-ph
收藏

基于空间上下文的多数据集地震反演的联合学习方法

Joint Learning for Spatial Context-based Seismic Inversion of Multiple Datasets for Improved Generalizability and Robustness

Ahmad Mustafa, Motaz Alfarraj, Ghassan AlRegib

备注：
Accepted to Geophysics
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

地震反演在地震资料的精细地层解释中起着非常有用的作用。地震反演能够估计整个地震剖面上的岩石性质。传统的和基于机器学习的地震反演工作流限于独立于其他道来反演每个地震道以估计阻抗剖面，从而导致在地震资料中存在噪声和大的地质变化的情况下的横向不连续性。此外，如果模型在少量井上训练，则基于机器学习的方法会遇到过拟合的问题。我们提出了一个双管齐下的战略来克服这些问题。我们提出了一个时间卷积网络模型地震道时间。我们进一步注入空间背景为每个轨迹到其估计的阻抗分布。为了解决有限标记数据的问题，我们还提出了一种联合学习方案，即多个数据集同时用于训练，彼此共享有益的信息。这导致了所有数据集上的泛化性能的提高。我们提出了一个使用开源SEAM和Marmousi 2数据集进行声阻抗反演的案例研究。我们的评估表明，我们提出的方法是能够执行强大的和横向一致的估计阻抗存在的噪音地震资料和有限的标签。我们将我们的方法与文献中其他基于学习的地震反演方法进行比较和对比。在SEAM上，我们能够获得0.0966的平均MSE，是所有其他方法中最低的。

英文摘要：

Seismic inversion plays a very useful role in detailed stratigraphic interpretation of seismic data. Seismic inversion enables estimation of rock properties over the complete seismic section. Traditional and machine learning-based seismic inversion workflows are limited to inverting each seismic trace independently of other traces to estimate impedance profiles, leading to lateral discontinuities in the presence of noise and large geological variations in the seismic data. In addition, machine learning-based approaches suffer the problem of overfitting if there is a small number of wells on which the model is trained. We propose a two-pronged strategy to overcome these problems. We present a Temporal Convolutional Network that models seismic traces temporally. We further inject spatial context for each trace into its estimations of the impedance profile. To counter the problem of limited labeled data, we also present a joint learning scheme whereby multiple datasets are simultaneously used for training, sharing beneficial information among each other. This results in the improvement in generalization performance on all datasets. We present a case study of acoustic impedance inversion using the open source SEAM and Marmousi 2 datasets. Our evaluations show that our proposed approach is able to perform robust and laterally consistent estimations of impedance in the presence of noisy seismic data and limited labels. We compare and contrast our approach to other learning-based seismic inversion methodologies in the literature. On SEAM, we are able to obtain an average MSE of 0.0966, the lowest among all other methodologies.

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。

↑