[论文解读] Netherlands Dataset: A New Public Dataset for Machine Learning in Seismic Interpretation

Reinaldo Mozart Silva, Laís Baroni+4 more|arXiv (Cornell University)|Mar 26, 2019

Seismic Imaging and Inversion Techniques被引用 39

一句话总结

本文介绍了荷兰解释数据集用于地震ML，详细描述了9个地层界线和约19万张带标签的地震图像，源自公开的荷兰F3数据，并演示了数据集上两项DL任务（分类和语义分割）。

ABSTRACT

Machine learning and, more specifically, deep learning algorithms have seen remarkable growth in their popularity and usefulness in the last years. This is arguably due to three main factors: powerful computers, new techniques to train deeper networks and larger datasets. Although the first two are readily available in modern computers and ML libraries, the last one remains a challenge for many domains. It is a fact that big data is a reality in almost all fields nowadays, and geosciences are not an exception. However, to achieve the success of general-purpose applications such as ImageNet - for which there are +14 million labeled images for 1000 target classes - we not only need more data, we need more high-quality labeled data. When it comes to the Oil&Gas industry, confidentiality issues hamper even more the sharing of datasets. In this work, we present the Netherlands interpretation dataset, a contribution to the development of machine learning in seismic interpretation. The Netherlands F3 dataset acquisition was carried out in the North Sea, Netherlands offshore. The data is publicly available and contains pos-stack data, 8 horizons and well logs of 4 wells. For the purposes of our machine learning tasks, the original dataset was reinterpreted, generating 9 horizons separating different seismic facies intervals. The interpreted horizons were used to generate approximatelly 190,000 labeled images for inlines and crosslines. Finally, we present two deep learning applications in which the proposed dataset was employed and produced compelling results.

研究动机与目标

• 在地震解释中高质量标注数据集对深度学习成功的必要性进行动机说明。
• 介绍基于公开荷兰F3地震数据推导的 Netherlands interpretation dataset。
• 提供数据集特征，包括地层界线、图像，以及标签的生成方式。
• 演示两种深度学习应用（分类和语义分割）在该数据集上的应用。

提出的方法

• 基于 3D 荷兰 F3 地震数据重新定义基于地震相的 9 个地层界线。
• 通过在地震线相交生成约 190,000 张带标签的地震图像以产生带标签的区间。
• 通过将图像分割成 64x25 的图块并指派占优地层类别来创建分类图块；实现训练数据的平衡。
• 应用深度学习对岩层纹理进行分类，在测试集上达到 81.6% 的准确率。
• 应用迁移学习/分割方法来生成像素级（语义）标签，并在相关工作中报告 IoU 指标。

实验结果

研究问题

• RQ1 使用荷兰解释数据集，DL 模型是否能够从地震图块中以较高准确性分类岩层纹理？
• RQ2 基于该数据集的地震图像分割在基于地层标签的任务上能否达到较高的平均 IoU？
• RQ3 分块策略和类别平衡如何影响地震解释任务的 DL 性能？

主要发现

• 在提供的测试集上的分类达到了 81.6% 的准确率（论文中给出混淆矩阵）。
• 该数据集使相关工作中的语义分割性能达到较高水平，在不同设置下报道的平均 IoU 值超过 90–98%（来自参考工作）。
• 图块和标注方法平衡了类别，并允许应用标准指标进行评估。
• 数据集包含 9 个地层界线、651 条 Inline、951 条 Crossline，以及约 190k 张带标签的图像，适用于 DL 基准测试。
• 使用该数据集已经演示了两种 DL 应用（岩层分类和语义分割）。