测井数据区间的非对比表示学习
Non-contrastive representation learning for intervals from well logs
AI总结：
该研究首次将非对比自监督学习（BYOL和Barlow Twins）应用于测井数据区间表示，通过定制增强策略，在聚类和分类任务上取得优越性能，无需标注数据。
摘要：
石油天然气行业中的表示学习问题旨在构建一个模型，该模型基于测井数据为井段提供表示。以往的尝试主要是监督式的，并侧重于相似性任务，即估计区间之间的接近程度。我们希望在无需使用监督（标注）数据的情况下构建信息丰富的表示。一种可能的方法是自监督学习（SSL）。与监督范式相比，自监督学习对数据标签的要求很少或没有。如今，大多数自监督学习方法要么是对比式的，要么是非对比式的。对比方法使相似（正）对象的表示更接近，并使不同（负）对象的表示更远离。由于正负对的标记可能出错，这些方法可能产生较差的性能。非对比方法不依赖于这种标记，在计算机视觉中广泛应用。它们仅使用相似对象对进行学习，这些对象对在测井数据中更容易识别。我们首次将非对比自监督学习引入测井数据。具体而言，我们利用了Bootstrap Your Own Latent（BYOL）和Barlow Twins方法，这些方法避免使用负样本对，仅专注于匹配正样本对。这些方法的关键部分是数据增强策略。我们的增强策略以及对BYOL和Barlow Twins的适配，使我们能够在聚类任务上获得优越的质量，并在大多数分类任务上取得最佳性能。我们的结果证明了所提出的非对比自监督方法在表示学习以及区间相似性方面的有效性。
英文摘要：
The representation learning problem in the oil & gas industry aims to construct a model that provides a representation based on logging data for a well interval. Previous attempts are mainly supervised and focus on similarity task, which estimates closeness between intervals. We desire to build informative representations without using supervised (labelled) data. One of the possible approaches is self-supervised learning (SSL). In contrast to the supervised paradigm, this one requires little or no labels for the data. Nowadays, most SSL approaches are either contrastive or non-contrastive. Contrastive methods make representations of similar (positive) objects closer and distancing different (negative) ones. Due to possible wrong marking of positive and negative pairs, these methods can provide an inferior performance. Non-contrastive methods don't rely on such labelling and are widespread in computer vision. They learn using only pairs of similar objects that are easier to identify in logging data. We are the first to introduce non-contrastive SSL for well-logging data. In particular, we exploit Bootstrap Your Own Latent (BYOL) and Barlow Twins methods that avoid using negative pairs and focus only on matching positive pairs. The crucial part of these methods is an augmentation strategy. Our augmentation strategies and adaption of BYOL and Barlow Twins together allow us to achieve superior quality on clusterization and mostly the best performance on different classification tasks. Our results prove the usefulness of the proposed non-contrastive self-supervised approaches for representation learning and interval similarity in particular.
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。
