基于体素的地震数据三维岩相分割：一项对比研究
Voxel-based 3D Facies Segmentation from Seismic Data: A Comparative Study
- FPT Software AI Center（FPT软件人工智能中心）
- Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA)（信息与随机系统研究所）
- Université Bretagne Sud（南布列塔尼大学）
- University of Liverpool（利物浦大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对地震岩相分割存在的三维空间连续性缺失问题，本研究构建基于体素的三维分割可复现基准，评估三类现代三维分割架构并建立基线结果，为该领域后续研究提供参考。
AI中文摘要：
地震岩相分割已成为地球物理学领域的一项重大挑战，需要可靠的方法和系统，以在标注数据有限的情况下有效识别地质上相似的岩相。尽管现有研究在二维岩相分割中已显示出良好结果，但它们通常将原始三维地震体预处理为二维切片集（通常为 inline 和 crossline 方向），并将该问题视为纯二维分割任务。这种简化会导致切片间的不连续性，无法保留三维地震数据中的空间和结构连续性，从而限制模型学习连贯地质模式的能力。本研究构建了基于体素的三维地震岩相分割的可复现对比基准，使用公开可用的地震体，包括 Netherlands F3 和 Parihaka 数据集，并采用标准化的数据划分和评估指标。通过评估三类代表性的现代三维分割架构，我们建立了强有力的基线结果，凸显了该领域未来研究的潜力和剩余挑战。
英文摘要：
Seismic facies segmentation has emerged as a significant challenge in geophysics, requiring robust methods and systems to effectively identify geologically analogous facies with limited labeled data. Although existing studies have shown promising results in 2D facies segmentation, they often preprocess the original 3D seismic volumes into sets of 2D slices, typically the inline and crossline directions, and treat this problem as a purely 2D segmentation task. This simplification introduces discontinuities across slices and fails to preserve the spatial and structural continuity in 3D seismic data, thus limiting the model's ability to learn coherent geological patterns. In this work, we present a comparative and reproducible benchmark for voxel-based 3D seismic facies segmentation, built upon publicly available seismic volumes including the Netherlands F3 and the Parihaka datasets, with standardized data splits and evaluation metrics. By evaluating the three representative families of modern 3D segmentation architectures, we establish strong baseline results that highlight the potential and remaining challenges for future research in this domain.
