将地质先验融入注意力机制，提升岩性识别准确率与可解释性。
GIAT: A Geologically-Informed Attention Transformer for Lithology Identification
- 用地质相关性滤波生成注意力偏置矩阵，引导模型学习地质合理模式。
- 在两个数据集上达到最高95.4%准确率，显著优于现有方法。
- 预测结果更符合地质规律，适合需要可信深度学习的地球科学场景。
从测井数据中准确识别岩性对地下资源评估至关重要。尽管基于Transformer的模型在序列建模上表现优异，但其“黑箱”特性及缺乏地质指导限制了性能与可信度。为此，本文提出地质启发注意力变压器（GIAT），一种将数据驱动的地质先验深度融合至Transformer注意力机制的新框架。GIAT的核心是新型注意力偏置机制：通过重构类别相关序列相关性（CSC）滤波器生成地质启发的关系矩阵，并注入自注意力计算，显式引导模型关注地质一致模式。在两个具有挑战性的数据集上，GIAT实现了高达95.4%的准确率，显著优于现有模型。更重要的是，GIAT在输入扰动下表现出卓越的可解释性忠实度，生成的预测结果具备地质合理性。本工作为构建更准确、可靠且可解释的深度学习模型提供了地球科学应用的新范式。
原文摘要 · Abstract (English)
Accurate lithology identification from well logs is crucial for subsurface resource evaluation. Although Transformer-based models excel at sequence modeling, their "black-box" nature and lack of geological guidance limit their performance and trustworthiness. To overcome these limitations, this letter proposes the Geologically-Informed Attention Transformer (GIAT), a novel framework that deeply fuses data-driven geological priors with the Transformer's attention mechanism. The core of GIAT is a new attention-biasing mechanism. We repurpose Category-Wise Sequence Correlation (CSC) filters to generate a geologically-informed relational matrix, which is injected into the self-attention calculation to explicitly guide the model toward geologically coherent patterns. On two challenging datasets, GIAT achieves state-of-the-art performance with an accuracy of up to 95.4%, significantly outperforming existing models. More importantly, GIAT demonstrates exceptional interpretation faithfulness under input perturbations and generates geologically coherent predictions. Our work presents a new paradigm for building more accurate, reliable, and interpretable deep learning models for geoscience applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。