Saved in:
Bibliographic Details
Main Authors: Li, Jie, Yang, Qishun, Li, Nuo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.09165
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911501276676096
author Li, Jie
Yang, Qishun
Li, Nuo
author_facet Li, Jie
Yang, Qishun
Li, Nuo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09165
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GIAT: A Geologically-Informed Attention Transformer for Lithology Identification
Li, Jie
Yang, Qishun
Li, Nuo
Machine Learning
Artificial Intelligence
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.
title GIAT: A Geologically-Informed Attention Transformer for Lithology Identification
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.09165