GIAT: A Geologically-Informed Attention Transformer for Lithology Identification

• URL: http://arxiv.org/abs/2603.09165v1
• Date: Tue, 10 Mar 2026 04:02:57 GMT
• Title: GIAT: A Geologically-Informed Attention Transformer for Lithology Identification
• Abstract summary: Geologically-Informed Attention Transformer (GIAT) is a novel framework that fuses data-driven geological priors with the Transformer's attention mechanism.<n>GIAT achieves state-of-the-art performance with an accuracy of up to 95.4%, significantly outperforming existing models.
• Score: 6.315199366662337
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Defending against Model Extraction for GNNs with Model Reprogramming [57.82196268649236]
  Graph Neural Networks (GNNs) serve as the backbone for high-stakes applications in Machine-Learning-as-a-Service (ML)<n>Still, their black-box deployment exposes them to Model Extraction (ME) attacks.<n>Existing defenses suffer from a critical ''Euclidean bias''<n>We propose GraphRP, a proactive defense framework that repurposes Model Reprogramming for security.
  arXiv  Detail & Related papers  (2026-08-11T23:20:15Z)
• Towards Fast GNN Surrogates for CO2 Migration in Complex Geological Formations [58.079925240809644]
  We propose an end-to-end graph neural surrogate tailored to CO$$ibility plume migration forecasting in geological storage.<n>The method is evaluated on the SPE11A benchmark, a well-known industry test case designed to assess CO$$ storage scenarios.<n>The proposed model produces competitive forecasts of gas saturation and liquid-phase density, with cumulative errors that remain moderate over extended forecasting horizons.
  arXiv  Detail & Related papers  (2026-06-15T18:19:17Z)
• Geo-Expert: Towards Expert-Level Geological Reasoning via Parameter-Efficient Fine-Tuning [8.269639082702934]
  Current AI in Earth sciences predominantly targets surface remote sensing and GIS.<n>We introduce Geo-Expert, a family of parameter-efficient geological LLMs fine-tuned on a custom-curated, high-quality instruction dataset.<n>Our evaluation on a novel domain-specific benchmark, Geo-Eval, reveals that a domain-aligned 8B model can outperform open-weight 70B generalists and proprietary GPT-4o on specialized geological reasoning.
  arXiv  Detail & Related papers  (2026-05-24T03:28:17Z)
• GeoDecider: A Coarse-to-Fine Agentic Workflow for Explainable Lithology Classification [52.5232577739543]
  Lithology classification aims to infer subsurface rock types from well-logging signals.<n>Existing methods still treat lithology classification as a single-pass classification task.<n>We propose GeoDecider, a coarse-to-fine agentic workflow that enables accurate and explainable lithology classification.
  arXiv  Detail & Related papers  (2026-05-05T05:42:51Z)
• GeoMind: An Agentic Workflow for Lithology Classification with Reasoned Tool Invocation [18.369627120655608]
  Lithology classification in well logs is a fundamental geoscience data mining task.<n>Existing approaches typically formulate the problem as a static, single-step discriminative mapping.<n>We propose GeoMind, a tool-augmented agentic framework that models lithology classification as a sequential reasoning process.
  arXiv  Detail & Related papers  (2026-04-23T10:02:59Z)
• GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI [52.13138825802668]
  GeoFMs are transforming Earth Observation, but evaluation lacks standardized protocols.<n> GEO-Bench-2 addresses this with a comprehensive framework spanning classification, segmentation, regression, object detection, and instance segmentation.<n>Code, data, and leaderboard for GEO-Bench-2 are publicly released under a permissive license.
  arXiv  Detail & Related papers  (2025-11-19T17:45:02Z)
• History Matching under Uncertainty of Geological Scenarios with Implicit Geological Realism Control with Generative Deep Learning and Graph Convolutions [0.10923877073891446]
  The graph-based variational autoencoder represents an architecture that can handle the uncertainty of different geological scenarios.<n>We offer in-depth analysis of the latent space using tools such as PCA, t-SNE, and TDA to illustrate its structure.
  arXiv  Detail & Related papers  (2025-07-14T12:14:17Z)
• Exoplanet Classification through Vision Transformers with Temporal Image Analysis [0.0]
  We propose a methodology that transforms raw light curve data from NASA's Kepler mission into Gramian Angular Fields (GAFs) and Recurrence Plots (RPs)<n>These transformed images serve as inputs to the Vision Transformer (ViT) model, leveraging its ability to capture intricate temporal dependencies.<n>We assess the performance of the model through recall, precision, and F1 score metrics, using a 5-fold cross-validation approach to obtain a robust estimate of the model's performance.
  arXiv  Detail & Related papers  (2025-06-19T20:57:17Z)
• Leveraging Time-Series Foundation Model for Subsurface Well Logs Prediction and Anomaly Detection [0.0]
  We present a time-series foundation model for predicting and detecting anomalies in borehole well log data.<n>Our proposed model demonstrated excellent performance, achieving R2 of up to 87% and a mean absolute percentage error (MAPE) as low as 1.95%.<n>The model's zero-shot capability successfully identified subtle yet critical anomalies, such as drilling hazards or unexpected geological formations, with an overall accuracy of 93%.
  arXiv  Detail & Related papers  (2024-12-07T15:23:52Z)
• SPARTAN: A Sparse Transformer Learning Local Causation [63.29645501232935]
  Causal structures play a central role in world models that flexibly adapt to changes in the environment. We present the SPARse TrANsformer World model (SPARTAN), a Transformer-based world model that learns local causal structures between entities in a scene. By applying sparsity regularisation on the attention pattern between object-factored tokens, SPARTAN identifies sparse local causal models that accurately predict future object states.
  arXiv  Detail & Related papers  (2024-11-11T11:42:48Z)
• Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model [45.45700202300292]
  CaPaint aims to identify causal regions in data and endow model with causal reasoning ability in a two-stage process.<n>By using a fine-tuned unconditional Diffusion Probabilistic Model (DDPM) as the generative prior, we in-fill the masks defined as environmental parts.<n>Experiments conducted on five real-world ST benchmarks demonstrate that integrating the CaPaint concept allows models to achieve improvements ranging from 4.3% to 77.3%.
  arXiv  Detail & Related papers  (2024-09-29T08:18:50Z)
• Surrogate Model for Geological CO2 Storage and Its Use in Hierarchical MCMC History Matching [0.0]
  We extend the recently introduced recurrent R-U-Net surrogate model to treat geomodel realizations drawn from a wide range of geological scenarios. We show that, using observed data from monitoring wells in synthetic true' models, geological uncertainty is reduced substantially.
  arXiv  Detail & Related papers  (2023-08-11T18:29:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.