Salvato in:
Dettagli Bibliografici
Autori principali: Qi, Zhenyu, Yu, Qing, Wang, Jichen, Zhao, Yun-Bo, Li, Zerui, Lv, Wenjun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2509.18152
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912599899111424
author Qi, Zhenyu
Yu, Qing
Wang, Jichen
Zhao, Yun-Bo
Li, Zerui
Lv, Wenjun
author_facet Qi, Zhenyu
Yu, Qing
Wang, Jichen
Zhao, Yun-Bo
Li, Zerui
Lv, Wenjun
contents Well-log interpretation is fundamental for subsurface characterization but remains challenged by heterogeneous tool responses, noisy signals, and limited labels. We propose WLFM, a foundation model pretrained on multi-curve logs from 1200 wells, comprising three stages: tokenization of log patches into geological tokens, self-supervised pretraining with masked-token modeling and stratigraphy-aware contrastive learning, and multi-task adaptation with few-shot fine-tuning. WLFM consistently outperforms state-of-the-art baselines, achieving 0.0041 MSE in porosity estimation and 74.13\% accuracy in lithology classification, while WLFM-Finetune further improves to 0.0038 MSE and 78.10\% accuracy. Beyond predictive accuracy, WLFM exhibits emergent layer-awareness, learns a reusable geological vocabulary, and reconstructs masked curves with reasonable fidelity, though systematic offsets are observed in shallow and ultra-deep intervals. Although boundary detection is not explicitly evaluated here, clustering analyses suggest strong potential for future extension. These results establish WLFM as a scalable, interpretable, and transferable backbone for geological AI, with implications for multi-modal integration of logs, seismic, and textual data.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18152
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WLFM: A Well-Logs Foundation Model for Multi-Task and Cross-Well Geological Interpretation
Qi, Zhenyu
Yu, Qing
Wang, Jichen
Zhao, Yun-Bo
Li, Zerui
Lv, Wenjun
Machine Learning
Artificial Intelligence
Well-log interpretation is fundamental for subsurface characterization but remains challenged by heterogeneous tool responses, noisy signals, and limited labels. We propose WLFM, a foundation model pretrained on multi-curve logs from 1200 wells, comprising three stages: tokenization of log patches into geological tokens, self-supervised pretraining with masked-token modeling and stratigraphy-aware contrastive learning, and multi-task adaptation with few-shot fine-tuning. WLFM consistently outperforms state-of-the-art baselines, achieving 0.0041 MSE in porosity estimation and 74.13\% accuracy in lithology classification, while WLFM-Finetune further improves to 0.0038 MSE and 78.10\% accuracy. Beyond predictive accuracy, WLFM exhibits emergent layer-awareness, learns a reusable geological vocabulary, and reconstructs masked curves with reasonable fidelity, though systematic offsets are observed in shallow and ultra-deep intervals. Although boundary detection is not explicitly evaluated here, clustering analyses suggest strong potential for future extension. These results establish WLFM as a scalable, interpretable, and transferable backbone for geological AI, with implications for multi-modal integration of logs, seismic, and textual data.
title WLFM: A Well-Logs Foundation Model for Multi-Task and Cross-Well Geological Interpretation
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.18152