Pretrain-to-alignment learning paradigm to improve geophysical AI applicability under scarce field labels and synthetic-to-field gaps: A case study of relative geologic time estimation in global shelf-edge clinothems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Hui, Wu, Xinming, Yang, Jiarun, Gao, Zhixiang, Dou, Yimin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914571867914240
author Gao, Hui
Wu, Xinming
Yang, Jiarun
Gao, Zhixiang
Dou, Yimin
author_facet Gao, Hui
Wu, Xinming
Yang, Jiarun
Gao, Zhixiang
Dou, Yimin
contents Artificial intelligence (AI) has been increasingly applied to various geophysical scenarios, yet its practical deployment remains limited by scarce field labels, pronounced synthetic-to-field domain gaps, and insufficient physical consistency under complex and variable field conditions. To address these challenges, we propose a pretrain-to-alignment learning paradigm that systematically integrates self-supervised pretraining, synthetic supervision, prior-driven refinement, and domain-adaptation fine-tuning into a unified progressive learning workflow. In this paradigm, geophysical AI models are developed through sequential stages that progressively build field-relevant representations, task-specific mapping capability, field consistency, and target-specific adaptability. We validate this paradigm using cross-survey relative geologic time (RGT) estimation in global shelf-edge clinothems as a representative case study. Results from 3,000 field datasets spanning multiple sedimentary basins demonstrate that the proposed paradigm achieves accurate, robust, and well-generalized performance across diverse field surveys, while significantly improving fine-scale stratigraphic and structural details. More broadly, this study provides a practical methodological reference for a broader range of geophysical AI tasks, such as interpretation, regression, and inversion problems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_16783
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Pretrain-to-alignment learning paradigm to improve geophysical AI applicability under scarce field labels and synthetic-to-field gaps: A case study of relative geologic time estimation in global shelf-edge clinothems
Gao, Hui
Wu, Xinming
Yang, Jiarun
Gao, Zhixiang
Dou, Yimin
Geophysics
Artificial intelligence (AI) has been increasingly applied to various geophysical scenarios, yet its practical deployment remains limited by scarce field labels, pronounced synthetic-to-field domain gaps, and insufficient physical consistency under complex and variable field conditions. To address these challenges, we propose a pretrain-to-alignment learning paradigm that systematically integrates self-supervised pretraining, synthetic supervision, prior-driven refinement, and domain-adaptation fine-tuning into a unified progressive learning workflow. In this paradigm, geophysical AI models are developed through sequential stages that progressively build field-relevant representations, task-specific mapping capability, field consistency, and target-specific adaptability. We validate this paradigm using cross-survey relative geologic time (RGT) estimation in global shelf-edge clinothems as a representative case study. Results from 3,000 field datasets spanning multiple sedimentary basins demonstrate that the proposed paradigm achieves accurate, robust, and well-generalized performance across diverse field surveys, while significantly improving fine-scale stratigraphic and structural details. More broadly, this study provides a practical methodological reference for a broader range of geophysical AI tasks, such as interpretation, regression, and inversion problems.
title Pretrain-to-alignment learning paradigm to improve geophysical AI applicability under scarce field labels and synthetic-to-field gaps: A case study of relative geologic time estimation in global shelf-edge clinothems
topic Geophysics
url https://arxiv.org/abs/2605.16783