A foundation model enpowered by a multi-modal prompt engine for universal seismic geobody interpretation across surveys

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Hang, Wu, Xinming, Liang, Luming, Sheng, Hanlin, Si, Xu, Hui, Gao, Li, Yaxing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913500011429888
author Gao, Hang
Wu, Xinming
Liang, Luming
Sheng, Hanlin
Si, Xu
Hui, Gao
Li, Yaxing
author_facet Gao, Hang
Wu, Xinming
Liang, Luming
Sheng, Hanlin
Si, Xu
Hui, Gao
Li, Yaxing
contents Seismic geobody interpretation is crucial for structural geology studies and various engineering applications. Existing deep learning methods show promise but lack support for multi-modal inputs and struggle to generalize to different geobody types or surveys. We introduce a promptable foundation model for interpreting any geobodies across seismic surveys. This model integrates a pre-trained vision foundation model (VFM) with a sophisticated multi-modal prompt engine. The VFM, pre-trained on massive natural images and fine-tuned on seismic data, provides robust feature extraction for cross-survey generalization. The prompt engine incorporates multi-modal prior information to iteratively refine geobody delineation. Extensive experiments demonstrate the model's superior accuracy, scalability from 2D to 3D, and generalizability to various geobody types, including those unseen during training. To our knowledge, this is the first highly scalable and versatile multi-modal foundation model capable of interpreting any geobodies across surveys while supporting real-time interactions. Our approach establishes a new paradigm for geoscientific data interpretation, with broad potential for transfer to other tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2409_04962
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A foundation model enpowered by a multi-modal prompt engine for universal seismic geobody interpretation across surveys
Gao, Hang
Wu, Xinming
Liang, Luming
Sheng, Hanlin
Si, Xu
Hui, Gao
Li, Yaxing
Geophysics
Machine Learning
Seismic geobody interpretation is crucial for structural geology studies and various engineering applications. Existing deep learning methods show promise but lack support for multi-modal inputs and struggle to generalize to different geobody types or surveys. We introduce a promptable foundation model for interpreting any geobodies across seismic surveys. This model integrates a pre-trained vision foundation model (VFM) with a sophisticated multi-modal prompt engine. The VFM, pre-trained on massive natural images and fine-tuned on seismic data, provides robust feature extraction for cross-survey generalization. The prompt engine incorporates multi-modal prior information to iteratively refine geobody delineation. Extensive experiments demonstrate the model's superior accuracy, scalability from 2D to 3D, and generalizability to various geobody types, including those unseen during training. To our knowledge, this is the first highly scalable and versatile multi-modal foundation model capable of interpreting any geobodies across surveys while supporting real-time interactions. Our approach establishes a new paradigm for geoscientific data interpretation, with broad potential for transfer to other tasks.
title A foundation model enpowered by a multi-modal prompt engine for universal seismic geobody interpretation across surveys
topic Geophysics
Machine Learning
url https://arxiv.org/abs/2409.04962