ConSeisDiff: A conditional diffusion approach to mitigate synthetic-real disparities in seismic fault detection

IF 2.1 3区 地球科学 Q2 GEOSCIENCES, MULTIDISCIPLINARY
Isack Farady , Chia-Chen Kuo , Soufiene Sellami , Chih-Yang Lin
{"title":"ConSeisDiff: A conditional diffusion approach to mitigate synthetic-real disparities in seismic fault detection","authors":"Isack Farady ,&nbsp;Chia-Chen Kuo ,&nbsp;Soufiene Sellami ,&nbsp;Chih-Yang Lin","doi":"10.1016/j.jappgeo.2025.105956","DOIUrl":null,"url":null,"abstract":"<div><div>Seismic fault detection is a critical task in geophysical exploration, demanding accuracy and efficiency in interpreting subsurface structures. While manual interpretation requires significant resources, deep learning models have become invaluable in automating the process of fault detection. However, the availability of labeled seismic fault data remains extremely limited, which pushes researchers to rely on synthetic images. In this work, we introduce ConSeisDiff (Conditional Seismic Diffusion) network, a novel conditional denoising diffusion model designed to generate synthetic seismic data for fault detection. Unlike traditional methods that rely on simplistic and conventional fault generation approaches, ConSeisDiff generates 2D seismic images by conditioning on fault layer attributes and facies maps. A key finding of our model is the introduction of a seismic conditional encoder, which incorporates seismic layer information extracted from the Canny edge algorithm, thereby enhancing the model’s ability to capture complex geological layers and structures. ConSeisDiff leverages a dual-path encoder–decoder architecture, combining residual blocks with transformer-based attention mechanisms to capture both local and global seismic features. We evaluate ConSeisDiff using several metrics, including MSE, PSNR, DSSIM, and FID, demonstrating that it outperforms state-of-the-art generative models in terms of fidelity and structural quality. Furthermore, we show that models trained on synthetic data generated by ConSeisDiff achieve performance comparable to those trained on real seismic data, effectively bridging the gap between synthetic and real-world applications.</div></div>","PeriodicalId":54882,"journal":{"name":"Journal of Applied Geophysics","volume":"243 ","pages":"Article 105956"},"PeriodicalIF":2.1000,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Applied Geophysics","FirstCategoryId":"89","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0926985125003374","RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Seismic fault detection is a critical task in geophysical exploration, demanding accuracy and efficiency in interpreting subsurface structures. While manual interpretation requires significant resources, deep learning models have become invaluable in automating the process of fault detection. However, the availability of labeled seismic fault data remains extremely limited, which pushes researchers to rely on synthetic images. In this work, we introduce ConSeisDiff (Conditional Seismic Diffusion) network, a novel conditional denoising diffusion model designed to generate synthetic seismic data for fault detection. Unlike traditional methods that rely on simplistic and conventional fault generation approaches, ConSeisDiff generates 2D seismic images by conditioning on fault layer attributes and facies maps. A key finding of our model is the introduction of a seismic conditional encoder, which incorporates seismic layer information extracted from the Canny edge algorithm, thereby enhancing the model’s ability to capture complex geological layers and structures. ConSeisDiff leverages a dual-path encoder–decoder architecture, combining residual blocks with transformer-based attention mechanisms to capture both local and global seismic features. We evaluate ConSeisDiff using several metrics, including MSE, PSNR, DSSIM, and FID, demonstrating that it outperforms state-of-the-art generative models in terms of fidelity and structural quality. Furthermore, we show that models trained on synthetic data generated by ConSeisDiff achieve performance comparable to those trained on real seismic data, effectively bridging the gap between synthetic and real-world applications.
ConSeisDiff:一种条件扩散方法来缓解地震断层检测中的合成-真实差异
地震断层检测是地球物理勘探中的一项重要任务,对地下构造的解释精度和效率要求很高。虽然人工解释需要大量的资源,但深度学习模型在自动化故障检测过程中已经变得非常宝贵。然而,标记地震断层数据的可用性仍然非常有限,这迫使研究人员依赖于合成图像。在这项工作中,我们引入了ConSeisDiff(条件地震扩散)网络,这是一种新的条件去噪扩散模型,旨在生成用于故障检测的合成地震数据。与传统方法依赖于简单的常规断层生成方法不同,ConSeisDiff通过断层层属性和相图来生成二维地震图像。该模型的一个关键发现是引入了地震条件编码器,该编码器结合了从Canny边缘算法中提取的地震层信息,从而增强了模型捕获复杂地质层和结构的能力。ConSeisDiff利用双路径编码器-解码器架构,将剩余块与基于变压器的注意机制相结合,以捕获局部和全局地震特征。我们使用几个指标来评估ConSeisDiff,包括MSE、PSNR、DSSIM和FID,证明它在保真度和结构质量方面优于最先进的生成模型。此外,我们还表明,在ConSeisDiff生成的合成数据上训练的模型的性能与在真实地震数据上训练的模型相当,有效地弥合了合成应用与真实应用之间的差距。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Journal of Applied Geophysics
Journal of Applied Geophysics 地学-地球科学综合
CiteScore
3.60
自引率
10.00%
发文量
274
审稿时长
4 months
期刊介绍: The Journal of Applied Geophysics with its key objective of responding to pertinent and timely needs, places particular emphasis on methodological developments and innovative applications of geophysical techniques for addressing environmental, engineering, and hydrological problems. Related topical research in exploration geophysics and in soil and rock physics is also covered by the Journal of Applied Geophysics.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信