石油物探2025，Vol.64Issue(2)：315-327,13.DOI:10.12431/issn.1000-1441.2023.0426
基于多尺度注意力UNet++的地震层位识别方法
A seismic horizon identification method based on multi-scale attention UNet++
摘要
Abstract
Common horizon identification methods based on deep learning primarily focus on seismic amplitude without sufficient attention to the spatial relationship among horizons of different scales,resulting in discontinuous and even inaccurate interpretation.To address this problem,we propose a method based on the multi-scale attention UNet++,termed MR_CBAM_UNet++,which involves MultiResBlock to extract a broader spectrum of horizon scale features,CBAM to reduce the amplitude interference of non-target signals,and a UNet++.A joint loss function composed of Focal Loss and Dice Loss is utilized for network training,and the uniqueness constraint is incorporated to refine the results of horizon identification.According to its application to actual seismic data,the MR_CBAM_UNet++model shows significantly improved capabilities compared to traditional models in suppressing non-horizon information and identifying horizons in complex subsurface conditions.A mean pixel accuracy rate of 86.19%is achieved for the test dataset,indicating more accurate horizon interpretation with better continuity.Additionally,the results of horizon identification are more geologically significant by using the uniqueness constraint.关键词
地震层位解释/UNet++/CBAM注意力模块/MultiResBlock多尺度残差模块/联合损失函数Key words
seismic horizon interpretation/UNet++/CBAM/MultiResBlock/joint loss function分类
地质学引用本文复制引用
杨润湉,马强,王志宝,李菲,吴钧,王如意..基于多尺度注意力UNet++的地震层位识别方法[J].石油物探,2025,64(2):315-327,13.基金项目
黑龙江省揭榜挂帅科技攻关项目(DQYT-2022-JS-750)、中国石油天然气集团有限公司重大科技专项(2021ZZ10-05)和黑龙江八一农垦大学自然科学人才支持计划(ZRCQC202310)共同资助. This research is financially supported by the Heilongjiang Provincial Science and Technology Tackling Project(Grant No.DQYT-2022-JS-750),China National Petroleum Corporation Major Science and Technology Project(Grant No.2021ZZ10-05),Natural Science Talent Support Program of Heilongjiang Bayi Agricultural University(Grant No.ZRCQC202310). （DQYT-2022-JS-750）
