石油物探2026，Vol.65Issue(3)：427-441,15.DOI:10.12431/issn.1000-1441.2025.0099
基于Transformer架构的GLT-Unet网络地震数据去噪方法
The Transformer architecture-based GLT-Unet network for seismic data denoising
摘要
Abstract
Due to the limitations of complex field environments and acquisition equipment conditions,seismic data inevitably contain noise during the recording process,which adversely affects subsequent data processing and interpretation.The U-Net architecture is effective in capturing local feature details,while the Transformer excels at modeling global contextual information.Both types of networks have shown significant potential in seismic data denoising,but there exists a semantic gap when fusing features from these two architectures,which reduces the accuracy of signal reconstruction and hinders the preservation of weak but valid signals.To address this issue,a Global-Local Transformer U-net(GLT-Unet)based on the Transformer architecture was proposed.Built upon U-Net and Transformer,a Global-Local Context Feature Block(G-LCF)module was designed,which effectively fused local and global features of seismic data,thereby suppressing noise while preserving valid signals.Specifically,GLT-Unet first employed a CNN-Transformer hybrid encoder to extract local and global features from the seismic data.Then,the G-LCF module integrated these features to enhance the fusion effect.Finally,the decoder adopted a cascaded up-sampling structure to progressively reconstruct signal details,improving the preservation of weak signals.Denoising experiments on both synthetic and field data demonstrated that the proposed method achieved superior noise suppression compared to the K-means Singular Value Decomposition(K-SVD)dictionary learning method and the TransUNet network,while also providing better protection for weak but valid signals.关键词
Transformer架构/GLT-Unet网络/地震数据去噪/特征融合/G-LCF模块Key words
Transformer architecture/GLT-Unet/seismic data denoising/feature fusion/G-LCF module分类
能源科技引用本文复制引用
郑续发,白敏,吴娟,马昭阳,曾阳,桂志先..基于Transformer架构的GLT-Unet网络地震数据去噪方法[J].石油物探,2026,65(3):427-441,15.基金项目
国家自然科学基金项目(42174159,41904110)、湖北省教育厅科学技术研究项目重点项目(D20241304)和油气资源与勘探技术教育部重点实验室青年创新团队项目(KPI2021-01)共同资助. This research is financially supported by the National Natural Science Foundation of China(Grant Nos.42174159,41904110),the Science and Technology Research Program of the Education Department of Hubei Province(Grant No.D20241304),and the Key Laboratory of Exploration Technologies for Oil and Gas Resources(Yangtze University),Ministry of Education(Grant No.KPI2021-01). （42174159,41904110）
