煤田地质与勘探2025，Vol.53Issue(5)：196-206,11.DOI:10.12363/issn.1001-1986.24.09.0601
卷积Mamba模型驱动的地震随机噪声压制方法
A seismic random noise suppression method based on CNN-Mamba
摘要
Abstract
[Background]Seismic random noise suppression is recognized as a key step to improve the quality of seis-mic data.Data-driven deep learning provides an intelligent solution for the noise suppression.However,mainstream ran-dom noise intelligent methods based on convolutional neural networks(CNNs)are constrained by their local receptive fields.This limitation results in insufficient collaborative optimization between local details and macroscopic structures during denoising,further reducing the noise suppression accuracy.Transformer models,which are widely applied to global feature extraction,can effectively capture long-distance dependencies through the self-attention mechanism,the-oretically overcoming the limitations of CNNs in global modeling.However,these models face challenges such as slow computation,high resource consumption,and limited applications.[Objective and Methods]To address these issues,this study proposed a CMUNet seismic random noise suppression network that integrates CNN and Mamba.Based on the 2D-selective-scan(SS2D)mechanism,which can traverse the input data along horizontal and vertical directions,a global dynamic system was constructed using state-space equations.This enabled the trans-scale feature extraction of the spatiotemporal characteristics of seismic data.The hardware-aware parallel algorithm of Mamba was employed to re-duce the computational resource consumption,thus ensuring the denoising performance while enhancing computational efficiency.Targeting the characteristics of seismic data,this study designed a CNN-Mamba hybrid block to construct hierarchical feature extraction pathways in the UNet encoder.Specifically,the CNN in a shallow layer focused on local noise pattern recognition,while Mamba in a deep layer was used to capture the correlations of large-scale geological structures.Additionally,residual channel attention gating was further introduced to enhance the feature separability between effective signals and noise.[Results and Conclusions]The results indicate that for synthetic data,the pro-posed CMUNet network increased the signal-to-noise ratio(RS/N),peak signal-to-noise ratio(RPSN),and structural similarity by 2.4 dB,2.4 dB,and 0.005 6,respectively compared to UNet.These results suggest that the CMUNet net-work enables effective random noise suppression and preserves effective signals.This network was applied to field seis-mic data.An image-based local similarity analysis reveals that the network yielded low local similarity,further corrobor-ating that it causes minimal damage to effective signals and exhibits superior amplitude preservation.Therefore,the CMUNet network proposed in this study holds great potential for application.关键词
地震随机噪声压制/深度学习/卷积神经网络/状态空间模型/MambaKey words
seismic random noise suppression/deep learning/convolutional neural network(CNN)/state-space model(SSM)/Mamba分类
天文与地球科学引用本文复制引用
韦秀娟,刘兴业,周怀来..卷积Mamba模型驱动的地震随机噪声压制方法[J].煤田地质与勘探,2025,53(5):196-206,11.基金项目
四川省自然科学基金项目(2024NSFSC1990,2024NSFSC1984) （2024NSFSC1990,2024NSFSC1984）
