Wang Mingwei, Li Yong, Liu Yingtian, Peng Junheng, Li Huating
{"title":"DCMSA: Multi-Head Self-Attention Mechanism Based on Deformable Convolution For Seismic Data Denoising","authors":"Wang Mingwei, Li Yong, Liu Yingtian, Peng Junheng, Li Huating","doi":"arxiv-2408.06963","DOIUrl":null,"url":null,"abstract":"When dealing with seismic data, diffusion models often face challenges in\nadequately capturing local features and expressing spatial relationships. This\nlimitation makes it difficult for diffusion models to remove noise from complex\nstructures effectively. To tackle this issue, we propose a novel convolutional\nattention mechanism Multi-head Self-attention mechanism based on Deformable\nconvolution (DCMSA) achieving efficient fusion of diffusion models with\nconvolutional attention. The implementation of DCMSA is as follows: First, we\nintegrate DCMSA into the UNet architecture to enhance the network's capability\nin recognizing and processing complex seismic data. Next, the diffusion model\nutilizes the UNet enhanced with DCMSA to process noisy data. The results\nindicate that this method addresses the shortcomings of diffusion models in\ncapturing local features and expressing spatial relationships effectively,\nproving superior to traditional diffusion models and standard neural networks\nin noise suppression and preserving meaningful seismic data information.","PeriodicalId":501270,"journal":{"name":"arXiv - PHYS - Geophysics","volume":"15 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Geophysics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.06963","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
When dealing with seismic data, diffusion models often face challenges in
adequately capturing local features and expressing spatial relationships. This
limitation makes it difficult for diffusion models to remove noise from complex
structures effectively. To tackle this issue, we propose a novel convolutional
attention mechanism Multi-head Self-attention mechanism based on Deformable
convolution (DCMSA) achieving efficient fusion of diffusion models with
convolutional attention. The implementation of DCMSA is as follows: First, we
integrate DCMSA into the UNet architecture to enhance the network's capability
in recognizing and processing complex seismic data. Next, the diffusion model
utilizes the UNet enhanced with DCMSA to process noisy data. The results
indicate that this method addresses the shortcomings of diffusion models in
capturing local features and expressing spatial relationships effectively,
proving superior to traditional diffusion models and standard neural networks
in noise suppression and preserving meaningful seismic data information.