物探与化探2024，Vol.48Issue(4)：1065-1075,11.DOI:10.11720/wtyht.2024.1380
基于可伸缩型注意力机制的神经网络地震数据去噪方法
A method for seismic data denoising based on the neural network with a retractable attention mechanism
摘要
Abstract
Random noise in seismic data impairs the quality of the data,thus affecting the accuracy of subsequent processing and inter-pretation.Conventional denoising methods,constrained by prior conditions,exhibit low efficiency.Neural networks possess a strong fea-ture extraction ability,which can make up for these shortcomings.However,the limitations of convolution kernels in conventional neural networks may lead to the loss of global information.Hence,this study introduced a retractable attention mechanism to the convolutional neural network(CNN).This mechanism presents both dense and sparse self-attention modules in the CNN.The alternate use of the two self-attention modules can significantly enhance the performance of the CNN and expand the receptive field.The shallow and deep fea-tures of seismic data were extracted using the convolutional layer and self-attention modules.Combined with CNN's local modeling abili-ty and Transformer's global modeling ability,they contributed to enhancing CNN's global interaction and ability to reduce noise and deal with details.As indicated by the experimental results of synthetic and field data,the method used in this study can more effectively sup-press noise and retain effective information of seismic data compared to Unet and DnCNN,significantly improving the signal-to-noise ra-tio and thus assisting in the processing and interpretation of seismic data.关键词
随机噪声/卷积神经网络/可伸缩型注意力机制/TransformerKey words
random noise/convolutional neural network/retractable attention mechanism/Transformer分类
天文与地球科学引用本文复制引用
张敏,许一卓,易继东..基于可伸缩型注意力机制的神经网络地震数据去噪方法[J].物探与化探,2024,48(4):1065-1075,11.基金项目
国家自然科学基金项目(42074133) （42074133）
中石油重大科技合作项目(ZD2019-183-003) （ZD2019-183-003）
