石油物探2024，Vol.63Issue(1)：116-128,13.DOI:10.12431/issn.1000-1441.2024.63.01.010
基于Swin-Transformer与生成对抗网络的地震随机噪声压制方法
Seismic random noise suppression based on Swin-Transformer and generative adversarial network
摘要
Abstract
Noise suppression using deep learning methods is mostly based on convolutional neural networks.The convolution operation u-sing the convolution kernel extracts local features,instead of global features,of seismic data;thus,random noises could not be eliminated perfectly.In addition,L1 and L2 loss functions tend to generate an over-smoothed network model and consequent false events and errone-ously high values of peak signal-to-noise ratio(PSNR)and structural similarity(SSIM).To address this issue,we develop a denoising method based on the Swin-Transformer and generative adversarial network(ST-GAN).The Swin-Transformer functions as the generative network in the GAN for denoising,and the discrimination network is based on a convolutional neural network.Global features of seismic da-ta,which could be obtained owing to the self-attention mechanism of the Transformer,and local features derived from the convolutional neural network may complement each other for the better performance of the network model.The use of adversarial loss makes it possible to recover more details by applying the network model and mitigate artificial events caused by over-smoothing.The comparative analysis shows that our approach is superior to other denoising methods in feature extraction and signal-to-noise ratio because random noises are ef-fectively reduced and meanwhile more details of seismic data are recovered and preserved.关键词
深度学习/噪声压制/Swin-Transformer/自注意力机制/生成对抗网络/卷积神经网络/损失函数Key words
deep learning/noise suppression/Swin-Transformer/self-attention/GAN/CNN/loss function分类
天文与地球科学引用本文复制引用
周鸿帅,程冰洁,徐天吉..基于Swin-Transformer与生成对抗网络的地震随机噪声压制方法[J].石油物探,2024,63(1):116-128,13.基金项目
国家自然科学基金面上基金(42074160)和四川省自然科学基金项目(2023NSFSC0255)共同资助.This research is financially supported by the National Natural Science Foundation of China(Grant No.42074160),Natural Science Foundation of Si-chuan(Grant No.2023NSFSC0255). （42074160）
