物探化探计算技术2026，Vol.48Issue(4)：514-524,11.DOI:10.12474/wthtjs.20260226-0002
基于残差Haar离散小波变换与多约束损失的深度学习地震超分和去噪方法研究
Research on deep learning seismic super-resolution and denoising method based on residual Haar discrete wavelet transform and multi-constraint loss
摘要
Abstract
Addressing the pervasive issues of insufficient resolution and noise interference in field seismic data,this study develops a deep learning approach that integrates architectural enhancements with multi-constrained loss function optimization to achieve joint seismic image super-resolution and denoising.Built upon the U-Net framework,the method replaces standard downsampling operations with a Residual Haar Discrete Wavelet Transform(RHDWT)module to better preserve the frequency characteristics of seismic signals.Simultaneously,sub-pixel convolutional layers are employed for efficient upsampling,complemented by residual blocks to enhance the network's ability to learn detailed seismic features.Regarding the loss function design,a composite function comprising L1 loss,Multi-Scale Structural Similarity(MS-SSIM)loss,and Frequency Focal Loss(FFL)is constructed.This framework constrains the training process across multiple dimensions—image reconstruction error,structural consistency,and spectral information—thereby synergistically optimizing both super-resolution and denoising performance.Experimental results on both synthetic and field data demonstrate that the proposed method effectively suppresses noise while enhancing the resolution of seismic profiles.It successfully recovers high-frequency details,improving the lateral continuity of weak reflectors and the spatial identification of thin-bed structures.关键词
地震数据/超分辨率/深度学习/焦点频率损失/小波变换Key words
seismic data/super-resolution/deep learning/focal frequency loss/wavelet transform分类
天文与地球科学引用本文复制引用
王锐,李亚星,杨丰瑞,黄建平..基于残差Haar离散小波变换与多约束损失的深度学习地震超分和去噪方法研究[J].物探化探计算技术,2026,48(4):514-524,11.基金项目
国家自然科学基金(42504129) （42504129）
四川省自然科学基金创新研究群体项目(2026NSFSCZY0053) （2026NSFSCZY0053）
