石油物探2025，Vol.64Issue(3)：482-493,12.DOI:10.12431/issn.1000-1441.2024.0128
基于多尺度特征融合的生成对抗网络地震数据重建算法
Seismic data reconstruction based on MSF-GAN
摘要
Abstract
To address the problems of spatial discontinuity,blurred edges,and loss of structural details in seismic data reconstruction,a new algorithm is proposed based on multi-scale feature fusion and generative adversarial network(MSF-GAN).The algorithm designs a multi-scale feature fusion generator in the GAN for effective seismic feature extraction and multi-scale fusion.A feature splicing module is designed in the generator for adaptively adding masks to seismic data,so as to splice the reconstructed data and the original intact data and improve computational efficiency.A multi-dimensional adversarial discriminator is designed in the GAN to improve reconstruction accuracy.Furthermore,a hybrid loss function integrating Smooth L1 reconstruction loss and adversarial loss is proposed to update the generator and improve reconstruction reliability.Public data and seismic data from Daqing oilfield are reconstructed to validate the algorithm in different scenarios:continuous data loss,random data loss,and regular data loss.MSF-GAN performs better than orthogonal matching pursuit,projection onto convex sets,and spectrally normalized generative adversarial network in structural details and spatial continuity.关键词
地震数据重建/生成对抗网络/多尺度特征融合/特征拼接/深度学习Key words
seismic data reconstruction/generator adversarial network/multi-scale feature fusion/feature splicing/deep learning分类
石油、天然气工程引用本文复制引用
李跃,罗倩,段中钰..基于多尺度特征融合的生成对抗网络地震数据重建算法[J].石油物探,2025,64(3):482-493,12.基金项目
山西省科技重大专项项目"煤层气储层三维精细地质建模方法及软件研发"(20201101004)资助.This research is financially supported by the Major Science and Technology Project of Shanxi Province(Grant No.20201101004). （20201101004）
