Residual Learning of Cycle-GAN for Seismic Data Denoising

Random noise attenuation has always been an indispensable step in the seismic exploration workflow. The quality of the results directly affects the results of subsequent inversion and migration imaging. This paper proposes a cycle-GAN denoising framework based on the data augmentation strategy. We introduced residual learning into the cycle-GAN to improve the training efficiency of the network. We proposed a method for generating labeled datasets directly from unlabeled real noisy data. Then we significantly improve the diversity of the training samples through an augmentation strategy. Through RCGAN, we can realize intelligent seismic data denoising work, which dramatically reduces the manual selection and intervention of denoising parameters. Finally, numerical experiments prove that our method has a remarkably good random noise suppression ability and a minimally damaging effect on useful seismic signals. The experiment tests on synthetic and real data also show the effectiveness and superiority of the proposed method RCGAN compared to the state-of-the-art denoising methods.