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.

Seismic data denoising 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. In this article, we proposed a fast and flexible convolutional neural network (FFCNN) based on DnCNN. In contrast to the existing DnCNN and other artificial intelligence (AI)-based denoisers, FFCNN enjoys several desirable properties: 1) downsampling and upscaling operations, which can sensibly reduce runtimes and memory requirements while maintaining the denoising performance, and 2) we introduced noised level maps, which can make that a single convolutional neural network (CNN) model is expected to inherit the flexibility of handling noise models with different parameters, even spatially variant noises by noting $M$ can be nonuniform. Another benefit of increasing the noise-level map is that we can preserve more useful seismic data information by controlling the tradeoff of noise removal effect and seismic data detail preservation. For real seismic data denoised work, the main work and advantages of this article are concentrated on the following two aspects: 1) we introduced a data augmentation strategy to overcome the lack of well-labeled samples and 2) transfer learning has been introduced to the training processing, which used the well-trained synthetic seismic data denoising network as a pretrained model. In this way, we can greatly accelerate and optimize the learning efficiency of the training network. Ultimately, we can greatly improve the computational efficiency and denoising performance based on this intelligent denoised network FFCNN. Finally, numerical experiments prove the effectiveness of our method in synthetic and real seismic data

The noise attenuation of seismic data is an indispensable part of seismic data processing, directly impacting the following inversion and imaging. This paper focuses on two bottlenecks in the AI-based denoising method of seismic data: the destruction of structural information of seismic data and the inferior generalizability. We propose a flexible attention-CNN (FACNN) and realized the denoising work of seismic data. This paper’s main work and advantages were concentrated on the following three aspects: (i) We propose attention gates (AGs), which progressively suppressed features in irrelevant background parts and improved the denoising performance. (ii) We added a noise level map M as an additional channel, making a single CNN model expected to inherit the flexibility of handling noise models with different parameters, even spatially variant noises. (iii) We propose a mixed loss function based on MS_SSIM to improve the performance of FACNN further. Adding the noise level map can improve the network’s generalization ability, and adding the attention structure with the mixed loss function can better protect the structural information of the seismic data. The numerical tests showed that our method has better generalization and can better protect the details of seismic events.

The finite difference method is widely used in seismic wave numerical simulation, reverse time migration and full waveform inversion. However, the numerical dispersion problem seriously affects the results of seismic imaging and inversion. Based on this, we introduced cosine-combined window function (CCWF) used in harmonic analysis of the power system and compared the amplitude response and error properties with other window functions. Then, an optimised CCWF and a new weighting method are proposed, which results in finite-difference operators with not only large spectral coverage but also small precision error fluctuation. In this paper, the analysis shows the good stability of using finite difference operators. Finally, we perform numerical forward modelling, which denotes that our method is superior than other optimum methods. From an economic point of view, this method will effectively reduce the computation cost and improve efficiency.