The neural network denoising technique has achieved impressive results by being able to automatically learn the effective signal from the data without any assumptions. However, it has been found experimentally that the performance of the method using neural networks gradually decreases with increasing pollution levels when processing contaminated seismic data, and how to improve the performance will become the direction of further development of the method. As a traditional method widely used for tainted seismic data, the wavelet transform can effectively separate the signal from the noise. Thus, we propose a method combining wavelet transform and a residual neural network that achieves good results in suppressing random noise data.

The incorporation of effective denoising techniques is a crucial requirement for seismic data processing during the acquisition phase due to the inherent susceptibility of the seismic data acquisition process to various forms of interference, such as random and coherent noise. For random noise, the Residual Neural Network (Resnet), with its notable ability to effectively suppress noise in seismic data, has garnered widespread utilization in removing unwanted disturbances or interference due to its elegant simplicity and outstanding performance. Despite the considerable advancements achieved by conventional Resnet in the field of suppressing noise, it is irrefutable that there is still room for amelioration in their ability to filter out unwanted disturbances. As a result, this paper puts forth a novel attention-based methodology for Resnet, intended to overcome the present constraints and attain an optimal seismic signal enhancement. Specifically, we add the convolutional block attention module (CBAM) after the convolutional layer of the residual module and add channel attention on the shortcut connections to filter out the disturbance. We replace the commonly used ReLU activation function in the network with ELU, which is better suited for suppressing seismic noise. Empirical assessments conducted on both synthetic and authentic datasets have demonstrated the efficacy of the proposed methodology in amplifying the denoising prowess of Resnet. Our proposed method remains stable even when dealing with seismic data that has complex waveforms. The findings of this investigation evince that the recommended approach furnishes a substantial augmentation in the signal-to-noise ratio (SNR), thereby facilitating the efficient and robust extraction of the underlying signal from the noisy observations.

In microseismic monitoring, the reconstruction of a reliable velocity model is essential for precise seismic source localization and subsurface imaging. However, traditional methods for microseismic velocity inversion face challenges in terms of precision and computational efficiency. In this paper, we use deep learning (DL) algorithms to achieve precise and efficient real-time microseismic velocity modeling, which holds significant importance for ensuring engineering safety and preventing geological disasters in microseismic monitoring. Given that this task was approached as a non-linear regression problem, we adopted and modified the Attention U-Net network for inversion. Depending on the degree of coupling among microseismic events, we trained the network using both single-event and multi-event simulation records as feature datasets. This approach can achieve velocity modeling when dealing with inseparable microseismic records. Numerical tests demonstrate that the Attention U-Net can automatically uncover latent features and patterns between microseismic records and velocity models. It performs effectively in real time and achieves high precision in velocity modeling for Tilted Transverse Isotropy (TTI) velocity structures such as anticlines, synclines, and anomalous velocity models. Furthermore, it can provide reliable initial models for traditional methods.

The Marchenko method is a data-driven way that makes it possible to calculate Green’s functions from virtual points in the subsurface using the reflection data at the surface and requiring only a macro velocity model. This method requires collocated sources and receivers. However, in practice, irregular sampling of sources or receivers will cause gaps and distortions in the obtained focusing functions and Green’s functions. To solve this problem, this paper proposes to integrate a sparse inversion into the iterative Marchenko scheme. Specifically, we add sparsity constraints to the Marchenko equations and apply the sparse inversion during the iterative process. To reduce the strict requirements on acquisition geometries, our work deals with the situation in which the sources are subsampled where the integrations are carried out over the receivers, while the existing point spread function method solves the situation where the receivers are subsampled. We make a step to handle both situations at the same time by integrating this method with our work because of the same iterative framework. Our new method is applied to a two-dimensional numerical example with irregularly sampled data. The result shows that it can effectively fill gaps in the obtained focusing functions and Green’s functions in the Marchenko method.

Isotropic prestack depth migration (ISO PSDM) is still widely used in practical seismic imaging, and a large number of ISO PSDM results have already been generated in mature exploration areas. However, in anisotropic or structurally complex regions, the isotropic assumption may lead to structural mispositioning, event discontinuity, and degraded focusing quality. Although tilted transversely isotropic prestack depth migration (TTI PSDM) can improve imaging accuracy under such conditions, complete TTI reprocessing is often constrained by anisotropic parameter estimation, access to original seismic data, and computational cost. To address this practical problem, this study proposes a gated residual PSDM network, termed GRP-Net, for image-domain correction of existing ISO PSDM results toward TTI-reference-guided imaging. The proposed method formulates the task as residual learning between paired ISO and TTI PSDM images, allowing the network to capture anisotropy-related local discrepancies while preserving the dominant structural framework of the input image. A hybrid loss function combining residual-amplitude fitting value and local structural constraints is adopted to improve numerical fidelity and local structural consistency. The method is evaluated using a synthetic model and two field datasets. The corrected results show reflector continuity, structural positioning, fault delineation, and local focusing that are closer to the reference TTI PSDM images than the original ISO PSDM inputs. These results indicate that GRP-Net provides an efficient post-imaging correction strategy for anisotropy-aware updating of existing ISO PSDM images when complete TTI reprocessing is impractical.

The Marchenko method is a data-driven way which makes it possible to calculate Green's functions from virtual points in the subsurface by the reflection data at the surface, only requiring a macro velocity model. This method requires collocated sources and receivers. However, in practice, subsampling of sources or receivers will cause gaps and distortions in the obtained focusing functions and Green's functions. To solve this problem, this paper proposes to integrate sparse inversion into the iterative Marchenko scheme. Specifically, we add sparsity constraints to the Marchenko equations and apply sparse inversion during the iterative process. Our work not only reduces the strict requirements on acquisition geometries, but also avoids the complexity and instability of direct inversion for Marchenko equations. This new method is applied to a two-dimensional numerical example with irregular sampled data. The result shows that it can effectively fill gaps of the obtained focusing functions and Green's functions in the Marchenko method.