Suppressing multiples from seismic records is necessary to improve imaging quality. Deep neural networks (DNNs) can automatically mine features from data. Once a network is successfully trained, it can process data with extremely high efficiency. In this letter, a generative adversarial network (GAN) framework is proposed to remove surface-related multiples in both synthetic and field datasets, where the generator is U-Net with Markov discriminator. Adding self-attention (SA) blocks to GAN improves processing precision. Improved signal noise ratio (SNR), and accurate reverse time migration (RTM) images implemented by network’s outputs of synthetic datasets, jointly support that this network is effective on surface-related multiple suppression. Based on the results from field application, deep learning method in this letter is comparable to conventional adaptive surface-related multiple elimination (SRME) method but time-saving. By constructing an end-to-end workflow for seismic surface-related multiples suppression, small batches dataset can be used to train the network, and large batches of datasets can be processed accurately and efficiently.

The emerging distributed fiber-optic acoustic sensing (DAS) technology has broad prospects for application in vertical seismic profiles (VSP). However, the acquired DAS-VSP data often suffers from coupled noise that seriously affects data quality. Traditional methods for suppressing coupled noise are usually time-consuming and not suitable for the large-scale denoising of DAS-VSP data. To address this, a coupled noise suppression method based on the U-Net network is proposed, and a self-attention (SA) block is introduced to enhance the denoising ability of the network. Transfer learning is employed to achieve coupled noise suppression from synthetic data to field data. Denoising results demonstrate that the network can effectively suppress coupled noise in DAS-VSP data while preserving signal energy to a certain extent, exhibiting strong generalization capability. Upon completion of network training, denoising results can be obtained within seconds, making it more convenient and efficient compared to traditional methods.

The extraction of travel-time curve of seismic phase is very important for the subsequent inference of the structural properties of underground media in seismology. In recent years, with the increase in the amount of data, manual processing is facing significant challenges, and automatic signal processing has gradually become the mainstream. According to the similarity of array signals and considering the elimination of outliers, we propose an improved multi-channel cross-correlation method using the $L_1$ norm measure to obtain preliminary results, which builds on a new controllable measurement mode. Then, the post-correction step is carried out in combination with the signal gain property of beamforming technique. Based on these two methods, this paper proposes a new scheme of automatic arrival time picking. We apply the scheme to actual data to verify the effects of the two methods step by step. The entire scheme achieves fine results: direct water waves, seismic waves refracted by the crust and seismic waves reflected by the upper mantle are automatically detected. In addition, compared with the two traditional methods, the scheme proposed in this paper has a better overall effect and a reasonable computation cost.

Utilizing the difference in phase and power spectrum between signals and noise, the estimation of direction of arrival (DOA) can be transferred to a spatial sample classification problem. The power ratio, namely signal-to-noise ratio (SNR), is highly required in most high-resolution beamforming methods so that high resolution and robustness are incompatible in a noisy background. Therefore, this paper proposes a Subspaces Deconvolution Vector (SDV) beamforming method to improve the robustness of a high-resolution DOA estimation. In a noisy environment, to handle the difficulty in separating signals from noise, we intend to initial beamforming value presets by incoherent eigenvalue in the frequency domain. The high resolution in the frequency domain guarantees the stability of the beamforming. By combining the robustness of conventional beamforming, the proposed method makes use of the subspace deconvolution vector to build a high-resolution beamforming process. The SDV method is aimed to obtain unitary frequency matrixes more stably and improve the accuracy of signal subspaces. The results of simulations and experiments show that when the input SNR is less than −27 dB, signals of decomposition differ unremarkably in the subspace while the SDV method can still obtain clear angles. In a marine background, this method works well in separating the noise and recruiting the characteristics of the signal into the DOA for subsequent processing.