Xiaoli Wei

Accurate interpolation of seismic data is crucial for improving the quality of imaging and interpretation. In recent years, deep learning models such as U-Net and generative adversarial networks have been widely applied to seismic data interpolation. However, they often underperform when the training and test missing patterns do not match. To alleviate this issue, here we propose a novel framework that is built upon the multi-modal adaptable diffusion models. In the training phase, following the common wisdom, we use the denoising diffusion probabilistic model with a cosine noise schedule. This cosine global noise configuration improves the use of seismic data by reducing the involvement of excessive noise stages. In the inference phase, we introduce the denoising diffusion implicit model to reduce the number of sampling steps. Different from the conventional unconditional generation, we incorporate the known trace information into each reverse sampling step for achieving conditional interpolation. To enhance the coherence and continuity between the revealed traces and the missing traces, we further propose two strategies, including successive coherence correction and resampling. Coherence correction penalizes the mismatches in the revealed traces, while resampling conducts cyclic interpolation between adjacent reverse steps. Extensive experiments on synthetic and field seismic data validate our model’s superiority and demonstrate its generalization capability to various missing patterns and different noise levels with just one training session. In addition, uncertainty quantification and ablation studies are also investigated.

In seismic exploration, first break (FB) picking is a crucial aspect in determining subsurface velocity models, significantly influencing the placement of wells. Many deep neural networks (DNNs)-based automatic picking methods have been proposed to accelerate this process. Significantly, the segmentation-based DNN methods provide a segmentation map and then estimate FB from the map using a thresholding technique. However, these automatic methods applied in field datasets cannot ensure robustness, especially in the case of a low signal-to-noise ratio (SNR). In this paper, we introduce uncertainty quantification into FB picking and propose a novel uncertainty-based picking deep learning network called UPNet. UPNet specifically consists of two DNNs. A Bayesian network infers a posterior distribution by sampling the segmentation map of FB. Subsequently, a regression network integrates the segmentation map, the original trace, and the low-frequency trace to infer the FB trace by trace. Finally, a decision-making method provides the final FB based on uncertainty analysis, offering people robust FB. Importantly, UPNet avoids post-processing to obtain FB using the threshold method, as in the segmentation-based picking methods, and instead provides the FB of each trace end-to-end. Moreover, UPNet not only estimates the uncertainty of the network output but can also filter out predictions with low confidence. Many experiments have shown that UPNet demonstrates higher accuracy and robustness than the deterministic DNN-based model, achieving state-of-the-art (SOTA) performance in field surveys. In addition, we verify that the calculated uncertainty is significant, which can serve as a reference for human decision-making.

Picking the first arrival of prestack gathers is an indispensable step in seismic data processing. To enhance the efficiency of seismic data processing, some deep-learning-based methods for first-arrival picking have been developed. However, when applying currently trained models to data that significantly differ from the training set, the results are often suboptimal. We refer to this predictive scenario as cross-survey picking. Therefore, further improving model generalization for accurate cross-survey picking has become an urgent problem. To overcome the problem, we develop a multistage picking method called multistage segmentation picking network (MSSPN), which breaks down the complex picking task into four stages. In the first stage, we develop a coarse segmentation network to recognize a rough trend of first arrivals. Second, a robust trend estimation method is developed in the second stage to further obtain a tighter range of first arrivals. Third, a refined segmentation network is conducted in the third stage to pick high-precision first arrivals. Finally, we develop a velocity constraint-based postprocessing strategy to remove the outliers of network pickings. Extensive experiments indicate that MSSPN outperforms current state-of-the-art methods under the cross-survey test situation in terms of the metrics of accuracy and stability. Particularly, MSSPN achieves 94.64% and 89.74% accuracy under the cross-survey field cases of the median and low signal-to-noise ratio data, respectively.

Random noise attenuation is essential in seismic data processing. In this paper, we propose an unsupervised method called “shot2shot with re-de-noising regularization” to remove random noise. Shot2Shot (S2S) is a new way to train a denoising neural network. S2S takes a shot-gather and its multiple neighboring shot-gathers as input and labels of the neural network, respectively. The principle that S2S can eliminate noise is the correlation of seismic waves and the independence of random noise between neighboring shot-gathers. Because neural networks are more likely to learn correlated information between inputs and labels rather than independent information. Although S2S is effective in denoising, this mode of training may lead to relatively coarse results. Therefore, we propose re-de-noising regularization to make the results of S2S more refined. The re-de-noising regularization consists of two penalty terms that balance each other, the re-de-noising term and the stability term. The stability term is responsible for introducing more fine content from the observations, such as weak waves, but this can introduce new noise. Thus the re-de-noising term is used to avoid the interference of this new noise. Experimentally, our method outperforms other state-of-the-art methods in terms of quantitative results. Visually, our method not only removes the noise but also reconstructs the noisy data more completely. In addition, we explain the role of S2S and re-de-noising regularization more intuitively through ablation experiments. Finally, the robustness of the key hyperparameters is discussed.

Seismic data interpolation is an indispensable part of seismic data processing. In recent years, deep-learning-based interpolation algorithms for seismic data have become popular due to their high accuracy. However, a considerable amount of work has focused on the migration of concepts and algorithms in deep-learning-based methods while ignoring the implicit properties of seismic data itself. In this paper, we propose the regeneration prior, which is an implicit property of seismic data with respect to the interpolation function, and are used for self-supervised seismic data interpolation tasks. In mathematical form, the regeneration prior can be considered as a regular term describing the structure of the seismic data. Theoretically, the regeneration prior is a necessary condition to obtain an optimal interpolation function. Experimentally, the proposed method achieves significant improvement in accuracy and intuitive visualization in comparison with advanced unsupervised or self-supervised methods. In addition, we provide an intuitive interpretation of the regeneration prior, and our study shows that the regeneration prior plays an anti-overfitting structuring role in the parameter learning process of the interpolation function. Finally, we analyze the robustness of the regeneration prior. The experimental results show that the performance of the regeneration prior is stable despite the fact that the hyperparameters associated with the regeneration prior are perturbed in a considerable range.

Seismic data are generally sampled irregularly and sparsely along spatial coordinates because economic costs and obstacles hinder the regular arrangement of geophones in the field. Thus, the sampled seismic data often contain missing traces which result in difficulties for later processing steps. To alleviate this issue, versatile interpolation methods have been developed to interpolate the missing traces. However, the existing models for recovering seismic data with consecutively missing traces in a large amplitude range tend to produce artifacts and blurred signal details. We propose in this paper a hybrid loss guided coarse-to-fine model which consists of a coarse network and a refinement network to allow different regions of seismic data to be recovered in different stages. The coarse network is designed to reconstruct the strong signals and the refinement network is implemented subsequently to recover the weak signals. In addition, the refinement network focuses its attention on the areas which are not well recovered by the coarse network via a weight-masked mechanism. By resorting to the hybrid loss function L1+SSIM+Relativistic Average Least-Square Generative Adversarial Network (RaLSGAN), our model enables more accurate and realistic signal details to be reconstructed. Experiments with synthetic and field data demonstrate that our model is superior to the existing mainstream approaches and the role of the key components is also investigated through ablation studies.

This paper empirically evaluates two kinds of features, which are extracted, respectively, with traditional statistical methods and convolutional neural networks (CNNs), in order to improve the performance of seismic patch image classification. In the latter case, feature vectors, named “CNN-features”, were extracted from one trained CNN model, and were then used to learn existing classifiers, such as support vector machines. In this case, to learn the CNN model, a technique of transfer learning using synthetic seismic patch data in the source domain, and real-world patch data in the target domain, was applied. The experimental results show that CNN-features lead to some improvements in the classification performance. By analyzing the data complexity measures, the CNN-features are found to have the strongest discriminant capabilities. Furthermore, the transfer learning technique alleviates the problems of long processing times and the lack of learning data.