5 April 2024 in Geophysics
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.
7 August 2024 in IEEE Transactions on Geoscience and Remote Sensing
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.
17 November 2025 in Applied Soft Computing
2 April 2026 in Applied Soft Computing
13 March 2024 in Geophysical Prospecting
3 September 2024 in IEEE Geoscience and Remote Sensing Letters
Source point offset (SPO) plays a crucial role in geophysical prospecting, as it places the source points away from obstacles to facilitate exploration efforts. However, it is time-consuming for manual work to consider various intricate conditions, such as the smoothness of source lines and uniformity of fold distribution. Moreover, existing methods cost much time in optimizing one specific objective, which limits the applicability to diverse construction areas. To address this challenge, this letter leverages the widely adopted Transformer architecture as the model and uses REINFORCE to train this model, by formulating the SPO as a combinatorial optimization problem. To enhance communication among candidate nodes in SPO, a graph attention layer extracts distinct information among these nodes. Experimental results on four field datasets demonstrate comparable performance of our method with the conventional method, while providing a reference for deviated geometry design quickly in field test survey.