DSU-Net: Dynamic Snake U-Net for 2-D Seismic First Break Picking

Abstract

In seismic exploration, identifying the first break (FB) is critical in establishing subsurface velocity models. Various automatic picking techniques based on deep learning have been developed to expedite this procedure. The most popular method involves using semantic segmentation networks to pick on a shot gather known as 2-D picking. Concretely, segmentation-based methods input a gather, and produce a binary segmentation map, where the highest value in each column represents the FB. However, currently designed segmentation networks make it difficult to ensure the horizontal continuity of the segmentation. FB jumps also exist in some areas, and it is challenging for current models to detect such jumps. Therefore, it is important to pick as much as possible and ensure horizontal continuity. To address this issue, we propose a novel network for 2-D seismic FB picking. We introduce the dynamic snake convolution (DSConv) from computer vision into U-Net and refer to the new model as dynamic snake U-Net (DSU-Net). Specifically, we develop the original DSConv and propose a novel DSConv module, which can extract the horizontally continuous texture in the shallow features of the shot gather. Many experiments show that DSU-Net demonstrates higher accuracy and robustness than the other 2-D segmentation-based models, achieving state-of-the-art (SOTA) performance in 2-D seismic field surveys. Particularly, it can effectively detect FB jumps and better ensure the horizontal continuity of FBs. In addition, the ablation experiment and the anti-noise experiment, respectively, verify the optimal structure of the DSConv module and the robustness of the picking.