Near-offset gap trace extrapolation based on self-supervised learning

Abstract

Marine seismic surveys conducted using a towed streamer system acquire data with missing traces in the near-offset range due to the limitations of the survey equipment. This means that the data is not fully acquired to zero offset. Therefore, the restoration of near-offset data using deep learning (DL) techniques presents unique challenges because it is impossible to learn from label data, which are typically used in DL-based interpolation methods. Therefore, we propose a novel approach involving self-supervised learning (SSL). SSL is a training paradigm in DL, where a model is trained on a task using the data itself, rather than over-relying on label data. SSL consists of a two-step process; upstream and downstream tasks. In this study, an upstream task performs training of various near-offset features using synthetic datasets from public domain. Subsequently, the downstream task produces an extrapolation model through transfer learning with the pre-trained near-offset features to the target data. In other words, the trained model is not only able to learn the information of the near-offset range effectively, but is also properly tailored to the features of the target data. The effectiveness of the proposed method was validated in numerical experiments. Then, to verify the field applicability, we tested its performance using field data. The reliability of the proposed approach was established through cross-validation, by comparing its results with those of a previous DL-based method and the pre-trained model. All experiment results demonstrated that the proposed method effectively extrapolated near-offset gaps in real field data.