Real-world application of deep learning in large-scale seismic interference attenuation: A case study in the Camie Field of Angola

ABSTRACT In marine seismic acquisition, seismic interference (SI) occurs when energy from nearby external seismic source(s) is captured. It typically appears as coherent noise with linear or nonlinear movement and varying amplitudes across different sail lines. SI is commonly observed and poses a challenge for seismic data processing. A case history of a previously proposed deep neural network (DNN)-based workflow applied for SI attenuation across a marine seismic block in the Camie Field of Angola was investigated. This field survey covered more than 345 km2 and was marked by the challenge of multiple SI types. The used DNN-based workflow performed SI attenuation in the common shot domain based on a supervised learning framework: a small subset of the SI-contaminated data was first processed by a conventional geophysical algorithm to obtain an estimate of the SI noise, which was then manually blended with the SI-free common shot gathers from the same survey to generate the training pairs. To ensure signal fidelity, several techniques were applied to improve the DNN’s performance. A key highlight of the case history was its scale: it represented a real-world, large-scale processing project, and a comprehensive comparison of the DNN-based workflow with the conventional geophysical algorithm across the entire survey block, focusing on processing quality and processing time, was performed. The results demonstrated the outstanding performance of the used DNN-based workflow, which achieved higher SI removal accuracy with less signal leakage and more complete SI removal. The promising results of this application also opened up possibilities for integrating deep learning into other seismic denoising tasks. In addition, the limitations of this case history, aiming to provide insights for future research and applications in the field, were discussed.