A mixed domain deblending approach for simultaneous source data based on deep learning

Abstract

The simultaneous source acquisition technology breaks the limitations of traditional seismic survey, which allows more than one source to fire almost at the same time. When the survey time is fixed, simultaneous source acquisition can increase the number of sources, while when the number of sources is fixed, this technique can greatly reduce the survey time. At present, the great advantages of this high-efficiency acquisition technology have received wide attention from academia and industry, and researchers have proposed a series of deblending methods and obtained good results. In recent years, the rapid development of deep learning provides a new solution for deblending, and it has obvious advantages in computational time compared to traditional methods when processing large-scale seismic data. We proposed a novel iterative deblending method based on deep learning, which integrates the advantages of seismic data processing in different domains. In the proposed method, by selecting the appropriate combination of domains, the separation quality is significantly improved compared to the deblended results in a single domain. The effectiveness of the proposed method is verified by deblending the synthetic and field data, and the better performance of the proposed method are demonstrated by comparing it with the multilevel median filter method and conventional deep learning-based methods.