Surface-related multiple elimination with deep learning

Ali Siahkoohi, D.J. Verschuur, F Herrmann

    Research output: Contribution to conferencePaperpeer-review

    11 Citations (Scopus)


    We explore the potential of neural networks in approximating the action of the computationally expensive Estimation of Primaries by Sparse Inversion (EPSI) algorithm, applied to real data, via a supervised learning algorithm. We show that given suitable training data, consisting of a relatively cheap prediction of multiples and pairs of shot records with and without surface-related multiples, obtained via EPSI, a well-trained neural network is capable of providing an approximation to the action of the EPSI algorithm. We perform our numerical experiment on the field Nelson data set. Our results demonstrate that the quality of the multiple elimination via our neural network improves compared to the case where we only feed the network with shot records with surface-related multiples. We take these benefits by supplying the neural network with a relatively poor prediction of the multiples, e.g. obtained by a relatively cheap single step of Surface-Related Multiple Elimination.
    Original languageEnglish
    Publication statusPublished - 2019
    EventSEG International Exposition and Annual Meeting 2019 - San Antonio, United States
    Duration: 15 Sep 201920 Sep 2019


    ConferenceSEG International Exposition and Annual Meeting 2019
    Abbreviated titleSEG 2019
    CountryUnited States


    Dive into the research topics of 'Surface-related multiple elimination with deep learning'. Together they form a unique fingerprint.

    Cite this