Abstract
Simultaneous acquisition is a construction method that has been proposed in recent years to meet the requirements of ultra-large-scale and high-precision seismic exploration. Such method is highly efficient and can significantly reduce exploration costs by saving manpower and material resources, being extensively used in offshore exploration and several foreign seismic exploration projects. The data deblending step is a significant part of the operation of simultaneous acquisition, which directly affects the acquired data quality, and is a key factor for the success of oil and gas exploration. The simultaneous use of multiple seismic sources can generate blended noise with a random distribution in non-shot-gather datasets. However, the useful signal exhibits strong coherence, making it possible to separate the non-used wavefield from the blended data. Although the blended noise is randomly distributed in non-shot-gather datasets, it also has characteristics that are different from normal ambient noise, and its kinematic and dynamical characteristics are almost similar to the useful signal. As such, traditional filtering methods are not applicable, especially in the case of strong background noise. In the present study, simultaneous acquisition was introduced, the principle of data deblending using CNN was analyzed, and a data deblending method based on an improved version of GoogLeNet was established. The experimental results show that the trained network model could quickly and effectively separate the mixed wavefield from blended data, and achieve the expected useful signal.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.