Inversion-based multistage seismic data processing with physics-driven priors

被引:1
|
作者
Kumar R. [1 ]
Kamil Y. [1 ]
Bilsby P. [1 ]
Narayan A. [1 ]
Mahdad A. [2 ]
Brouwer W.G. [1 ]
Misbah A. [3 ]
Vassallo M. [2 ]
Zarkhidze A. [1 ]
Watterson P. [1 ]
机构
[1] SLB, Gatwick
[2] SLB, Houston, TX
[3] SLB, Cairo
来源
Leading Edge | 2023年 / 42卷 / 01期
关键词
We thank SLB for allowing us to publish this work. We also thank Robin Fletcher; Kemal Ozdemir; Robert Bloor; Courtney Anzalone; and Nigel Seymour at SLB Digital and Integration for their constructive feedback and suggestions that made this work possible;
D O I
10.1190/tle42010052.1
中图分类号
学科分类号
摘要
Various aspects of survey design have a profound impact on how noise appears on the coherent signal of interest, thus impacting conventional inversion methods in complex environments. We propose a multistage physics-driven prior-based processing technique that is versatile and can be used in a wide range of inversion-based processing applications such as source separation and/or interpolation for any acquisition environments (e.g., land, marine, and ocean-bottom nodes). The inversion-based multistage approach progressively builds the coherent signal model while eliminating the aliasing, blending, and background noise in a signal-safe manner. To stabilize the inversion process, we include physics-driven priors in the multiple stage process, which enhances the sparsity of the coherent signal in the transform domain. Results using real data from land and ocean-bottom node surveys validate the potential of the proposed approach to produce optimal processing results while dealing with the common geophysical challenges related to different seismic acquisitions. © 2023 Society of Exploration Geophysicists. All rights reserved.
引用
收藏
页码:52 / 60
页数:8
相关论文
共 50 条
  • [1] From seismic traces to reservoir properties: Physics-driven inversion
    Stanford University, Stanford, CA, United States
    不详
    Leading Edge, 2008, 4 (456-461):
  • [2] Physics-driven self-supervised learning system for seismic velocity inversion
    Liu, Bin
    Jiang, Peng
    Wang, Qingyang
    Ren, Yuxiao
    Yang, Senlin
    Cohn, Anthony G.
    GEOPHYSICS, 2023, 88 (02) : R145 - R161
  • [3] PHYSICS-DRIVEN PRIORS FOR IMPROVED SPATIAL MODELS AND AVERAGES
    Seshadri, Pranay
    Duncan, Andrew B.
    Thorne, George
    Vazquez, Raul
    PROCEEDINGS OF ASME TURBO EXPO 2023: TURBOMACHINERY TECHNICAL CONFERENCE AND EXPOSITION, GT2023, VOL 13D, 2023,
  • [4] Physics-driven deep-learning for marine CSEM data inversion
    Liang, Hao
    Gao, Ruoyun
    Yin, Changchun
    Su, Yang
    He, Zhanxiang
    Liu, Yunhe
    JOURNAL OF APPLIED GEOPHYSICS, 2024, 229
  • [5] Physics-Driven Deep Learning Inversion for Direct Current Resistivity Survey Data
    Liu, Bin
    Pang, Yonghao
    Jiang, Peng
    Liu, Zhengyu
    Liu, Benchao
    Zhang, Yongheng
    Cai, Yumei
    Liu, Jiawen
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61
  • [6] A Physics-Driven Deep Learning Network for Subsurface Inversion
    Jin, Yuchen
    Wu, Xuqing
    Chen, Jiefu
    Huang, Yueqin
    2019 UNITED STATES NATIONAL COMMITTEE OF URSI NATIONAL RADIO SCIENCE MEETING (USNC-URSI NRSM), 2019,
  • [7] Physics-Driven Neural Network for Interval Q Inversion
    Wang, Yonghao
    Cao, Wei
    Geng, Weiheng
    Jia, Zhuo
    Lu, Wenkai
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024, 62
  • [8] Physics-driven cycle network for seismic impedance inversion using conditional generative adversarial networks
    Wang, Yaojun
    Zong, Jingjing
    Wang, Liangji
    Zou, Bangli
    Chen, Ziteng
    Luo, Yang
    JOURNAL OF GEOPHYSICS AND ENGINEERING, 2023, 20 (06) : 1337 - 1347
  • [9] Physics-Driven Deep Learning Inversion with Application to Magnetotelluric
    Liu, Wei
    Wang, He
    Xi, Zhenzhu
    Zhang, Rongqing
    Huang, Xiaodi
    REMOTE SENSING, 2022, 14 (13)
  • [10] Data-driven inversion-based control of nonlinear systems
    Formentin, Simone
    Novara, Carlo
    Savaresi, Sergio M.
    Milanese, Mario
    IFAC PAPERSONLINE, 2015, 48 (28): : 1343 - 1348