CO2 Storage Monitoring via Time-Lapse Full Waveform Inversion with Automatic Differentiation

被引:1
|
作者
Yang, Jixin [1 ,2 ]
Yu, Pengliang [1 ]
Wang, Suran [3 ]
Sun, Zheng [4 ]
机构
[1] Penn State Univ, Dept Geosci, University Pk, PA 16802 USA
[2] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[3] CNOOC Res Inst Co Ltd, Beijing 100028, Peoples R China
[4] China Univ Min & Technol, CUMT UCASAL Joint Res Ctr Biomin & Soil Ecol Resto, State Key Lab Coal Resources & Safe Min, Xuzhou 221116, Peoples R China
关键词
automatic differentiation; CO2 capture utilization and storage; time-lapse monitoring; full waveform inversion; deep learning tool; INJECTED CO2; PLUME;
D O I
10.3390/nano14020138
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
In the field of CO2 capture utilization and storage (CCUS), recent advancements in active-source monitoring have significantly enhanced the capabilities of time-lapse acoustical imaging, facilitating continuous capture of detailed physical parameter images from acoustic signals. Central to these advancements is time-lapse full waveform inversion (TLFWI), which is increasingly recognized for its ability to extract high-resolution images from active-source datasets. However, conventional TLFWI methodologies, which are reliant on gradient optimization, face a significant challenge due to the need for complex, explicit formulation of the physical model gradient relative to the misfit function between observed and predicted data over time. Addressing this limitation, our study introduces automatic differentiation (AD) into the TLFWI process, utilizing deep learning frameworks such as PyTorch to automate gradient calculation using the chain rule. This novel approach, AD-TLFWI, not only streamlines the inversion of time-lapse images for CO2 monitoring but also tackles the issue of local minima commonly encountered in deep learning optimizers. The effectiveness of AD-TLFWI was validated using a realistic model from the Frio-II CO2 injection site, where it successfully produced high-resolution images that demonstrate significant changes in velocity due to CO2 injection. This advancement in TLFWI methodology, underpinned by the integration of AD, represents a pivotal development in active-source monitoring systems, enhancing information extraction capabilities and providing potential solutions to complex multiphysics monitoring challenges.
引用
收藏
页数:10
相关论文
共 50 条
  • [21] Weighted-average time-lapse seismic full-waveform inversion
    Mardan A.
    Giroux B.
    Fabien-Ouellet G.
    Geophysics, 2022, 88 (01)
  • [22] Weighted-average time-lapse seismic full-waveform inversion
    Mardan, Amir
    Giroux, Bernard
    Fabien-Ouellet, Gabriel
    GEOPHYSICS, 2023, 88 (01) : R25 - R38
  • [23] Tuning effect in time-lapse seismic inversion for CO2 plume monitoring at Sleipner field
    Izadian, Saeed
    INTERNATIONAL JOURNAL OF GREENHOUSE GAS CONTROL, 2024, 137
  • [24] CO2 monitoring with time-lapse vertical seismic profile
    Zhao Hai-ying
    Chen Yuan-zhong
    Li Yan-peng
    Liu Guo-jun
    Li Tao
    Xia Shu-jun
    Fan Han-zhou
    ROCK AND SOIL MECHANICS, 2018, 39 (08) : 3095 - 3102
  • [25] Quantitative analysis of time-lapse seismic monitoring data at the Sleipner CO2 storage operation
    Chadwick A.
    Williams G.
    Delepine N.
    Clochard V.
    Labat K.
    Sturton S.
    Buddensiek M.-L.
    Dillen M.
    Nickel M.
    Lima A.L.
    Arts R.
    Neele F.
    Rossi G.
    Leading Edge (Tulsa, OK), 2010, 29 (02): : 170 - 177
  • [26] Source-independent time-lapse full-waveform inversion for VTI media
    Liu Y.
    Tsvankin I.
    Geophysics, 2021, 87 (01) : 1 - 51
  • [27] Source-independent time-lapse full-waveform inversion for anisotropic media
    Liu, Yanhua
    Tsvankin, Ilya
    GEOPHYSICS, 2022, 87 (01) : R110 - R122
  • [28] Full waveform inversion of repeating seismic events to estimate time-lapse velocity changes
    Kamei, R.
    Lumley, D.
    GEOPHYSICAL JOURNAL INTERNATIONAL, 2017, 209 (02) : 1239 - 1264
  • [29] Stochastic inversion method of time-lapse controlled source electromagnetic data for CO2 plume monitoring
    Ayani, Mohit
    Grana, Dario
    Liu, Mingliang
    INTERNATIONAL JOURNAL OF GREENHOUSE GAS CONTROL, 2020, 100 (100)
  • [30] Integrated kinematic time-lapse inversion workflow leveraging full-waveform inversion and machine learning
    Maharramov M.
    Willemsen B.
    Routh P.S.
    Peacock E.F.
    Froneberger M.
    Robinson A.P.
    Bear G.W.
    Lazaratos S.K.
    Leading Edge, 2019, 38 (12): : 943 - 948