A deep learning-accelerated data assimilation and forecasting workflow for commercial-scale geologic carbon storage

Tang, Hewei; Fu, Pengcheng; Sherman, Christopher S.; Zhang, Jize; Ju, Xin; Hamon, François; Azzolina, Nicholas A.; Burton-Kelly, Matthew; Morris, Joseph P.

doi:10.1016/j.ijggc.2021.103488

Title: A deep learning-accelerated data assimilation and forecasting workflow for commercial-scale geologic carbon storage

Journal Article · Sun Oct 10 00:00:00 EDT 2021 · International Journal of Greenhouse Gas Control

DOI:https://doi.org/10.1016/j.ijggc.2021.103488· OSTI ID:1844075

Tang, Hewei ^[1]; Fu, Pengcheng ^[1]; Sherman, Christopher S. ^[1]; Zhang, Jize ^[1]; Ju, Xin ^[1]; Hamon, François ^[2]; Azzolina, Nicholas A. ^[3]; Burton-Kelly, Matthew ^[3]; Morris, Joseph P. ^[1]

Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Total E&P Research and Technology, Houston, TX (United States)
Univ. of North Dakota, Grand Forks, ND (United States)

Fast assimilation of monitoring data to update forecasts of pressure buildup and carbon dioxide (CO₂) plume migration under geologic uncertainties is a challenging problem in geologic carbon storage. The high computational cost of data assimilation with a high-dimensional parameter space impedes fast decision-making for commercial-scale reservoir management. We propose to leverage physical understandings of porous medium flow behavior with deep learning techniques to develop a fast data assimilation-reservoir response forecasting workflow. Applying an Ensemble Smoother Multiple Data Assimilation (ES-MDA) framework, the workflow updates geologic properties and predicts reservoir performance with quantified uncertainty from pressure history and CO₂ plumes interpreted through seismic inversion. As the most computationally expensive component in such a workflow is reservoir simulation, we developed surrogate models to predict dynamic pressure and CO₂ plume extents under multi-well injection. The surrogate models employ deep convolutional neural networks, specifically, a wide residual network and a residual U-Net. The workflow is validated against a flat threedimensional reservoir model representative of a clastic shelf depositional environment. Intelligent treatments are applied to bridge between quantities in a true-3D reservoir model and those in a single-layer reservoir model. The workflow can complete history matching and reservoir forecasting with uncertainty quantification in less than one hour on a mainstream personal workstation.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: AC52-07NA27344

OSTI ID:: 1844075

Report Number(s):: LLNL-JRNL-822252; 1034152

Journal Information:: International Journal of Greenhouse Gas Control, Vol. 112; ISSN 1750-5836

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (46)

Fractals and Chaos in Geology and Geophysics Turcotte, Donald L.; Brown, Stephen R. Physics Today, Vol. 46, Issue 5 https://doi.org/10.1063/1.2808908	journal	May 1993
Bayesian deep convolutional encoder–decoder networks for surrogate modeling and uncertainty quantification Zhu, Yinhao; Zabaras, Nicholas Journal of Computational Physics, Vol. 366 https://doi.org/10.1016/j.jcp.2018.04.018	journal	August 2018
Training‐Image Based Geostatistical Inversion Using a Spatial Generative Adversarial Neural Network Laloy, Eric; Hérault, Romain; Jacques, Diederik Water Resources Research, Vol. 54, Issue 1 https://doi.org/10.1002/2017WR022148	journal	January 2018
CO2 Sequestration in Deep Sedimentary Formations Benson, S. M.; Cole, D. R. Elements, Vol. 4, Issue 5 https://doi.org/10.2113/gselements.4.5.325	journal	October 2008
Towards a predictor for CO2 plume migration using deep neural networks Wen, Gege; Tang, Meng; Benson, Sally M. International Journal of Greenhouse Gas Control, Vol. 105 https://doi.org/10.1016/j.ijggc.2020.103223	journal	February 2021
A Deep-Learning-Based Geological Parameterization for History Matching Complex Models Liu, Yimin; Sun, Wenyue; Durlofsky, Louis J. Mathematical Geosciences, Vol. 51, Issue 6 https://doi.org/10.1007/s11004-019-09794-9	journal	March 2019
A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems Tang, Meng; Liu, Yimin; Durlofsky, Louis J. Journal of Computational Physics, Vol. 413 https://doi.org/10.1016/j.jcp.2020.109456	journal	July 2020
Quantifying the effects of depositional environment on deep saline formation co2 storage efficiency and rate Bosshart, Nicholas W.; Azzolina, Nicholas A.; Ayash, Scott C. International Journal of Greenhouse Gas Control, Vol. 69 https://doi.org/10.1016/j.ijggc.2017.12.006	journal	February 2018
Revising the stochastic iterative ensemble smoother Raanes, Patrick Nima; Stordal, Andreas Størksen; Evensen, Geir Nonlinear Processes in Geophysics, Vol. 26, Issue 3 https://doi.org/10.5194/npg-26-325-2019	journal	January 2019
Storage of CO2 in saline aquifers–Lessons learned from 10 years of injection into the Utsira Formation in the Sleipner area Hermanrud, Christian; Andresen, Terje; Eiken, Ola Energy Procedia, Vol. 1, Issue 1 https://doi.org/10.1016/j.egypro.2009.01.260	journal	February 2009
Image Quality Assessment: From Error Visibility to Structural Similarity Wang, Z.; Bovik, A. C.; Sheikh, H. R. IEEE Transactions on Image Processing, Vol. 13, Issue 4 https://doi.org/10.1109/TIP.2003.819861	journal	April 2004
Kernel Principal Component Analysis for Efficient, Differentiable Parameterization of Multipoint Geostatistics Sarma, Pallav; Durlofsky, Louis J.; Aziz, Khalid Mathematical Geosciences, Vol. 40, Issue 1 https://doi.org/10.1007/s11004-007-9131-7	journal	December 2007
Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow Tang, Meng; Liu, Yimin; Durlofsky, Louis J. Computer Methods in Applied Mechanics and Engineering, Vol. 376 https://doi.org/10.1016/j.cma.2020.113636	journal	April 2021
Ensemble smoother with multiple data assimilation Emerick, Alexandre A.; Reynolds, Albert C. Computers & Geosciences, Vol. 55 https://doi.org/10.1016/j.cageo.2012.03.011	journal	June 2013
Uncertainty quantification and value of information assessment using proxies and Markov chain Monte Carlo method for a pilot project Chen, Bailian; He, Jincong; Wen, Xian-Huan Journal of Petroleum Science and Engineering, Vol. 157 https://doi.org/10.1016/j.petrol.2017.07.039	journal	August 2017
An improved model calculating CO2 solubility in pure water and aqueous NaCl solutions from 273 to 533 K and from 0 to 2000 bar Duan, Zhenhao; Sun, Rui Chemical Geology, Vol. 193, Issue 3-4 https://doi.org/10.1016/S0009-2541(02)00263-2	journal	February 2003
Characterization of flow and transport in a fracture network at the EGS Collab field experiment through stochastic modeling of tracer recovery Wu, Hui; Fu, Pengcheng; Morris, Joseph P. Journal of Hydrology, Vol. 593 https://doi.org/10.1016/j.jhydrol.2020.125888	journal	February 2021
Geological storage of CO2 in saline aquifers—A review of the experience from existing storage operations Michael, K.; Golab, A.; Shulakova, V. International Journal of Greenhouse Gas Control, Vol. 4, Issue 4 https://doi.org/10.1016/j.ijggc.2009.12.011	journal	July 2010
Reducing uncertainty in geologic CO2 sequestration risk assessment by assimilating monitoring data Chen, Bailian; Harp, Dylan R.; Lu, Zhiming International Journal of Greenhouse Gas Control, Vol. 94 https://doi.org/10.1016/j.ijggc.2019.102926	journal	March 2020
Markov chain Monte Carlo simulation using the DREAM software package: Theory, concepts, and MATLAB implementation Vrugt, Jasper A. Environmental Modelling & Software, Vol. 75 https://doi.org/10.1016/j.envsoft.2015.08.013	journal	January 2016
Hydrogeophysical Characterization of Nonstationary DNAPL Source Zones by Integrating a Convolutional Variational Autoencoder and Ensemble Smoother Kang, Xueyuan; Kokkinaki, Amalia; Kitanidis, Peter K. Water Resources Research, Vol. 57, Issue 2 https://doi.org/10.1029/2020WR028538	journal	February 2021
Petrophysical characterization of deep saline aquifers for CO2 storage using ensemble smoother and deep convolutional autoencoder Liu, Mingliang; Grana, Dario Advances in Water Resources, Vol. 142 https://doi.org/10.1016/j.advwatres.2020.103634	journal	August 2020
A New Differentiable Parameterization Based on Principal Component Analysis for the Low-Dimensional Representation of Complex Geological Models Vo, Hai X.; Durlofsky, Louis J. Mathematical Geosciences, Vol. 46, Issue 7 https://doi.org/10.1007/s11004-014-9541-2	journal	July 2014
Recent progress on reservoir history matching: a review Oliver, Dean S.; Chen, Yan Computational Geosciences, Vol. 15, Issue 1 https://doi.org/10.1007/s10596-010-9194-2	journal	July 2010
Integration of microseismic monitoring data into coupled flow and geomechanical models with ensemble Kalman filter Tarrahi, Mohammadali; Jafarpour, Behnam; Ghassemi, Ahmad Water Resources Research, Vol. 51, Issue 7 https://doi.org/10.1002/2014WR016264	journal	July 2015
Semiempirical correlation for Henry's constants over large temperature ranges Harvey, Allan H. AIChE Journal, Vol. 42, Issue 5 https://doi.org/10.1002/aic.690420531	journal	May 1996
Estimating Channelized-Reservoir Permeabilities With the Ensemble Kalman Filter: The Importance of Ensemble Design Jafarpour, Behnam; McLaughlin, Dennis B. SPE Journal, Vol. 14, Issue 02 https://doi.org/10.2118/108941-PA	journal	June 2009
A New Two-Constant Equation of State Peng, Ding-Yu; Robinson, Donald B. Industrial & Engineering Chemistry Fundamentals, Vol. 15, Issue 1 https://doi.org/10.1021/i160057a011	journal	February 1976
Regularized kernel PCA for the efficient parameterization of complex geological models Vo, Hai X.; Durlofsky, Louis J. Journal of Computational Physics, Vol. 322 https://doi.org/10.1016/j.jcp.2016.07.011	journal	October 2016
Fractal heterogeneities in sonic logs and low-frequency scattering attenuation Browaeys, Thomas J.; Fomel, Sergey GEOPHYSICS, Vol. 74, Issue 2 https://doi.org/10.1190/1.3062859	journal	March 2009
Assessment of the Limitations on the Seismic Detectability of Injected CO2 within a Deep Geological Reservoir Roach, Lisa A. N.; Angus, Doug A.; White, Don J. Energy Procedia, Vol. 114 https://doi.org/10.1016/j.egypro.2017.03.1541	journal	July 2017
Integrated hydrogeophysical modelling and data assimilation for geoelectrical leak detection Tso, Chak-Hau Michael; Johnson, Tim C.; Song, Xuehang Journal of Contaminant Hydrology, Vol. 234 https://doi.org/10.1016/j.jconhyd.2020.103679	journal	October 2020
Reservoir rock chemo-mechanical alteration quantified by triaxial tests and implications to fracture reactivation Sun, Zhuang; Espinoza, D. Nicolas; Balhoff, Matthew T. International Journal of Rock Mechanics and Mining Sciences, Vol. 106 https://doi.org/10.1016/j.ijrmms.2018.04.004	journal	June 2018
The effects of near-source heterogeneity on shear-wave evolution Sherman, Christopher S.; Rector, James; Glaser, Steven GEOPHYSICS, Vol. 79, Issue 4 https://doi.org/10.1190/geo2013-0199.1	journal	July 2014
Automatic and adaptive localization for ensemble-based history matching Luo, Xiaodong; Bhakta, Tuhin Journal of Petroleum Science and Engineering, Vol. 184 https://doi.org/10.1016/j.petrol.2019.106559	journal	January 2020
An Improved Method for Calculating Water Influx Carter, R. D.; Tracy, G. W. Transactions of the AIME, Vol. 219, Issue 01 https://doi.org/10.2118/1626-G	journal	December 1960
Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network Laloy, Eric; Hérault, Romain; Lee, John Advances in Water Resources, Vol. 110 https://doi.org/10.1016/j.advwatres.2017.09.029	journal	December 2017
Simultaneous assimilation of production and seismic data: application to the Norne field Lorentzen, Rolf J.; Bhakta, Tuhin; Grana, Dario Computational Geosciences, Vol. 24, Issue 2 https://doi.org/10.1007/s10596-019-09900-0	journal	November 2019
Machine learning assisted history matching for a deepwater lobe system Jo, Honggeun; Pan, Wen; Santos, Javier E. Journal of Petroleum Science and Engineering, Vol. 207 https://doi.org/10.1016/j.petrol.2021.109086	journal	December 2021
Time-lapse seismic history matching with an iterative ensemble smoother and deep convolutional autoencoder Liu, Mingliang; Grana, Dario GEOPHYSICS, Vol. 85, Issue 1 https://doi.org/10.1190/geo2019-0019.1	journal	January 2020
Benchmark Calibration and Prediction of the Sleipner CO2 Plume from 2006 to 2012 Cavanagh, Andrew Energy Procedia, Vol. 37 https://doi.org/10.1016/j.egypro.2013.06.246	journal	January 2013
4D seismic history matching Oliver, Dean S.; Fossum, Kristian; Bhakta, Tuhin Journal of Petroleum Science and Engineering, Vol. 207 https://doi.org/10.1016/j.petrol.2021.109119	journal	December 2021
A Characterization of Starshaped Sets Chan Stanek, Jean Canadian Journal of Mathematics, Vol. 29, Issue 4 https://doi.org/10.4153/CJM-1977-070-2	journal	August 1977
Dynamic characterization of geologic CO2 storage aquifers from monitoring data with ensemble Kalman filter Ma, Wei; Jafarpour, Behnam; Qin, Joe International Journal of Greenhouse Gas Control, Vol. 81 https://doi.org/10.1016/j.ijggc.2018.10.009	journal	February 2019
CO2 charged brines changed rock strength and stiffness at Crystal Geyser, Utah: Implications for leaking subsurface CO2 storage reservoirs Espinoza, D. Nicolas; Jung, Hojung; Major, Jonathan R. International Journal of Greenhouse Gas Control, Vol. 73 https://doi.org/10.1016/j.ijggc.2018.03.017	journal	June 2018
Deep Convolutional Encoder‐Decoder Networks for Uncertainty Quantification of Dynamic Multiphase Flow in Heterogeneous Media Mo, Shaoxing; Zhu, Yinhao; Zabaras, Nicholas Water Resources Research, Vol. 55, Issue 1 https://doi.org/10.1029/2018WR023528	journal	January 2019

Similar Records

Deep learning-accelerated 3D carbon storage reservoir pressure forecasting based on data assimilation using surface displacement from InSAR

Journal Article · Fri Sep 02 00:00:00 EDT 2022 · International Journal of Greenhouse Gas Control · OSTI ID:1844075

Tang, Hewei; Fu, Pengcheng; Jo, Honggeun; +5 more

Reducing Uncertainty in Geologic CO₂ Sequestration Risk Assessment by Assimilating Monitoring Data

Journal Article · Wed Dec 04 00:00:00 EST 2019 · International Journal of Greenhouse Gas Control · OSTI ID:1844075

Chen, Bailian; Harp, Dylan Robert; Lu, Zhiming; +1 more

Robust Carbon Dioxide Plume Imaging Using Joint Tomographic Inversion of Seismic Onset Time and Distributed Pressure and Temperature Measurements (Final Report)

Technical Report · Fri Mar 25 00:00:00 EDT 2022 · OSTI ID:1844075

Datta-Gupta, Akhil; Mishra, Srikanta

Related Subjects

25 ENERGY STORAGE
Deep learning
Data assimilation
Geologic carbon storage
Ensemble-based methods
Surrogate modeling

Title: A deep learning-accelerated data assimilation and forecasting workflow for commercial-scale geologic carbon storage

Citation Formats

References (46)

Similar Records

Related Subjects