Development of a convolutional neural network based geomechanical upscaling technique for heterogeneous geological reservoir

Ma, Zhiwei; Ou, Xiaoyan; Zhang, Bo

doi:10.1016/j.jrmge.2024.02.009

Title: Development of a convolutional neural network based geomechanical upscaling technique for heterogeneous geological reservoir

Journal Article · 26 April 2024 · Journal of Rock Mechanics and Geotechnical Engineering

DOI: https://doi.org/10.1016/j.jrmge.2024.02.009 · OSTI ID:2346105

^[1]; Ou, Xiaoyan ^[2];

^[2]

Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Univ. of Alberta, Edmonton, AB (Canada)

Geomechanical assessment using coupled reservoir-geomechanical simulation is becoming increasingly important for analyzing the potential geomechanical risks in subsurface geological developments. However, a robust and efficient geomechanical upscaling technique for heterogeneous geological reservoirs is lacking to advance the applications of three-dimensional (3D) reservoir-scale geomechanical simulation considering detailed geological heterogeneities. Here, we develop convolutional neural network (CNN) proxies that reproduce the anisotropic nonlinear geomechanical response caused by lithological heterogeneity, and compute upscaled geomechanical properties from CNN proxies. The CNN proxies are trained using a large dataset of randomly generated spatially correlated sand-shale realizations as inputs and simulation results of their macroscopic geomechanical response as outputs. The trained CNN models can provide the upscaled shear strength (R²>0.949), stress-strain behavior (R²>0.925), and volumetric strain changes (R²>0.958) that highly agree with the numerical simulation results while saving over two orders of magnitude of computational time. This is a major advantage in computing the upscaled geomechanical properties directly from geological realizations without the need to perform local numerical simulations to obtain the geomechanical response. The proposed CNN proxy-based upscaling technique has the ability to (1) bridge the gap between the fine-scale geocellular models considering geological uncertainties and computationally efficient geomechanical models used to assess the geomechanical risks of large-scale subsurface development, and (2) improve the efficiency of numerical upscaling techniques that rely on local numerical simulations, leading to significantly increased computational time for uncertainty quantification using numerous geological realizations.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA); Natural Sciences and Engineering Research Council of Canada (NSERC)

Grant/Contract Number:: 89233218CNA000001

OSTI ID:: 2346105

Alternate ID(s):: OSTI ID: 2348958

Report Number(s):: LA-UR--24-21924

Journal Information:: Journal of Rock Mechanics and Geotechnical Engineering, Journal Name: Journal of Rock Mechanics and Geotechnical Engineering Journal Issue: 6 Vol. 16; ISSN 1674-7755

Publisher:: Chinese Society for Rock Mechanics and Engineering - ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (63)

Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning Qu, Tongming; Di, Shaocheng; Feng, Y. T. International Journal of Plasticity, Vol. 144 https://doi.org/10.1016/j.ijplas.2021.103046	journal	September 2021
Deep material network with cohesive layers: Multi-stage training and interfacial failure analysis Liu, Zeliang Computer Methods in Applied Mechanics and Engineering, Vol. 363 https://doi.org/10.1016/j.cma.2020.112913	journal	May 2020
Machine learning-based constitutive model for J2- plasticity Jang, Dong Phill; Fazily, Piemaan; Yoon, Jeong Whan International Journal of Plasticity, Vol. 138 https://doi.org/10.1016/j.ijplas.2020.102919	journal	March 2021
A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials Liu, Zeliang; Wu, C. T.; Koishi, M. Computer Methods in Applied Mechanics and Engineering, Vol. 345 https://doi.org/10.1016/j.cma.2018.09.020	journal	March 2019
Deep active learning for constitutive modelling of granular materials: From representative volume elements to implicit finite element modelling Qu, Tongming; Guan, Shaoheng; Feng, Y. T. International Journal of Plasticity, Vol. 164 https://doi.org/10.1016/j.ijplas.2023.103576	journal	May 2023
Stochastic upscaling in solid mechanics: An excercise in machine learning Koutsourelakis, P. S. Journal of Computational Physics, Vol. 226, Issue 1 https://doi.org/10.1016/j.jcp.2007.04.012	journal	September 2007
Neural Networks in Materials Science. Bhadeshia, H. K. D. H. ISIJ International, Vol. 39, Issue 10 https://doi.org/10.2355/isijinternational.39.966	journal	January 1999
Non-local multi-continua upscaling for flows in heterogeneous fractured media Chung, Eric T.; Efendiev, Yalchin; Leung, Wing Tat Journal of Computational Physics, Vol. 372 https://doi.org/10.1016/j.jcp.2018.05.038	journal	November 2018
FE2 multiscale approach for modelling the elastoviscoplastic behaviour of long fibre SiC/Ti composite materials Feyel, Frédéric; Chaboche, Jean-Louis Computer Methods in Applied Mechanics and Engineering, Vol. 183, Issue 3-4 https://doi.org/10.1016/S0045-7825(99)00224-8	journal	March 2000
Computational homogenization of nonlinear elastic materials using neural networks: NEURAL NETWORKS-BASED COMPUTATIONAL HOMOGENIZATION Le, B. A.; Yvonnet, J.; He, Q. -C. International Journal for Numerical Methods in Engineering, Vol. 104, Issue 12 https://doi.org/10.1002/nme.4953	journal	June 2015
A knowledge-based heterogeneity characterization framework for 3D steam-assisted gravity drainage reservoirs Ma, Zhiwei; Leung, Juliana Y. Knowledge-Based Systems, Vol. 192 https://doi.org/10.1016/j.knosys.2019.105327	journal	March 2020
ImageNet classification with deep convolutional neural networks Krizhevsky, Alex; Sutskever, Ilya; Hinton, Geoffrey E. Communications of the ACM, Vol. 60, Issue 6 https://doi.org/10.1145/3065386	journal	May 2017
A multilevel finite element method (FE2) to describe the response of highly non-linear structures using generalized continua Feyel, Frédéric Computer Methods in Applied Mechanics and Engineering, Vol. 192, Issue 28-30 https://doi.org/10.1016/S0045-7825(03)00348-7	journal	July 2003
A sequential indicator simulation program for categorical variables with point and block data: BlockSIS Deutsch, Clayton V. Computers & Geosciences, Vol. 32, Issue 10 https://doi.org/10.1016/j.cageo.2006.03.005	journal	December 2006
A micromechanical model of elastoplastic and damage behavior of a cohesive geomaterial Guéry, A. Abou-Chakra; Cormery, F.; Shao, J. F. International Journal of Solids and Structures, Vol. 45, Issue 5 https://doi.org/10.1016/j.ijsolstr.2007.09.025	journal	March 2008
Machine learning for accelerating macroscopic parameters prediction for poroelasticity problem in stochastic media Vasilyeva, Maria; Tyrylgin, Aleksey Computers & Mathematics with Applications, Vol. 84 https://doi.org/10.1016/j.camwa.2020.09.024	journal	February 2021
Predicting the mechanical response of oligocrystals with deep learning Frankel, A. L.; Jones, R. E.; Alleman, C. Computational Materials Science, Vol. 169 https://doi.org/10.1016/j.commatsci.2019.109099	journal	November 2019
Average stress in matrix and average elastic energy of materials with misfitting inclusions Mori, T.; Tanaka, K. Acta Metallurgica, Vol. 21, Issue 5 https://doi.org/10.1016/0001-6160(73)90064-3	journal	May 1973
Model-data-driven constitutive responses: Application to a multiscale computational framework Fuhg, Jan Niklas; Böhm, Christoph; Bouklas, Nikolaos International Journal of Engineering Science, Vol. 167 https://doi.org/10.1016/j.ijengsci.2021.103522	journal	October 2021
A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale features Krokos, Vasilis; Bui Xuan, Viet; Bordas, Stéphane P. A. Computational Mechanics, Vol. 69, Issue 3 https://doi.org/10.1007/s00466-021-02112-3	journal	November 2021
From CP-FFT to CP-RNN: Recurrent neural network surrogate model of crystal plasticity Bonatti, Colin; Berisha, Bekim; Mohr, Dirk International Journal of Plasticity, Vol. 158 https://doi.org/10.1016/j.ijplas.2022.103430	journal	November 2022
A new ANN based crystal plasticity model for FCC materials and its application to non-monotonic strain paths Ibragimova, Olga; Brahme, Abhijit; Muhammad, Waqas International Journal of Plasticity, Vol. 144 https://doi.org/10.1016/j.ijplas.2021.103059	journal	September 2021
A multiscale approach for modeling progressive damage of composite materials using fast Fourier transforms Spahn, J.; Andrä, H.; Kabel, M. Computer Methods in Applied Mechanics and Engineering, Vol. 268 https://doi.org/10.1016/j.cma.2013.10.017	journal	January 2014
Upscaling Shear Strength of Heterogeneous Oil Sands with Interbedded Shales Using Artificial Neural Network Zhang, Bo; Ma, Zhiwei; Zheng, Dongming SPE Journal, Vol. 28, Issue 02 https://doi.org/10.2118/208885-PA	journal	September 2022
Efficient tracking and estimation of solvent chamber development during warm solvent injection in heterogeneous reservoirs via machine learning Ma, Zhiwei; Leung, Juliana Y. Journal of Petroleum Science and Engineering, Vol. 206 https://doi.org/10.1016/j.petrol.2021.109089	journal	November 2021
Determination of an infill well placement using a data-driven multi-modal convolutional neural network Chu, Min-gon; Min, Baehyun; Kwon, Seoyoon Journal of Petroleum Science and Engineering, Vol. 195 https://doi.org/10.1016/j.petrol.2019.106805	journal	December 2020
Analytical and numerical analysis of frictional damage in quasi brittle materials Zhu, Q. Z.; Zhao, L. Y.; Shao, J. F. Journal of the Mechanics and Physics of Solids, Vol. 92 https://doi.org/10.1016/j.jmps.2016.04.002	journal	July 2016
Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network Ghavamian, F.; Simone, A. Computer Methods in Applied Mechanics and Engineering, Vol. 357 https://doi.org/10.1016/j.cma.2019.112594	journal	December 2019
Data-driven approach for dynamic homogenization using meta learning Shah, Aarohi; Rimoli, Julian J. Computer Methods in Applied Mechanics and Engineering, Vol. 401 https://doi.org/10.1016/j.cma.2022.115672	journal	November 2022
Finite strain FE2 analysis with data-driven homogenization using deep neural networks Feng, Nan; Zhang, Guodong; Khandelwal, Kapil Computers & Structures, Vol. 263 https://doi.org/10.1016/j.compstruc.2022.106742	journal	April 2022
Knowledge‐Based Modeling of Material Behavior with Neural Networks Ghaboussi, J.; Garrett, J. H.; Wu, X. Journal of Engineering Mechanics, Vol. 117, Issue 1 https://doi.org/10.1061/(ASCE)0733-9399(1991)117:1(132)	journal	January 1991
Smart constitutive laws: Inelastic homogenization through machine learning Logarzo, Hernan J.; Capuano, German; Rimoli, Julian J. Computer Methods in Applied Mechanics and Engineering, Vol. 373 https://doi.org/10.1016/j.cma.2020.113482	journal	January 2021
Continuum micro-mechanics of elastoplastic polycrystals Hill, R. Journal of the Mechanics and Physics of Solids, Vol. 13, Issue 2 https://doi.org/10.1016/0022-5096(65)90023-2	journal	April 1965
Deep CNNs as universal predictors of elasticity tensors in homogenization Eidel, Bernhard Computer Methods in Applied Mechanics and Engineering, Vol. 403 https://doi.org/10.1016/j.cma.2022.115741	journal	January 2023
Three-dimensional convolutional neural network (3D-CNN) for heterogeneous material homogenization Rao, Chengping; Liu, Yang Computational Materials Science, Vol. 184 https://doi.org/10.1016/j.commatsci.2020.109850	journal	November 2020
Learning macroscopic parameters in nonlinear multiscale simulations using nonlocal multicontinua upscaling techniques Vasilyeva, Maria; Leung, Wing T.; Chung, Eric T. Journal of Computational Physics, Vol. 412 https://doi.org/10.1016/j.jcp.2020.109323	journal	July 2020
Integration of deep learning and data analytics for SAGD temperature and production analysis Ma, Zhiwei; Leung, Juliana Y. Computational Geosciences, Vol. 24, Issue 3 https://doi.org/10.1007/s10596-020-09940-x	journal	January 2020
An overview of soil heterogeneity: quantification and implications on geotechnical field problems Elkateb, Tamer; Chalaturnyk, Rick; Robertson, Peter K. Canadian Geotechnical Journal, Vol. 40, Issue 1 https://doi.org/10.1139/t02-090	journal	February 2003
Generalized multiscale finite element methods (GMsFEM) Efendiev, Yalchin; Galvis, Juan; Hou, Thomas Y. Journal of Computational Physics, Vol. 251 https://doi.org/10.1016/j.jcp.2013.04.045	journal	October 2013
Multi-scale constitutive modelling of heterogeneous materials with a gradient-enhanced computational homogenization scheme Kouznetsova, V.; Geers, M. G. D.; Brekelmans, W. A. M. International Journal for Numerical Methods in Engineering, Vol. 54, Issue 8 https://doi.org/10.1002/nme.541	journal	January 2002
Generalised Mori-Tanaka Scheme to Model Anisotropic Damage Using Numerical Eshelby Tensor Desrumaux, F.; Meraghni, F.; Benzeggagh, M. L. Journal of Composite Materials, Vol. 35, Issue 7 https://doi.org/10.1177/002199801772662091	journal	April 2001
A micro–macro model for clayey rocks with a plastic compressible porous matrix Shen, W. Q.; Shao, J. F.; Kondo, D. International Journal of Plasticity, Vol. 36 https://doi.org/10.1016/j.ijplas.2012.03.006	journal	September 2012
Numerically explicit potentials for the homogenization of nonlinear elastic heterogeneous materials Yvonnet, J.; Gonzalez, D.; He, Q. -C. Computer Methods in Applied Mechanics and Engineering, Vol. 198, Issue 33-36 https://doi.org/10.1016/j.cma.2009.03.017	journal	July 2009
Numerical upscaling of anisotropic failure criteria in heterogeneous reservoirs Zhang, Bo; Deisman, Nathan; Chalaturnyk, Rick Engineering Geology, Vol. 331 https://doi.org/10.1016/j.enggeo.2024.107455	journal	March 2024
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
InversionNet: An Efficient and Accurate Data-Driven Full Waveform Inversion Wu, Yue; Lin, Youzuo IEEE Transactions on Computational Imaging, Vol. 6 https://doi.org/10.1109/TCI.2019.2956866	journal	January 2020
Exploring the 3D architectures of deep material network in data-driven multiscale mechanics Liu, Zeliang; Wu, C. T. Journal of the Mechanics and Physics of Solids, Vol. 127 https://doi.org/10.1016/j.jmps.2019.03.004	journal	June 2019
A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning Wang, Kun; Sun, WaiChing Computer Methods in Applied Mechanics and Engineering, Vol. 334 https://doi.org/10.1016/j.cma.2018.01.036	journal	June 2018
Constitutive modelling of idealised granular materials using machine learning method Wu, Mengmeng; Xia, Zhangqi; Wang, Jianfeng Journal of Rock Mechanics and Geotechnical Engineering, Vol. 15, Issue 4 https://doi.org/10.1016/j.jrmge.2022.08.002	journal	April 2023
Smart finite elements: A novel machine learning application Capuano, German; Rimoli, Julian J. Computer Methods in Applied Mechanics and Engineering, Vol. 345 https://doi.org/10.1016/j.cma.2018.10.046	journal	March 2019
Linked multicontinuum and crack tensor approach for modeling of coupled geomechanics, fluid flow and transport in fractured rock Rutqvist, Jonny; Leung, Colin; Hoch, Andrew Journal of Rock Mechanics and Geotechnical Engineering, Vol. 5, Issue 1 https://doi.org/10.1016/j.jrmge.2012.08.001	journal	February 2013
Geostatistical simulation to map the spatial heterogeneity of geomechanical parameters: A case study with rock mass rating Pinheiro, Marisa; Vallejos, Javier; Miranda, Tiago Engineering Geology, Vol. 205 https://doi.org/10.1016/j.enggeo.2016.03.003	journal	April 2016
Cell division in deep material networks applied to multiscale strain localization modeling Liu, Zeliang Computer Methods in Applied Mechanics and Engineering, Vol. 384 https://doi.org/10.1016/j.cma.2021.113914	journal	October 2021
Machine learning-enabled self-consistent parametrically-upscaled crystal plasticity model for Ni-based superalloys Weber, George; Pinz, Maxwell; Ghosh, Somnath Computer Methods in Applied Mechanics and Engineering, Vol. 402 https://doi.org/10.1016/j.cma.2022.115384	journal	December 2022
Coupling of scales in a multiscale simulation using neural networks Unger, Jörg F.; Könke, Carsten Computers & Structures, Vol. 86, Issue 21-22 https://doi.org/10.1016/j.compstruc.2008.05.004	journal	November 2008
Hydro-mechanical behavior of an argillaceous limestone considered as a potential host formation for radioactive waste disposal Nguyen, T. S.; Li, Zhenze; Su, Grant Journal of Rock Mechanics and Geotechnical Engineering, Vol. 10, Issue 6 https://doi.org/10.1016/j.jrmge.2018.03.010	journal	December 2018
Characterization of rock heterogeneity and numerical verification Liu, H. Y.; Roquete, M.; Kou, S. Q. Engineering Geology, Vol. 72, Issue 1-2 https://doi.org/10.1016/j.enggeo.2003.06.004	journal	March 2004
A numerical characterization workflow for assessing the strength and failure modes of heterogeneous oil sands Zhang, Bo; Chalaturnyk, Rick; Boisvert, Jeff Canadian Geotechnical Journal, Vol. 58, Issue 6 https://doi.org/10.1139/cgj-2020-0137	journal	June 2021
A micromechanical model for the elastic–plastic behavior of porous rocks Zeng, T.; Shao, J. F.; Xu, W. Y. Computers and Geotechnics, Vol. 70 https://doi.org/10.1016/j.compgeo.2015.08.001	journal	October 2015
A data-driven computational homogenization method based on neural networks for the nonlinear anisotropic electrical response of graphene/polymer nanocomposites Lu, Xiaoxin; Giovanis, Dimitris G.; Yvonnet, Julien Computational Mechanics, Vol. 64, Issue 2 https://doi.org/10.1007/s00466-018-1643-0	journal	October 2018
Local approximate Gaussian process regression for data-driven constitutive models: development and comparison with neural networks Fuhg, Jan N.; Marino, Michele; Bouklas, Nikolaos Computer Methods in Applied Mechanics and Engineering, Vol. 388 https://doi.org/10.1016/j.cma.2021.114217	journal	January 2022
Efficient and accurate two-scale FE-FFT-based prediction of the effective material behavior of elasto-viscoplastic polycrystals Kochmann, Julian; Wulfinghoff, Stephan; Ehle, Lisa Computational Mechanics, Vol. 61, Issue 6 https://doi.org/10.1007/s00466-017-1476-2	journal	September 2017
A Mori–Tanaka homogenization scheme for non-linear elasto-viscoplastic heterogeneous materials based on translated fields: An affine extension Berbenni, Stéphane; Capolungo, Laurent Comptes Rendus Mécanique, Vol. 343, Issue 2 https://doi.org/10.1016/j.crme.2014.12.003	journal	February 2015

Similar Records

Influence of local capillary trapping on containment system effectiveness

Technical Report · 2014 · OSTI ID:1179183

Bryant, Steven

North Dakota Integrated Carbon Storage Complex Feasibility Study. Final report

Technical Report · 2020 · OSTI ID:1606011

Peck, Wes D.; Azzolina, Nicholas A.; Nakles, Dave V.; +15 more

Experimental design applications for modeling and assessing carbon dioxide sequestration in saline aquifers

Technical Report · 2014 · OSTI ID:1167109

Rogers, John

Related Subjects

58 GEOSCIENCES
Upscaling
Lithological heterogeneity
Convolutional neural network (CNN)
Anisotropic shear strength
Nonlinear stress–strain behavior

Title: Development of a convolutional neural network based geomechanical upscaling technique for heterogeneous geological reservoir

Citation Formats

References (63)

Similar Records

Related Subjects