Advances in Intelligent Prediction of the Percolation Properties of Digital Rocks

Liang Jianxun; Jia Ninghong; Lü Weifeng; Zhang Qing; Xie Chiyu

doi:10.21656/1000-0887.460219

Volume 47 Issue 7

Jul. 2026

Turn off MathJax

Article Contents

Article Navigation > Applied Mathematics and Mechanics > 2026 > 47(7): 825-844

Liang Jianxun, Jia Ninghong, Lü Weifeng, Zhang Qing, Xie Chiyu. Advances in Intelligent Prediction of the Percolation Properties of Digital Rocks[J]. Applied Mathematics and Mechanics, 2026, 47(7): 825-844. doi: 10.21656/1000-0887.460219

Citation:

PDF( 2743 KB)

Advances in Intelligent Prediction of the Percolation Properties of Digital Rocks

doi: 10.21656/1000-0887.460219

Liang Jianxun^{1, 2, 3
,},
Jia Ninghong^{2, 3, 4
,
,},
Lü Weifeng^{2, 3, 4},
Zhang Qing^{3, 4},
Xie Chiyu^{5
,
,}

1.
University of Chinese Academy of Sciences, Beijing 100049, P.R. China
2.
Institute of Porous Flow & Fluid Mechanics, Chinese Academy of Sciences, Langfang, Hebei 065007, P.R. China
3.
State Key Laboratory of Enhanced Oil and Gas Recovery, Beijing 100083, P.R. China
4.
Research Institute of Petroleum Exploration and Development, PetroChina, Beijing 100083, P.R. China
5.
School of Astronautics, Beihang University, Beijing 100191, P.R. China

Received Date: 2025-12-02
Rev Recd Date: 2025-12-24
Publish Date: 2026-07-01

Abstract

Abstract

Core analysis is the cornerstone of reservoir evaluation. The digital rock physics (DRP) enables the quantitative characterization of reservoir microstructures and flow properties through 3D imaging and numerical simulation. The evolution of DRP paradigms was reviewed from the 1st-generation "What you see is what you get" (geometric characterization) and the 2nd-generation "What you calculate is what you get" (numerical simulation), to the emerging 3rd-generation "What you learn is what you get" (intelligent prediction). The 1st 2 paradigms face 2 core bottlenecks: the difficulty in determining the representative elementary volume (REV) and the prohibitive computational costs of numerical simulations. The progress of the 3rd-generation intelligent prediction paradigm was systematically summarized, with the focus on structural properties, single-phase permeability, and multiphase flow properties (relative permeability, capillary pressure, and wettability). Centered on deep learning, this paradigm offers revolutionary pathways to overcome traditional limitations: on one hand, the generative adversarial networks (GANs) and the super-resolution (SR) techniques were employed for data-driven reconstruction to mitigate REV challenges; on the other hand, the efficient surrogate models, such as the convolutional neural networks (CNNs), were constructed to accelerate property prediction by orders of magnitude. Finally, the current challenges regarding data dependence, model generalization, and physical interpretability were discussed to outlines future directions, including integrating physical mechanisms into AI models (physics-informed AI), promoting multi-scale data fusion, and constructing reservoir "digital twins" to support the development of smart oilfields.
- digital core,
- artificial intelligence,
- deep learning,
- percolation properties,
- parameter prediction

(Contributed by Xie Chiyu, Member of the Youth Editorial Board of AMM)

FullText(HTML)

References(134)

References

[1]	Wu P, Dong Z, Liu S, et al. Microstructure and physical properties of hydrate-bearing sediment: digital core and deep learning application[J]. Fuel, 2026, 404: 136283. doi: 10.1016/j.fuel.2025.136283
[2]	Fan W, Yu H, He S, et al. Micro-scale two-phase flow experiments and residual oil distribution in tight sandstone[J]. Natural Resources Research, 2025, 34(6): 3179-3192. doi: 10.1007/s11053-025-10539-1
[3]	Bera A, Shukla B, Jogani D. A perspective review of applications of the computed tomography (CT) scan imaging technique for microscopic reservoir rock characterization[J]. Deep Underground Science and Engineering, 2026, 5(1): 4-27. doi: 10.1002/dug2.12138
[4]	Andrä H, Combaret N, Dvorkin J, et al. Digital rock physics benchmarks, part Ⅰ: imaging and segmentation[J]. Computers & Geosciences, 2013, 50: 25-32.
[5]	Cnudde V, Boone M N. High-resolution X-ray computed tomography in geosciences: a review of the current technology and applications[J]. Earth-Science Reviews, 2013, 123: 1-17.
[6]	Ying D W, Blunt M J, Armstrong R T, et al. Deep learning in pore scale imaging and modeling[J]. Earth-Science Reviews, 2021, 215: 103555. doi: 10.1016/j.earscirev.2021.103555
[7]	Pu Z, Tian Y, Fu J, et al. Stress-sensitive porosity and permeability in carbonate rocks for underground hydrogen storage: a digital rock simulation study[J]. International Journal of Coal Science & Technology, 2025, 12: 55.
[8]	Su X, Han D, Wu F, et al. Evaluation of sealing and permeability reduction during coal seam grouting based on computed tomography imaging technique[J]. Gas Science and Engineering, 2025, 143: 205736. doi: 10.1016/j.jgsce.2025.205736
[9]	Ma S, Liu J, Wang Z, et al. An improved method for pore size distribution measurement of porous geomaterials based on microscopic images[J]. Computers & Geosciences, 2025, 205: 106017.
[10]	Ugolkov E, He X, Kwak H, et al. Super-resolution of 3D micro-CT images using generative adversarial networks: enhancing resolution and segmentation accuracy[J]. Computers & Geosciences, 2025, 205: 106018.
[11]	Li P, Song Y, Jiang J, et al. Pore-scale simulation of oil-water flow in shale media after fracture hits: an integrated approach using U-Net and lattice Boltzmann method[J]. Fuel, 2025, 402: 136038. doi: 10.1016/j.fuel.2025.136038
[12]	Yu H, Xu H, Fan J, et al. Transport of shale gas in microporous/nanoporous media: molecular to pore-scale simulations[J]. Energy & Fuels, 2021, 35(2): 911-943.
[13]	龚文波, 陈志强, 郑江韬, 等. 页岩油孔隙微纳渗流的格子Boltzmann方法模拟[J]. 力学学报, 2025, 57(12): 2802-2813. Gong Wenbo, Chen Zhiqiang, Zheng Jiangtao, et al. Pore-scale simulation of shale oil flow in nanoporous media using lattice Boltzmann method[J]. Chinese Journal of Theoretical and Applied Mechanics, 2025, 57(12): 2802-2813. (in Chinese)
[14]	Moghadasi R, Foroughi S, Goodarzi S, et al. Trapping and remobilization during geological CO₂ storage: a pore-scale imaging and modeling study[J]. Advances in Water Resources, 2025, 205: 105092. doi: 10.1016/j.advwatres.2025.105092
[15]	Wang Q, Wang H, Wang X, et al. Numerical simulation study on microseepage and displacement mechanism of coal based on digital core technology[J]. Physics of Fluids, 2025, 37(9): 096610. doi: 10.1063/5.0281372
[16]	Hashemi L, Blunt M, Hajibeygi H. Pore-scale modelling and sensitivity analyses of hydrogen-brine multiphase flow in geological porous media[J]. Scientific Reports, 2021, 11: 8348. doi: 10.1038/s41598-021-87490-7
[17]	Blunt M J, Jackson M D, Piri M, et al. Detailed physics, predictive capabilities and macroscopic consequences for pore-network models of multiphase flow[J]. Advances in Water Resources, 2002, 25(8/9/10/11/12): 1069-1089.
[18]	Chen L, He A, Zhao J, et al. Pore-scale modeling of complex transport phenomena in porous media[J]. Progress in Energy and Combustion Science, 2022, 88: 100968. doi: 10.1016/j.pecs.2021.100968
[19]	Joekar-Niasar V, Hassanizadeh S M. Analysis of fundamentals of two-phase flow in porous media using dynamic pore-network models: a review[J]. Critical Reviews in Environmental Science and Technology, 2012, 42(18): 1895-1976. doi: 10.1080/10643389.2011.574101
[20]	Tian J, Qi C, Sun Y, et al. Permeability prediction of porous media using a combination of computational fluid dynamics and hybrid machine learning methods[J]. Engineering With Computers, 2021, 37(4): 3455-3471. doi: 10.1007/s00366-020-01012-z
[21]	Blunt M J. Flow in porous media: pore-network models and multiphase flow[J]. Current Opinion in Colloid & Interface Science, 2001, 6(3): 197-207.
[22]	Chen S, Doolen G D. Lattice Boltzmann method for fluid flows[J]. Annual Review of Fluid Mechanics, 1998, 30: 329-364. doi: 10.1146/annurev.fluid.30.1.329
[23]	Alqahtani N, Alzubaidi F, Armstrong R T, et al. Machine learning for predicting properties of porous media from 2D X-ray images[J]. Journal of Petroleum Science and Engineering, 2020, 184: 106514. doi: 10.1016/j.petrol.2019.106514
[24]	Santos J E, Xu D, Jo H, et al. PoreFlow-Net: a 3D convolutional neural network to predict fluid flow through porous media[J]. Advances in Water Resources, 2020, 138: 103539. doi: 10.1016/j.advwatres.2020.103539
[25]	刘合, 任义丽, 李欣, 等. 岩心智能识别技术内涵与展望[J]. 石油学报, 2024, 45(8): 1296-1308. Liu He, Ren Yili, Li Xin, et al. The essence and prospects of intelligent core identification technology[J]. Acta Petrolei Sinica, 2024, 45(8): 1296-1308. (in Chinese)
[26]	Iwai H, Shikazono N, Matsui T, et al. Quantification of SOFC anode microstructure based on dual beam FIB-SEM technique[J]. Journal of Power Sources, 2010, 195(4): 955-961. doi: 10.1016/j.jpowsour.2009.09.005
[27]	Lozano F A, Juliao-Lemus T, Pérez E R, et al. Review of microscopic techniques for digital rock models[J]. Boletin de Geologia, 2022, 44(1): 161-171.
[28]	Mostaghimi P, Blunt M J, Bijeljic B. Computations of absolute permeability on micro-CT images[J]. Mathematical Geosciences, 2013, 45(1): 103-125. doi: 10.1007/s11004-012-9431-4
[29]	Kang Q, Li K Q, Fu J L, et al. Hybrid LBM and machine learning algorithms for permeability prediction of porous media: a comparative study[J]. Computers and Geotechnics, 2024, 168: 106163. doi: 10.1016/j.compgeo.2024.106163
[30]	Wu J, Yin X, Xiao H. Seeing permeability from images: fast prediction with convolutional neural networks[J]. Science Bulletin, 2018, 63(18): 1215-1222. doi: 10.1016/j.scib.2018.08.006
[31]	Kazemi A, Esmaeili M. Enhancing permeability prediction from digital rock images using generative AI and transfer learning[J]. Gas Science and Engineering, 2025, 144: 205751. doi: 10.1016/j.jgsce.2025.205751
[32]	Dong C, Loy C C, He K, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(2): 295-307. doi: 10.1109/TPAMI.2015.2439281
[33]	Xie H, Jiang P, Xu R. A deep learning-based hybrid-coupled multiscale modeling framework for real-time flow field prediction in porous media[J]. Physics of Fluids, 2025, 37(8): 083143. doi: 10.1063/5.0289039
[34]	Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks[J]. Communications of the ACM, 2020, 63(11): 139-144. doi: 10.1145/3422622
[35]	Liu M, Mukerji T. Multiscale fusion of digital rock images based on deep generative adversarial networks[J]. Geophysical Research Letters, 2022, 49(9). DOI: 10.1029/2022GL098342.
[36]	Sudakov O, Burnaev E, Koroteev D. Driving digital rock towards machine learning: predicting permeability with gradient boosting and deep neural networks[J]. Computers & Geosciences, 2019, 127: 91-98.
[37]	Lavrukhin E V, Gerke K M, Romanenko K A, et al. Assessing the fidelity of neural network-based segmentation of soil XCT images based on pore-scale modelling of saturated flow properties[J]. Soil and Tillage Research, 2021, 209: 104942. doi: 10.1016/j.still.2021.104942
[38]	Yan T, Xu X, Liu J, et al. Data-driven predictive model of coal permeability based on microscopic fracture structure characterization[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2025, 17(7): 4476-4489. doi: 10.1016/j.jrmge.2024.11.056
[39]	Saxena N, Day-Stirrat R J, Hows A, et al. Application of deep learning for semantic segmentation of sandstone thin sections[J]. Computers & Geosciences, 2021, 152: 104778.
[40]	Caja M A, Castillo J N, Santos C A, et al. Digital rock physics in cuttings using high-resolution thin section scan images[J]. Minerals, 2023, 13(9): 1140. doi: 10.3390/min13091140
[41]	Chen L C, Papandreou G, Kokkinos I, et al. Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848. doi: 10.1109/TPAMI.2017.2699184
[42]	Chauhan S, Rühaak W, Khan F, et al. Processing of rock core microtomography images: using seven different machine learning algorithms[J]. Computers & Geosciences, 2016, 86: 120-128.
[43]	Esmaeili B, Hosseinzadeh S, Kadkhodaie A, et al. Simulating reservoir capillary pressure curves using image processing and classification machine learning algorithms applied to petrographic thin sections[J]. Journal of African Earth Sciences, 2024, 209: 105098. doi: 10.1016/j.jafrearsci.2023.105098
[44]	Niu Y, Mostaghimi P, Shabaninejad M, et al. Digital rock segmentation for petrophysical analysis with reduced user bias using convolutional neural networks[J]. Water Resources Research, 2020, 56(2): e2019WR026597. doi: 10.1029/2019WR026597
[45]	Blunt M J, Bijeljic B, Dong H, et al. Pore-scale imaging and modelling[J]. Advances in Water Resources, 2013, 51: 197-216. doi: 10.1016/j.advwatres.2012.03.003
[46]	Chorin A J. Numerical solution of the Navier-Stokes equations[J]. Mathematics of Computation, 1968, 22(104): 745-762. doi: 10.1090/S0025-5718-1968-0242392-2
[47]	Saxena N, Hofmann R, Alpak F O, et al. References and benchmarks for pore-scale flow simulated using micro-CT images of porous media and digital rocks[J]. Advances in Water Resources, 2017, 109: 211-235. doi: 10.1016/j.advwatres.2017.09.007
[48]	Liu H, Kang Q, Leonardi C R, et al. Multiphase lattice Boltzmann simulations for porous media applications: a review[J]. Computational Geosciences, 2016, 20(4): 777-805. doi: 10.1007/s10596-015-9542-3
[49]	Wang L, Wang S, Zhang R, et al. Review of multi-scale and multi-physical simulation technologies for shale and tight gasreservoirs[J]. Journal of Natural Gas Science and Engineering, 2017, 37: 560-578. doi: 10.1016/j.jngse.2016.11.051
[50]	朱伯靖, 石耀霖. 波尔兹曼数字岩芯致密砂岩渗透率研究[J]. 力学学报, 2013, 45(3): 384-394. Zhu Bojing, Shi Yaolin. Study of tight sandstone permeability from lattice Boltzmann & digital rock model[J]. Chinese Journal of Theoretical and Applied Mechanics, 2013, 45(3): 384-394. (in Chinese)
[51]	Chen L, Zhang L, Kang Q, et al. Nanoscale simulation of shale transport properties using the lattice Boltzmann method: permeability and diffusivity[J]. Scientific Reports, 2015, 5: 8089. doi: 10.1038/srep08089
[52]	Zhao J, Yao J, Zhang M, et al. Study of gas flow characteristics in tight porous media with a microscale lattice Boltzmann model[J]. Scientific Reports, 2016, 6: 32393. doi: 10.1038/srep32393
[53]	Zhao W, Jia C, Song Y, et al. Hydrocarbon migration and accumulation simulation: a review and a novel multi-scale quantitative numerical simulation method[J]. Advances in Colloid and Interface Science, 2025, 342: 103523. doi: 10.1016/j.cis.2025.103523
[54]	Zhao J, Kang Q, Yao J, et al. The effect of wettability heterogeneity on relative permeability of two-phase flow in porous media: a lattice Boltzmann study[J]. Water Resources Research, 2018, 54(2): 1295-1311. doi: 10.1002/2017WR021443
[55]	陈家豪, 娄钦. 考虑接触角滞后性多孔介质内非混相驱替研究[J]. 应用数学和力学, 2021, 42(9): 900-914. Chen Jiahao, Lou Qin. An investigation on the immiscible displacement in porous media with contact angle hysteresis[J]. Applied Mathematics and Mechanics, 2021, 42(9): 900-914. (in Chinese)
[56]	Liu T, Zhang S, Wang M. Does rheology of Bingham fluid influence upscaling of flow through tight porous media?[J]. Energies, 2021, 14(3): 680. doi: 10.3390/en14030680
[57]	丁弘毅, 王治云, 赵敬帅, 等. 含孔板微通道内随流气泡运动的两相格子Boltzmann模拟[J]. 应用数学和力学, 2024, 45(1): 97-109. Ding Hongyi, Wang Zhiyun, Zhao Jingshuai, et al. The 2-phase lattice Boltzmann simulation of flow-following bubble movement through microchannels in orifice plates[J]. Applied Mathematics and Mechanics, 2024, 45(1): 97-109. (in Chinese)
[58]	Chen C, Zhang D. Pore-scale simulation of density-driven convection in fractured porous media during geological CO₂ sequestration[J]. Water Resources Research, 2010, 46(11): 2010WR009453.
[59]	Zhang L, Jing W, Yang Y, et al. The investigation of permeability calculation using digital core simulation technology[J]. Energies, 2019, 12(17): 3273. doi: 10.3390/en12173273
[60]	Lanetc Z, Zhuravljov A, Jing Y, et al. Coupling of pore network modelling and volume of fluid methods for multiphase flow in fractured media[J]. Fuel, 2022, 319: 123563. doi: 10.1016/j.fuel.2022.123563
[61]	Wang J Q, Zhao J F, Yang M J, et al. Permeability of laboratory-formed porous media containing methane hydrate: observations using X-ray computed tomography and simulations with pore network models[J]. Fuel, 2015, 145: 170-179. doi: 10.1016/j.fuel.2014.12.079
[62]	Zhao J, Qin F, Derome D, et al. Improved pore network models to simulate single-phase flow in porous media by coupling with lattice Boltzmann method[J]. Advances in Water Resources, 2020, 145: 103738. doi: 10.1016/j.advwatres.2020.103738
[63]	Wang J. Continuum theory for dense gas-solid flow: a state-of-the-art review[J]. Chemical Engineering Science, 2020, 215: 115428. doi: 10.1016/j.ces.2019.115428
[64]	Chandra D, Vishal V. A critical review on pore to continuum scale imaging techniques for enhanced shale gas recovery[J]. Earth-Science Reviews, 2021, 217: 103638. doi: 10.1016/j.earscirev.2021.103638
[65]	Ranjbarzadeh R, Sappa G. Numerical and experimental study of fluid flow and heat transfer in porous media: a review article[J]. Energies, 2025, 18(4): 976. doi: 10.3390/en18040976
[66]	Yan X, Huang Z, Yao J, et al. Numerical simulation of hydro-mechanical coupling in fractured vuggy porous media using the equivalent continuum model and embedded discrete fracture model[J]. Advances in Water Resources, 2019, 126: 137-154. doi: 10.1016/j.advwatres.2019.02.013
[67]	Liu T, Jin X, Wang M. Critical resolution and sample size of digital rock analysis for unconventional reservoirs[J]. Energies, 2018, 11(7): 1798. doi: 10.3390/en11071798
[68]	Liu T, Wang M. Critical REV size of multiphase flow in porous media for upscaling by pore-scale modeling[J]. Transport in Porous Media, 2022, 144(1): 111-132. doi: 10.1007/s11242-021-01621-2
[69]	Kochkov D, Smith J A, Alieva A, et al. Machine learning-accelerated computational fluid dynamics[J]. Proceedings of the National Academy of Sciences of the United States of America, 2021, 118(21): e2101784118.
[70]	Petersen K J, Brinkerhoff J R. On the lattice Boltzmann method and its application to turbulent, multiphase flows of various fluids including cryogens: a review[J]. Physics of Fluids, 2021, 33(4): 041302. doi: 10.1063/5.0046938
[71]	Li Q, Luo K H, Kang Q J, et al. Lattice Boltzmann methods for multiphase flow and phase-change heat transfer[J]. Progress in Energy and Combustion Science, 2016, 52: 62-105. doi: 10.1016/j.pecs.2015.10.001
[72]	蔡少斌, 杨永飞, 刘杰. 考虑热流固耦合作用的多孔介质孔隙尺度两相流动模拟[J]. 力学学报, 2021, 53(8): 2225-2234. Cai Shaobin, Yang Yongfei, Liu Jie. Pore-scale simulation of multiphase flow considering thermo-hydro-mechanical coupling effect in porous media[J]. Chinese Journal of Theoretical and Applied Mechanics, 2021, 53(8): 2225-2234. (in Chinese)
[73]	Xi C, Gong W, Lu X, et al. Wettability evolution of sandpacks with clay content during long-term waterflooding: a pore-scale contact angle characterization[J]. SPE Journal, 2025, 30(1): 180-197. doi: 10.2118/223938-PA
[74]	Wang S, Shen Y. Coarse-grained CFD-DEM modelling of dense gas-solid reacting flow[J]. International Journal of Heat and Mass Transfer, 2022, 184: 122302. doi: 10.1016/j.ijheatmasstransfer.2021.122302
[75]	Patursson ∅, Swift M R, Tsukrov I, et al. Development of a porous media model with application to flow through and around a net panel[J]. Ocean Engineering, 2010, 37(2/3): 314-324.
[76]	Li X, Li B, Liu F, et al. Advances in the application of deep learning methods to digital rock technology[J]. Advances in Geo-Energy Research, 2023, 8(1): 5-18. doi: 10.46690/ager.2023.04.02
[77]	Yang Y, Liu F, Zhang Q, et al. Recent advances in multiscale digital rock reconstruction, flow simulation, and experiments during shale gas production[J]. Energy & Fuels, 2023, 37(4): 2475-2497.
[78]	Rabbani A, Babaei M, Shams R, et al. Deepore: a deep learning workflow for rapid and comprehensive characterization of porous materials[J]. Advances in Water Resources, 2020, 146: 103787. doi: 10.1016/j.advwatres.2020.103787
[79]	Fu J, Wang M, Chen B, et al. A data-driven framework for permeability prediction of natural porous rocks via microstructural characterization and pore-scale simulation[J]. Engineering With Computers, 2023, 39(6): 3895-3926. doi: 10.1007/s00366-023-01841-8
[80]	Cawte T, Bazylak A. A 3D convolutional neural network accurately predicts the permeability of gas diffusion layer materials directly from image data[J]. Current Opinion in Electrochemistry, 2022, 35: 101101. doi: 10.1016/j.coelec.2022.101101
[81]	Xie C, Zhu J, Wang J, et al. Direct prediction of relative permeability curve from 3D digital rock images based on deep learning approaches[J]. International Journal of Rock Mechanics and Mining Sciences, 2023, 170: 105544. doi: 10.1016/j.ijrmms.2023.105544
[82]	Wang Y, Rahman S S. Numerical modelling of reservoir at pore scale: a comprehensive review[J]. Journal of Computational Physics, 2023, 472: 111680. doi: 10.1016/j.jcp.2022.111680
[83]	Mosser L, Dubrule O, Blunt M J. Reconstruction of three-dimensional porous media using generative adversarial neural networks[J]. Physical Review E, 2017, 96(4): 043309. doi: 10.1103/PhysRevE.96.043309
[84]	Jiang Z, Wang W, Zhu H, et al. Review of shale gas transport prediction: basic theory, numerical simulation, application of AI methods, and perspectives[J]. Energy & Fuels, 2023, 37(4): 2520-2538.
[85]	Mirzaee H, Kamrava S, Tahmasebi P. Minireview on porous media and microstructure reconstruction using machine learning techniques: recent advances and outlook[J]. Energy & Fuels, 2023, 37(20): 15348-15372.
[86]	Song S, Zhang D, Mukerji T, et al. GANSim-surrogate: an integrated framework for stochastic conditional geomodelling[J]. Journal of Hydrology, 2023, 620: 129493. doi: 10.1016/j.jhydrol.2023.129493
[87]	Khosravi R, Chahardowli M, Simjoo M. Smart water-polymer hybrid flooding in heavy oil sandstone reservoirs: a detailed review and guidelines for future applications[J]. Energy & Fuels, 2024, 38(14): 12283-12302.
[88]	Zhu Y, Zabaras N. Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification[J]. Journal of Computational Physics, 2018, 366: 415-447. doi: 10.1016/j.jcp.2018.04.018
[89]	Mo S, Zhu Y, Zabaras N, et al. Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media[J]. Water Resources Research, 2019, 55(1): 703-728. doi: 10.1029/2018WR023528
[90]	Feng G, Zhang K, Wan H, et al. Enhancing oil-water flow prediction in heterogeneous porous media using machine learning[J]. Water, 2024, 16(10): 1411. doi: 10.3390/w16101411
[91]	Chen X, Zhang K, Ji Z, et al. Progress and challenges of integrated machine learning and traditional numerical algorithms: taking reservoir numerical simulation as an example[J]. Mathematics, 2023, 11(21): 4418. doi: 10.3390/math11214418
[92]	Tartakovsky A M, Marrero C O, Perdikaris P, et al. Physics-informed deep neural networks for learning parameters and constitutive relationships in subsurface flow problems[J]. Water Resources Research, 2020, 56(5): e2019WR026731. doi: 10.1029/2019WR026731
[93]	Vu-Quoc L, Humer A. Deep learning applied to computational mechanics: a comprehensive review, state of the art, and the classics[J]. Computer Modeling in Engineering & Sciences, 2023, 137(2): 1069-1343.
[94]	颜景越, 苏欢. 基于残差的Fourier神经网络求解广域椭圆型微分方程以及收敛性证明[J]. 应用数学和力学, 2026, 47(7): 912-923. Yan Jingyue, Su Huan. Residual-based Fourier neural network for solving elliptic differential equations on unbounded domains and convergence analysis[J]. Applied Mathematics and Mechanics, 2026, 47(7): 912-923. (in Chinese)
[95]	He Q, Barajas-Solano D, Tartakovsky G, et al. Physics-informed neural networks for multiphysics data assimilation with application to subsurface transport[J]. Advances in Water Resources, 2020, 141: 103610. doi: 10.1016/j.advwatres.2020.103610
[96]	Meng X, Karniadakis G E. A composite neural network that learns from multi-fidelity data: application to function approximation and inverse PDE problems[J]. Journal of Computational Physics, 2020, 401: 109020. doi: 10.1016/j.jcp.2019.109020
[97]	Yang Y, Perdikaris P. Adversarial uncertainty quantification in physics-informed neural networks[J]. Journal of Computational Physics, 2019, 394: 136-152. doi: 10.1016/j.jcp.2019.05.027
[98]	Kenzhebek Y, Imankulov T, Bekele S D, et al. Coupled pressure and saturation prediction for two-phase flow in porous media using physics-informed neural networks (PINNs)[J]. Computer Methods in Applied Mechanics and Engineering, 2025, 446: 118229. doi: 10.1016/j.cma.2025.118229
[99]	Xiang X, Chen Y, Zhang E, et al. Lightweight permeability prediction of digital rocks by merging 3D depthwise separable convolution with efficient multiscale attention[J]. Computational Geosciences, 2025, 29(3): 21. doi: 10.1007/s10596-025-10363-9
[100]	Jamshidi Gohari M S, Emami Niri M, Ghiasi-Freez J. Improving permeability estimation of carbonate rocks using extracted pore network parameters: a gas field case study[J]. Acta Geophysica, 2021, 69(2): 509-527. doi: 10.1007/s11600-021-00563-z
[101]	Tian J W, Qi C, Peng K, et al. Improved permeability prediction of porous media by feature selection and machine learning methods comparison[J]. Journal of Computing in Civil Engineering, 2022, 36(2): 04021040. doi: 10.1061/(ASCE)CP.1943-5487.0000983
[102]	周济民, 张海晨, 王沫然. 基于物理经验模型约束的机器学习方法在页岩油产量预测中的应用[J]. 应用数学和力学, 2021, 42(9): 881-890. doi: 10.21656/1000-0887.420015 Zhou Jimin, Zhang Haichen, Wang Moran. Machine learning with physical empirical model constraints for prediction of shale oil production[J]. Applied Mathematics and Mechanics, 2021, 42(9): 881-890. (in Chinese) doi: 10.21656/1000-0887.420015
[103]	Wang F, Zai Y. Image segmentation and flow prediction of digital rock with U-Net network[J]. Advances in Water Resources, 2023, 172: 104384. doi: 10.1016/j.advwatres.2023.104384
[104]	Tang P, Zhang D, Li H. Predicting permeability from 3D rock images based on CNN with physical information[J]. Journal of Hydrology, 2022, 606: 127473. doi: 10.1016/j.jhydrol.2022.127473
[105]	Wang H C, Zhang K, Chen N, et al. Better use of experience from other reservoirs for accurate production forecasting by learn-to-learn method[J]. Petroleum Science, 2024, 21(1): 716-728. doi: 10.1016/j.petsci.2023.04.015
[106]	Liu S, Fan M, Lu D. Uncertainty quantification of the convolutional neural networks on permeability estimation from micro-CT scanned sandstone and carbonate rock images[J]. Geoenergy Science and Engineering, 2023, 230: 212160. doi: 10.1016/j.geoen.2023.212160
[107]	Wang K, Chen Y, Mehana M, et al. A physics-informed and hierarchically regularized data-driven model for predicting fluid flow through porous media[J]. Journal of Computational Physics, 2021, 443: 110526. doi: 10.1016/j.jcp.2021.110526
[108]	Yu Y, Chen S, Wei H. Modified U-Net with attention gate and dense skip connection for flow field information prediction with porous media[J]. Flow Measurement and Instrumentation, 2023, 89: 102300. doi: 10.1016/j.flowmeasinst.2022.102300
[109]	Ko D D, Ji H, Ju Y S. Prediction of 3D velocity field of reticulated foams using deep learning for transport analysis[J]. Transport in Porous Media, 2023, 148(3): 577-604. doi: 10.1007/s11242-023-01961-1
[110]	Kumar I, Tripathi B K, Singh A. Velocity field prediction for digital porous media using attention-based deep convolutional recurrent neural network[J]. Chemical Engineering Science, 2025, 314: 121825. doi: 10.1016/j.ces.2025.121825
[111]	Zhou X H, McClure J E, Chen C, et al. Neural network-based pore flow field prediction in porous media using super resolution[J]. Physical Review Fluids, 2022, 7(7): 074302. doi: 10.1103/PhysRevFluids.7.074302
[112]	田键, 康毅力, 游利军, 等. 致密砂岩孔隙尺度下气-水界面动态演化可视化实验研究[J]. 力学学报, 2024, 56(3): 862-873. Tian Jian, Kang Yili, You Lijun, et al. Visualization study on the evolution of gas-water interface at pore-scale in tight sandstone rocks[J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(3): 862-873. (in Chinese)
[113]	Liu S, Zolfaghari A, Sattarin S, et al. Application of neural networks in multiphase flow through porous media: predicting capillary pressure and relative permeability curves[J]. Journal of Petroleum Science and Engineering, 2019, 180: 445-455. doi: 10.1016/j.petrol.2019.05.041
[114]	Telvari S, Sayyafzadeh M, Siavashi J, et al. Prediction of two-phase flow properties for digital sandstones using 3D convolutional neural networks[J]. Advances in Water Resources, 2023, 176: 104442. doi: 10.1016/j.advwatres.2023.104442
[115]	Xie C, Zhu J, Yang H, et al. Relative permeability curve prediction from digital rocks with variable sizes using deep learning[J]. Physics of Fluids, 2023, 35(9): 096605. doi: 10.1063/5.0167998
[116]	Jiang J. Simulating multiphase flow in fractured media with graph neural networks[J]. Physics of Fluids, 2024, 36(2): 023115. doi: 10.1063/5.0189174
[117]	Kim Y, Suh H S. GNPNM: a graph neural pore network model for predicting quasi-static drainage displacement patterns[J]. Computers and Geotechnics, 2025, 187: 107497. doi: 10.1016/j.compgeo.2025.107497
[118]	Ji L, Xu F, Lin M, et al. Rapid evaluation of capillary pressure and relative permeability for oil-water flow in tight sandstone based on a physics-informed neural network[J]. Journal of Petroleum Exploration and Production Technology, 2023, 13(12): 2499-2517. doi: 10.1007/s13202-023-01682-7
[119]	Hanna J M, Aguado J V, Comas-Cardona S, et al. Residual-based adaptivity for two-phase flow simulation in porous media using physics-informed neural networks[J]. Computer Methods in Applied Mechanics and Engineering, 2022, 396: 115100. doi: 10.1016/j.cma.2022.115100
[120]	Cui R, Cao D, Liu Q, et al. V_P and V_S prediction from digital rock images using a combination of U-Net and convolutional neural networks[J]. Geophysics, 2021, 86(1): MR27-MR37. doi: 10.1190/geo2020-0162.1
[121]	Karimpouli S, Tahmasebi P. Image-based velocity estimation of rock using convolutional neural networks[J]. Neural Networks, 2019, 111: 89-97. doi: 10.1016/j.neunet.2018.12.006
[122]	Moghadas D. One-dimensional deep learning inversion of electromagnetic induction data using convolutional neural network[J]. Geophysical Journal International, 2020, 222(1): 247-259. doi: 10.1093/gji/ggaa161
[123]	Puzyrev V, Swidinsky A. Inversion of 1D frequency- and time-domain electromagnetic data with convolutional neural networks[J]. Computers & Geosciences, 2021, 149: 104681.
[124]	Spichak V V, Zakharova O K. Seismological geothermometer, part Ⅰ: neural network modeling of the temperature prediction from seismic velocity data at borehole depth scale[J]. Journal of Applied Geophysics, 2025, 234: 105644. doi: 10.1016/j.jappgeo.2025.105644
[125]	Zhang T, Bian N, Liu Q, et al. 3D super-resolution reconstruction of porous media based on GANs and CBAMs[J]. Stochastic Environmental Research and Risk Assessment, 2024, 38(4): 1475-1504. doi: 10.1007/s00477-023-02639-2
[126]	Elmorsy M, El-Dakhakhni W, Zhao B. Generalizable permeability prediction of digital porous media via a novel multi-scale 3D convolutional neural network[J]. Water Resources Research, 2022, 58(3): e2021WR031454. doi: 10.1029/2021WR031454
[127]	Kashefi A, Mukerji T. Point-cloud deep learning of porous media for permeability prediction[J]. Physics of Fluids, 2021, 33(9): 097109. doi: 10.1063/5.0063904
[128]	Yang L, Wang S, Chen X, et al. High-fidelity permeability and porosity prediction using deep learning with the self-attention mechanism[J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(7): 3429-3443. doi: 10.1109/TNNLS.2022.3157765
[129]	Zhai S, Geng S, Li C, et al. An improved convolutional neural network for predicting porous media permeability from rock thin sections[J]. Gas Science and Engineering, 2024, 127: 205365. doi: 10.1016/j.jgsce.2024.205365
[130]	Dong Y, Song T, Li X, et al. Multi-scale enhanced multiwavelet-based operator learning model for multiphase flow simulation[J]. Physics of Fluids, 2025, 37(3): 033376. doi: 10.1063/5.0257751
[131]	Chen X, Zhou K, Jiang P, et al. Identification, characterization, and up-scaling of pore structure facies in the low permeability reservoirs: insight into reservoir quality evaluation and sweet-spots analysis[J]. Marine and Petroleum Geology, 2024, 162: 106646. doi: 10.1016/j.marpetgeo.2023.106646
[132]	Tosan M. Enhancing evapotranspiration estimation: a bibliometric and systematic review of hybrid neural networks in water resource management[J]. Computer Modeling in Engineering & Sciences, 2025, 142(2): 1109-1154.
[133]	Amini D, Haghighat E, Juanes R. Physics-informed neural network solution of thermo-hydro-mechanical processes in porous media[J]. Journal of Engineering Mechanics, 2022, 148(11): 04022070. doi: 10.1061/(ASCE)EM.1943-7889.0002156
[134]	Yan B, Harp D R, Chen B, et al. A gradient-based deep neural network model for simulating multiphase flow in porous media[J]. Journal of Computational Physics, 2022, 463: 111277. doi: 10.1016/j.jcp.2022.111277