Deep learning in digital rock technology: A comprehensive review
Abstract
Against the background of digital oil field development, deep learning has driven digital rock technology toward a more robust and data-driven characterization framework. This review comprehensively explores the integration of deep learning in pore structure analysis and micro-scale transport mechanisms. This paper systematically reviews the current status of four key areas, namely super-resolution reconstruction, image segmentation, physical property prediction, and flow simulation. Super-resolution reconstruction and image segmentation improve image quality and sharpen pore boundary identification, providing a solid basis for subsequent microscopic analysis. Physical property prediction further links microscopic structures to macroscopic properties, offering an effective approach for reservoir property evaluation. Flow simulation describes transport behavior in porous media and helps reveal flow patterns under different conditions. Despite significant progress, this review also identifies several challenges, including insufficient consideration of physical degradation during image acquisition, as well as limited availability of high-quality labeled data and three-dimensional spatial constraints. In addition, the generalization of physical property prediction and flow simulation models across scales and lithologies remains weak, and the incorporation of flow physics into neural architectures is still inadequate, which may affect physical consistency. This review also discusses emerging trends such as multi-scale modeling and physics-aware learning. Finally, future research directions are identified to support intelligent reservoir characterization and provide stronger technical support for oil and gas development decisions.
Document Type: Invited review
Cited as: Liu, C., Shan, L., Zhao, J., Xia, Y., Cai, J. Deep learning in digital rock technology: A comprehensive review. Advanced IntelliEngineering, 2026, 1(1): 4-20. https://doi.org/10.46690/aie.2026.01.02
DOI:
https://doi.org/10.46690/aie.2026.01.02Keywords:
Digital rock, deep learning, super-resolution reconstruction, image segmentation, physical property prediction, flow simulationReferences
[1] Alameedy, U., Abdul-Majeed, G., AlSaedi, H. N., et al. Role of artificial intelligence in enhancing efficiency and sustainability in middle eastern oil and gas: A review. Arabian Journal for Science and Engineering, 2026, 51(1): 1043-1066.
[2] Zhang, Q., Liu, J., Gao, Z., et al. Review on the challenges and strategies in oil and gas industry’s transition towards carbon neutrality in China. Petroleum Science, 2023, 20(6): 3931-3944.
[3] Wang, F., Chen, D., Li, M., et al. A novel method for predicting shallow hydrocarbon accumulation based onsource-fault-sand (SF-Sd) evaluation and ensemble neural network (ENN). Applied Energy, 2024, 359: 122684.
[4] Yang, D., Wang, P., Lu, J., et al. Leakage detection of oil and gas pipelines based on a multi-channel and multi-branch one-dimensional convolutional neural network with imbalanced samples. Computers in Industry, 2025a, 173: 104356.
[5] Yang, H., Feng, W., Diao, H., et al. Artificial intelligence in shale gas and oil: A comprehensive review of applications and challenges. Green and Smart Mining Engineering, 2025b, 2: 259-277.
[6] Tu, R., Liao, Q., Liu, Y., et al. Transformation of China’s petroleum pipeline industry in the renewable energy era: A review. Renewable and Sustainable Energy Reviews, 2026, 233: 116863.
[7] Xiong, A., Zhou, Y., Shen, Z., et al. Total pore-throat size distribution characteristics and oiliness differences analysis of different oil-bearing tight sandstone reservoirs - A case study of Chang6 reservoir in Xiasiwan Oilfield, Ordos Basin. Fractal and Fractional, 2025, 9(11): 729.
[8] Davoodi, S., Makarov, N., Wood, D. A., et al. A review of artificial intelligence techniques applied to subsurface oil and gas reservoir simulation. Applied Soft Computing, 2026, 198: 115222.
[9] Liu, J., Li, J., Song, Z., et al. Flow characteristics of shale oil and its geological controls: A case study of the Lucaogou Formation in the Jimsar Sag, Junggar Basin. Petroleum Science, 2025, 22(10): 3900-3914.
[10] Wang, D., Ma, Y., Hu, Z., et al. Pore network modeling of gas-water two-phase flow in deformed multi-scale fracture-porous media. Petroleum Science, 2025, 22(5): 2096-2108.
[11] Zhou, Y., Nie, X. Identification and parameter char acterization of pores and fractures in shales based on multi-scale digital core data. Advances in Geo-Energy Research, 2024, 13(2): 146-160.
[12] Xia, C., Shan, J., Li, Y., et al. Three-dimensional modeling of full-diameter micro-nano digital rock core based on CT scanning. Processes, 2026, 14(2): 337.
[13] Li, G., Zhao, J., Liu, Y., et al. Research on multi-scale digital core construction of carbonate rock with fractures and caves characteristics: A case study of dengying formation carbonate rocks in Sichuan Basin. Frontiers in Earth Science, 2025, 13: 1528829.
[14] Li, J., Teng, Q., Zhang, N., et al. Deep learning method of stochastic reconstruction of three-dimensional digital cores from a two-dimensional image. Physical Review E, 2023, 107(5): 055309.
[15] Luo, X., Sun, J., Zhang, R., et al. A multi-condition denoising diffusion probabilistic model controls the recon struction of 3D digital rocks. Computers & Geosciences, 2024, 184: 105541.
[16] Golsanami, N., Guo, D., Fernando, S. G., et al. Tensile fracture propagation in deep coalbed methane layers under brazilian test: A quantitative analysis using digital rock technology and deep learning-based image segmen tation. Rock Mechanics and Rock Engineering, 2025, 58(9): 10613-10641.
[17] Chen, Y., Chen, P., Dai, X., et al. Prediction of rate of penetration in oil and gas well drilling: A hybrid data driven approach with multi-stage data preprocessing. Engineering Applications of Artificial Intelligence, 2026, 163: 113085.
[18] Maroufi, K., Zahmatkesh, I. Effect of lithological variations on the performance of artificial intelligence techniques for estimating total organic carbon through well logs. Journal of Petroleum Science and Engineering, 2023, 220: 111213.
[19] Davoodi, S., Al-Shargabi, M., Wood, D. A., et al. Advancement of artificial intelligence applications in hydrocarbon well drilling technology: A review. Applied Soft Computing, 2025, 176: 113129.
[20] da Luz, M. A. L., Vasconcelos, M. A. R. Hybrid seismic automation: Integrating artificial intelligence and deterministic methods in velocity analysis. Journal of Applied Geophysics, 2026, 250: 106259.
[21] Zhao, G., Wu, Y., Wei, X. A high-fidelity digital rock representation based on digital grinding combined with deep learning for four-dimensional lattice spring model. International Journal of Rock Mechanics and Mining Sciences, 2025, 186: 106004.
[22] Wu, P., Dong, Z., Liu, S., et al. Microstructure and physical properties of hydrate-bearing sediment: Digital core and deep learning application. Fuel, 2026, 404: 136283.
[23] Neumann, R. F., Barsi-Andreeta, M., Lucas-Oliveira, E., et al. High accuracy capillary network representation in digital rock reveals permeability scaling functions. Scientific Reports, 2021, 11: 11370.
[24] Du, Y., Yan, S., Fu, C., et al. Study on the influence mechanism of the supercritical CO2-H2O-coal interaction on the anisotropy of coal permeability via digital rock technology. Energy, 2025, 343: 139813.
[25] Zhang, H., Zhang, Z., Nie, X., et al. Multiscale digital core technology for analyzing the genesis of low resistivity oil reservoirs in the guantao formation of bohai sea: Clay mineral-induced additional conductivity effect, pore structure regulation mechanism, and quantitative characterization. Geofluids, 2026, 2026(1): 9975345.
[26] Chi, P., Sun, J., Yan, W., et al. From digital rock to dig ital wellbore: Multiscale reconstruction and simulation. Advances in Geo-Energy Research, 2024, 13(1): 1-6.
[27] Jiang, F., Guo, Y., Tsuji, T., et al. Upscaling permeability using multiscale X-ray-CT images with digital rock modeling and deep learning techniques. Water Resources Research, 2023, 59(3): e2022WR033267.
[28] Fan, Y., Yan, W., Xing, H., et al. Investigating petro physical properties of gas hydrate-bearing sediments using digital rock technology: A microscopic perspective. Petroleum Science, 2025, 22(5): 1889-1911.
[29] Wei, X., Qu, D., Zhou, Z., et al. Three-dimensional refined discrete element numerical modeling method and its application for reef limestone based on digital core technology. Computers and Geotechnics, 2025, 185: 107362.
[30] Murugesu, M. P., Krishnan, V., Kovscek, A. R. Enhanc ing prediction of fluid-saturated fracture characteristics using deep learning super resolution. Applied Computing and Geosciences, 2024, 24: 100208.
[31] You, S., Liao, Q., Yan, Z., et al. Super-resolution recon struction of 3D digital rocks by deep neural networks. Geoenergy Science and Engineering, 2024, 237: 212781.
[32] Zohdparast, P., Kadkhodaie, A. High resolution estimation shear wave velocity and rock elastic properties using integration of the individual and hybrid machine learning models. Results in Engineering, 2026, 29: 109423.
[33] Lepcha, D. C., Goyal, B., Dogra, A., et al. Image super-resolution: A comprehensive review, recent trends, challenges and applications. Information Fusion, 2023, 91: 230-260.
[34] Su, H., Li, Y., Xu, Y., et al. A review of deep-learning based super-resolution: From methods to applications. Pattern Recognition, 2025, 157: 110935.
[35] Tang, K., Wang, Y., Regaieg, M., et al. Unlocking sub-micrometer features in carbonate rocks: A cas cading super-resolution approach for multiscale multi- instrument carbonate characterization. Water Resources Research, 2025, 61(8): e2025WR040865.
[36] Wang, Y., Armstrong, R. T., Mostaghimi, P. Enhancing resolution of digital rock images with super resolution convolutional neural networks. Journal of Petroleum Sci ence and Engineering, 2019, 182: 106261.
[37] Shan, L., Bai, X., Liu, C., et al. Super-resolution recon struction of digital rock CT images based on residual attention mechanism. Advances in Geo-Energy Research, 2022, 6(2): 157-168.
[38] Yang, Y., Wang, J., Liu, F., et al. Super-resolution of digital rock images with hybrid attention multi-branch neural network. Gas Science and Engineering, 2024, 128: 205395.
[39] Huo, F., Liu, K., Dong, H., et al. Rock core micrograph image super-resolution reconstruction using a novel deep residual network. Signal, Image and Video Processing, 2025, 19(5): 369.
[40] Liu, T., Xu, C., Tang, L., et al. OmniSR-M: A rock sheet with a multi-branch structure image super-resolution lightweight method. Applied Sciences, 2024, 14(7): 2779.
[41] Zhang, Y., Bi, J., Xu, L., et al. Lightweight multi-scale attention feature distillation network for super-resolution reconstruction of digital rock images. Geoenergy Science and Engineering, 2025, 246: 213628.
[42] Liu, C., Liu, Y., Shan, L., et al. Enhancing unsupervised rock CT image super-resolution with non-local attention. Geoenergy Science and Engineering, 2024, 238: 212912.
[43] Nwankwo, I., Male, F., Karpyn, Z. Patch-based super-resolution generative adversarial network for high-resolution image reconstruction in digital core analysis. Transport in Porous Media, 2026, 153(4): 50.
[44] Liu, M., Mukerji, T. Multiscale fusion of digital rock images based on deep generative adversarial networks. Geophysical Research Letters, 2022, 49(9): e2022GL098342.
[45] Wang, J., Yang, Y., Liu, F., et al. Digital rock super-resolution reconstruction with efficient 3D spatialadaptive feature modulation network. Geoenergy Science and Engineering, 2025, 248: 213748.
[46] Xing, Z., Yao, J., Liu, L., et al. Efficiently reconstructing high-quality details of 3D digital rocks with super-resolution transformer. Energy, 2024, 300: 131499.
[47] Niu, Z., Zhu, C., Zhang, W., et al. Physically-accurate super-resolution transformer for 3D digital rock CT reconstruction. Earth Science Informatics, 2026, 19(4): 49.
[48] Gao, T., Zhu, C., Niu, Z., et al. HLF-SASR: A high-low frequency guided structure-aware super-resolution network for digital rock images. Mathematical Geosciences, 2026, https://doi.org/10.1007/s11004-026-10287-9. (in Press)
[49] Yang, Z., Wu, H., Ding, H., et al. Enhanced U-Net model for rock pile segmentation and particle size analysis. Minerals Engineering, 2023, 203: 108352.
[50] Jin, C., Liang, J., Fan, C., et al. Study on segmentation of blasting fragment images from open-pit mine based on U-CARFnet. PLoS One, 2023, 18(9): e0291115.
[51] He, C., Sadeghpour, H., Shi, Y., et al. Mapping distribution of fractures and minerals in rock samples using Res-VGG-UNet and threshold segmentation methods. Computers and Geotechnics, 2024, 175: 106675.
[52] Ren, Y., Zeng, C., Li, X., et al. Intelligent evaluation of sandstone rock structure based on a visual large model. Petroleum Exploration and Development, 2025, 52(2): 548-558.
[53] Zhu, C., Wang, J., Zhang, L., et al. Sam-fusenet: Segment anything guided multimodal fusion for rgb-thermal aerial robotic perception. IEEE Transactions on Geoscience and Remote Sensing, 2025, 64: 1-12.
[54] Ren, Y., Li, X., Bi, J., et al. Multi-channel attention transformer for rock thin-section image segmentation. Journal of Engineering Research, 2025, 13(2): 730-740.
[55] Li, M., Chen, M., Lu, W., et al. RDT-FragNet: A DCN-Transformer network for intelligent rock fragment recog nition and particle size distribution acquisition. Comput ers and Geotechnics, 2025, 177: 106809.
[56] Wang, Y., Qin, R., Wei, D., et al. Super-resolution enhancement and segmentation for digital rock based on multi-task joint deep neural network. Geoenergy Science and Engineering, 2024, 243: 213385.
[57] Liu, F., Yang, Y., Yang, H., et al. Pore structure properties characterization of shale using generative adversarial network: Image augmentation, super-resolution reconstruction, and multi-mineral auto-segmentation. Petroleum Exploration and Development, 2025, 52(5): 1262-1274.
[58] Menke, H. P., Maes, J., Geiger, S. Upscaling the porosity-permeability relationship of a microporous carbonate for darcy-scale flow with machine learning. Scientific Reports, 2021, 11(1): 2625.
[59] Herrera, E., Oms, O., Remacha, E. Porosity and permeability estimations from X-Ray tomography images and data using a deep learning approach. Applied Sciences, 2026, 16(3): 1613.
[60] Tang, Z., Qiu, S., Wang, J., et al. A hybrid model for permeability prediction of porous media based on convit and transfer learning. International Journal of Heat andMass Transfer, 2026, 256: 128083.
[61] Alqahtani, N. J., Chung, T., Wang, Y., et al. Flow-based characterization of digital rock images using deep learning. SPE Journal, 2021, 26(4): 1800-1811.
[62] Alzahrani, M. K., Shapoval, A., Chen, Z., et al. Pore-GNN: A graph neural network-based framework for predicting flow properties of porous media from micro CT images. Advances in Geo-Energy Research, 2023, 10(1): 39-55.
[63] Wang, F., Zai, Y. Image segmentation and flow prediction of digital rock with U-Net network. Advances in Water Resources, 2023, 172: 104384.
[64] Xie, C., Zhu, J., Wang, J., et al. Direct prediction of relative permeability curve from 3D digital rock images based on deep learning approaches. International Journal of Rock Mechanics and Mining Sciences, 2023, 170: 105544.
[65] Ali, A., Mahmoud, A. A., Al Ramadan, M., et al. Assessing the influence of olive waste on the filtration properties, elasticity, porosity, and strength of oil well cement. Scientific Reports, 2025, 15(1): 6897.
[66] Wang, Y., Lin, G. Efficient deep learning techniques for multiphase flow simulation in heterogeneous porousc media. Journal of Computational Physics, 2020, 401: 108968.
[67] Balashov, V., Savenkov, E., Khlyupin, A., et al. Two-phase regularized phase-field density gradient Navier-Stokes based flow model: Tuning for microfluidic and digital core applications. Journal of Computational Physics, 2025, 521: 113554.
[68] Wang, Q., Wang, H., Wang, X., et al. Numerical simulation study on microseepage and displacement mechanism of coal based on digital core technology. Physics of Fluids, 2025, 37(9): 096610.
[69] Asadolahpour, S. R., Jiang, Z., Lewis, H., et al. Deep learning for pore-scale two-phase flow: Modelling drainage in realistic porous media. Petroleum Exploration and Development, 2024, 51(5): 1301-1315.
[70] Chung, J., Marcato, A., Guiltinan, E. J., et al. Accelerating multiphase simulations with denoising diffusion model driven initializations. Journal of Geophysical Research: Machine Learning and Computation, 2024, 1(4): e2024JH000293.
[71] Oommen, V., Shukla, K., Desai, S., et al. Rethinking materials simulations: Blending direct numerical simulations with neural operators. npj Computational Materials, 2024, 10(1): 145.
[72] Santos, J. E., Xu, D., Jo, H., et al. PoreFlow-Net: A 3D convolutional neural network to predict fluid flow through porous media. Advances in Water Resources, 2020, 138: 103539.
[73] Zhou, X., McClure, J. E., Chen, C., et al. Neural-network based pore flow field prediction in porous media using super resolution. Physical Review Fluids, 2022, 7(7): 074302.
[74] Zhao, J., Wu, J., Wang, H., et al. Single phase flow simulation in porous media by physical-informed Unet network based on lattice Boltzmann method. Journal ofHydrology, 2024, 639: 131501.
[75] Munarin, F., Gouze, P., Nepomuceno Filho, F. Two-phase flow dynamics in 3D fractures: Influence of aperture, wettability, and fluid properties from lattice boltzmann simulations. Advances in Water Resources, 2025, 206: 105133.
[76] Li, X., Peng, C., Zhang, C., et al. Comparative study and critical assessment of phase-field lattice boltzmann models for laminar and turbulent two-phase flow simulations. ArXiv Preprint ArXiv: 2511.11360, 2025.
[77] Wang, Y., Chung, T., Armstrong, R. T., et al. ML-LBM: Predicting and accelerating steady state flow simulation in porous media with convolutional neural networks. Transport in Porous Media, 2021, 138(1): 49-75.
[78] Kashefi, A., Mukerji, T. Prediction of fluid flow in porous media by sparse observations and physics-informed pointnet. Neural Networks, 2023, 167: 80-91.
[79] Kamrava, S., Sahimi, M., Tahmasebi, P. Simulating fluid flow in complex porous materials by integrating the governing equations with deep-layered machines. npj Computational Materials, 2021, 7(1): 127.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Chengqian Liu, Liqun Shan, Jiuyu Zhao, Yuxuan Xia, Jianchao Cai
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.