Dissolution patterns prediction for horizontal rough fracture based on deep neural network and lattice Boltzmann method
Abstract
Understanding thermal energy transfer and fracture evolution in submarine hydrothermal systems is essential for sustainable resource utilization, but simulating these complex multiphase, multi-physics processes is challenging. This study integrates the lattice Boltzmann method with a fully connected neural network to investigate hydrothermal phase separation and its effects on chemical dissolution in carbonate fractures at the pore scale. Specifically, the lattice Boltzmann method simulates gas-liquid phase separation induced by seawater boiling, affecting carbonate fracture dissolution at the pore scale. The fully connected neural network predicts the resulting fracture geometry and dissolution quantities under various physical conditions. Analysis of simulation datasets demonstrates that the fully connected neural network achieves high predictive accuracy, with a total loss of 0.01 and reduces computation time by over 20% compared to traditional methods. The coupled lattice Boltzmann method-fully connected neural network model effectively simulates fractures with sizes ranging from millimeters to centimeters, excelling in handling chemical dissolution, multiphase flows, and multicomponent interactions. This approach offers valuable predictive capabilities for applications such as enhanced geothermal systems and oil reservoir exploitation.
Document Type: Original article
Cited as: Yi, G., Zhuang, X., Zhang, D., Li, Y., Gong, L. Dissolution patterns prediction for horizontal rough fracture based on deep neural network and lattice Boltzmann method. Advances in Geo-Energy Research, 2025, 15(3): 273-282. https://doi.org/10.46690/ager.2025.03.09
Keywords:
Lattice Boltzmann method, fully connected neural network, gas-liquid phase change, dissolution reactionReferences
Akiba, T., Sano, S., Yanase, T., et al. Optuna: A next generation hyperparameter optimization framework. Paper KDD 2623-2631 Presented at the Twenty-fifth ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, Alaska, 4-8 August, 2019.
Bhadauria, A., Dorschner, B., Karlin, I. Lattice Boltzmann method for fluid–structure interaction in compressible flow. Physics of Fluids, 2021, 33(10): 106111.
Chen, L., He, Y., Kang, Q., et al. Coupled numerical approach combining finite volume and lattice Boltzmann methods for multi-scale multi-physicochemical processes. Journal of Computational Physics, 2013, 255: 83-105.
Coronado, M., Ramírez-Sabag, J., Valdiviezo-Mijangos, O. Double-porosity model for tracer transport in reservoirs having open conductive geological faults: Determination of the fault orientation. Journal of Petroleum Science and Engineering, 2011, 78(1): 65-77.
El-Amin, M. F., Alwated, B., Hoteit, H. Machine learning prediction of nanoparticle transport with two-phase flow in porous media. Energies, 2023, 16(2): 678.
Elrahmani, A., Al-Raoush, R. I., Ayari, M. A. Modeling of permeability impairment dynamics in porous media: A machine learning approach. Powder Technology, 2024, 433: 119272.
Fu, S., Su, W., Zhang, H., et al. An immersed moving boundary for fast discrete particle simulation with complex geometry. Chemical Engineering Science, 2024, 283: 119407.
Gong, L., Han, D., Chen, Z., et al. Research status and development trend of key technologies for enhanced
Gong, L., Han, D., Chen, Z., et al. Research status and development trend of key technologies for enhanced geothermal systems. Natural Gas Industry B, 2023, 10(2): 140-164.
He, H., Cao, J., Duan, N. Defects and their behaviors in mineral dissolution under water environment: A review. Science of the Total Environment, 2019, 651: 2208-2217.
Hinton, G. E., Osindero, S., Teh, Y. W. A fast learning algorithm for deep belief nets. Neural Computation, 2006, 18(7): 1527-1554.
Kamrava, S., Tahmasebi, P., Sahimi, M. Physics-and image-based prediction of fluid flow and transport in complex porous membranes and materials by deep learning. Journal of Membrane Science, 2021, 622: 119050.
Kang, Q., Lichtner, P. C., Viswanathan, H. S., et al. Pore scale modeling of reactive transport involved in geologic CO2 sequestration. Transport in Porous Media, 2010, 82(1): 197-213.
Liu, N., Liu, M. Simulation and analysis of wormhole propagation by VES acid in carbonate acidizing. Journal of Petroleum Science and Engineering, 2016, 138: 57-65.
Liu, X., Luo, X., Liu, S., et al. A numerical investigation of the nonlinear flow and heat transfer mechanism in rough fractured rock accounting for fluid phase transition effects. Water, 2024, 16(2): 342.
Lowell, R. P., Rona, P. A., Von Herzen, R. P. Seafloor hydrothermal systems. Journal of Geophysical Research: Solid Earth, 1995, 100(B1): 327-352.
Luo, Y., Feng, Y., Zhang, D., et al. Numerical simulation of chemical reactions’ influence on convective heat transfer in hydrothermal circulation reaction zones. Energies, 2024, 17(11): 2442.
Mahmoodi, A., Javadi, A., Sola, B. S. Porous media acidizing simulation: New two-phase two-scale continuum modeling approach. Journal of Petroleum Science and Engineering, 2018, 166: 679-692.
Martín-Díaz, J. P., González-Vega, A., Barreyre, T., et al. Unveiling the inherent physical-chemical dynamics: Direct measurements of hydrothermal fluid flow, heat, and nutrient outflow at the Tagoro submarine volcano (Canary Islands, Spain). Science of the Total Environment, 2024, 918: 170565.
Micale, D., Ferroni, C., Uglietti, R., et al. Computational fluid dynamics of reacting flows at surfaces: Methodologies and applications. Chemie Ingenieur Technik, 2022, 94(5): 634-651.
Mohammadi-Arani, R., Dehghan, M., Abbaszadeh, M. Extending matrix–vector framework on multiple relaxation time lattice Boltzmann method. Applied Mathematics Letters, 2024, 152: 108998.
Salakhutdinov, R., Hinton, G. Deep Boltzmann machines. Paper PMLR 5: 448-455 Presented at the 12th International Conference on Artificial Intelligence and Statistics, Florida, America, 16-18 April, 2009.
Shan, X., Chen, H. Lattice Boltzmann model for simulating flows with multiple phases and components. Physical Review E, 1993, 47(3): 1815.
Sharma, K. V., Straka, R., Tavares, F. W. Current status of Lattice Boltzmann Methods applied to aerodynamic, aeroacoustic, and thermal flows. Progress in Aerospace Sciences, 2020, 115: 100616.
Spitzmüller, L., Goldberg, V., Held, S., et al. Selective silica removal in geothermal fluids: Implications for applications for geothermal power plant operation and mineral extraction. Geothermics, 2021, 95: 102141.
Wang, H., Chen, S. Insights into the application of machine learning in reservoir engineering: current developments and future trends. Energies, 2023, 16(3): 1392.
Wang, J., Guo, T., Chen, M., et al. Numerical simulation of deflagration fracturing in shale gas reservoirs considering the effect of stress wave impact and gas drive. International Journal of Rock Mechanics and Mining Sciences, 2023, 170: 105478.
Xie, Z., Huang, Z., Li, G., et al. The effect of natural fractures on the failure mechanism of granite: Implication for enhanced geothermal systems. Engineering Fracture Mechanics, 2024, 299: 109938.
Xi, L., Yin, D., Park, J. S. Special issue: CFD modeling of complex chemical processes: Multiscale and multiphysics challenges. Processes, 2021, 9(5): 775.
Yamashita, R., Nishio, M., Do, R. K. G., et al. Convolutional neural networks: An overview and application in radiology. Insights into Imaging, 2018, 9: 611-629.
Yi, G., Zhuang, X., Li, Y. Probabilistic state estimation in district heating grids using deep neural network. Sustainable Energy, Grids and Networks, 2024, 38: 101353.
Zeng, H., Hu, P., He, Z., et al. Numerical simulation study of seafloor hydrothermal circulation based on hydrothermal foam: A case study of the Wocan-1 hydrothermal field, Carlsberg Ridge, Indian Ocean. Journal of Marine Science and Engineering, 2023, 12(1): 46.
Zhang, D., Li, S., Jiao, S., et al. Relative permeability of three immiscible fluids in random porous media determined by the lattice Boltzmann method. International Journal of Heat and Mass Transfer, 2019, 134: 311-320.
Zhang, D., Li, S., Li, Y. Lattice Boltzmann simulation of three phase reactive flow in random porous media at pore-scale. Applied Thermal Engineering, 2021a, 194: 117140.
Zhang, D., Li, S., Li, Y. Pore-scale investigation on the effect of gas-liquid phase separation on reactive flow in a horizontal rough fracture using the lattice Boltzmann method. Chemical Engineering Science, 2021b, 236: 116483.
Zhou, J., Qi, B., Zhang, Y., et al. Experimental and theoretical study of bubble coalescence and departure behaviors during nucleate pool boiling on uniform smooth and micro-pin-finned surfaces under different sub-cooling and heat fluxes. Experimental Thermal and Fluid Science, 2020a, 112: 109996.
Zhou, X., Xu, Z., Xia, Y., et al. Pore-scale investigation on reactive flow in porous media with immiscible phase using lattice Boltzmann method. Journal of Petroleum Science and Engineering, 2020b, 191: 107224.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.