Machine learning potential insights into mechanical response and heat transfer in CO2 hydrate
Abstract
Accurate prediction of the mechanical and thermal properties of CO2 hydrates is essential for their applications in carbon sequestration and refrigeration, yet remains challenging with empirical forcefields. In this work, a deep potential machine learning potential for CO2 hydrate, trained on density functional theory datasets, is for the first time developed to serve as a unified and accurate computational framework. The as-developed deep potential machine learning potential achieves near-density functional theory accuracy in energy, force, and virial stress predictions while enabling large-scale molecular dynamics simulations at significantly reduced computational cost. Uniaxial stress-strain analyses demonstrate that the model captures the tensile strength and progressive ductile-like failure behavior. Thermal conductivity prediction agrees closely with experimental measurements within 2% deviation, outperforming empirical forcefields. Vibrational dynamics and phonon analyses reveal that the deep potential machine learning potential more accurately describes the anharmonicity and phonon scattering, especially in high-frequency modes, yielding physically realistic thermal transport behavior. This work establishes deep potential machine learning potential as a robust tool for advancing CO2 hydrate-based technologies by providing a path for accurate and efficient multi-property prediction.
Document Type: Original article
Cited as: Xiong, K., Li, Y., Lin, Z., Luo, G., Wu, J. Machine learning potential insights into mechanical response and heat transfer in CO2 hydrate. Advances in Geo-Energy Research, 2025, 18(1): 38-50. https://doi.org/10.46690/ager.2025.10.04
Keywords:
CO2 hydrate, mechanical properties, thermal conductivity, deep potential, molecular dynamicsReferences
Abascal, J. L. F., Sanz,E., Garcia Fernandez, R., et al.A potential model for the study of ices and amorphous water: TIP4P/Ice. The Journal of Chemical Physics, 2005, 122(23):234511.
Abascal,J.L. F.Vega,C.A general purpose model for the condensed phases of water: TIP4P/2005. The Journal of Chemical Physics, 2005,123(23):234505.
Arora, R. Basu, A.. Mianiy. ., t a derstandingde p ral networks with rectified linear units. Paper presented at International Conference on Learning Representations, 2018, Vancouver, Canada.
Bell,_R.J.,Dean,P. Atomic vibrations in vireous silica. Discussions of the Faraday Society, 1970,50:55-61.
Berendsen,H.J.C., Grgera,J. R., Sratsma, T. P.The missing term in efective pair potentials. The Journal of Physical Chemistry, 1987,91(24):6269-6271
Chen, L. Sun,C., Chen,G., et al.Measurements of hydrate equilibrium conditions for CH4, CO2, and CH4+C2H6+ CgHs in various systems by step-heating method.Chinese Journal of Chemical Engineering, 2009, 17(4):635-641.
Dickey, J. M,Paskin, A.Computer simlation of the latice dynamics of solids. Physical Review, 1969, 188(3):14071418.
Hafner,J.Ab-initio simulations of materials using vasp: Density-functional theory and beyond. Journal of Computational Chemistry, 2008, 29(13):2044-2078.
Hagler, A. T.,Lifson,S. Dauber,P. Consistent force field studies of intermolecular forces in hydrogen-bonded crystals.2.A benchmark for the objective comparison of alternative force fields. Journal of the American Chemical Society, 1979,101(18):5122-5130.
Harris, J.G.,Yung,K.H.Carbon dioxide's liquid-vapor coexistence curve and critical properties as predicted by a simple molecular model. The Journal of Physical Chemistry, 1995,99(31):12021-12024.
Hassanpouryouzband, A.J Jonak, F., asreghni Frahani, M,et al. Gas hydrates in sustainable chemistry. Chemical Society Reviews, 2020,49(15):5225-5309.
Homn, H.W. Swope,W.C. Pitera,J.W.eta.Development of an improved four-site water model for biomolecular simulations: TIP4P-Ew.The Journal of Chemical Physics, 2004,120(20):9665-9678.
Jia, J., Liang, Y., Tsuji, T., et al. Elasticity and stability of clathrate hydrate: Role of guest molecule motions. Scientific Reports, 2017, 7(1): 1290.
Jiang, H., Jordan, K. D. Comparison of the properties of xenon, methane, and carbon dioxide hydrates from equilibrium and nonequilibrium molecular dynamics simulations. The Journal of Physical Chemistry C, 2010, 114(12): 5555-5564.
Jiao, L.-J., Wan, R.-C., Wang, Z.-L. Experimental investigation of CO2 hydrate dissociation in silica nanoparticle system with different thermal conductivity. International Journal of Thermophysics, 2021, 42(12): 170.
Jorgensen, W. L., Chandrasekhar, J., Madura, J. D., et al. Comparison of simple potential functions for simulating liquid water. The Journal of Chemical Physics, 1983, 79(2): 926-935.
Jorgensen, W. L., Maxwell, D. S., Tirado-Rives, J. Development and testing of the OPLS all-atom force field on conformational energetics and properties of organic liquids. Journal of the American Chemical Society, 1996, 118(45): 11225-11236.
Kang, S. P., Lee, H., Lee, C. S., et al. Hydrate phase equilibria of the guest mixtures containing CO2, N2 and tetrahydrofuran. Fluid Phase Equilibria, 2001, 185(1): 101-109.
Kresse, G., Furthmüller, J. Efficiency of ab-initio total energy calculations for metals and semiconductors using a planewave basis set. Computational Materials Science, 1996, 6(1): 15-50.
Li, J., Ying, P., Liang, T., et al. Mechanical and thermal properties of graphyne-coated carbon nanotubes: A molecular dynamics simulation on one-dimensional all-carbon van der waals heterostructures. Physical Chemistry Chemical Physics, 2023, 25(12): 8651-8663.
Li, Y., Xiong, K., Qu, Y., et al. Effects of guest molecular occupancy and electric field on thermal conductivity of CO2 hydrates. The Journal of Chemical Physics, 2025, 163(8): 084504.
Liang, T., Jiang, W., Xu, K., et al. Pysed: A tool for extracting kinetic-energy-weighted phonon dispersion and lifetime from molecular dynamics simulations. Journal of Applied Physics, 2025, 138(7): 075101.
Liang, T., Zhou, M., Zhang, P., et al. Multilayer in-plane graphene/hexagonal boron nitride heterostructures: Insights into the interfacial thermal transport properties. International Journal of Heat and Mass Transfer, 2020, 151: 119395.
Lin, Y., Liu, Y., Xu, K., Li, T., Zhang, Z., Wu, J. Strengthening and weakening of methane hydrate by water vacancies. Advances in Geo-Energy Research, 2022, 6(1): 23-37.
Liu, J. J., Fu, R., Lin, Y. W., et al. Mechanical destabilization and cage transformations in water vacancy-contained CO2 hydrates. ACS Sustainable Chemistry & Engineering, 2022, 10(31): 10339-10350.
Liu, N., Hong, C., Liu, X. Effects of nanoparticles on CO2 hydrate thermal conductivity. CIESC Journal, 2017, 68(9): 5.
Liu, T.-S., Liu, N., Hong, C.-F. Molecular dynamics simulation of thermal conductivity of CO2 hydrate. Journal of Atomic and Molecular Physics, 2021, 38(4): 6.
Lu, C., Qin, X., Sun, J., Wang, R., Cai, J. Research progress and scientific challenges in the depressurization exploitation mechanism of clayey-silt natural gas hydrates in the northern South China Sea. Advances in Geo-Energy Research, 2023, 10(1): 14-20.
Luo, K., Shen, Y., Li, J., et al. Pressure-induced stability of methane hydrate from machine learning force field simulations. The Journal of Physical Chemistry C, 2023, 127(15): 7071-7077.
Martinez, J. A., Yilmaz, D. E., Liang, T., et al. Fitting empirical potentials: Challenges and methodologies. Current Opinion in Solid State and Materials Science, 2013, 17(6): 263-270.
Plimpton, S. Fast parallel algorithms for short-range molecular dynamics. Journal of Computational Physics, 1995, 117(1): 1-19.
Potoff, J. J., Siepmann, J. I. Vapor-liquid equilibria of mixtures containing alkanes, carbon dioxide, and nitrogen. AIChE Journal, 2001, 47(7): 1676-1682.
Schober, H., Itoh, H., Klapproth, A., et al. Guest-host coupling and anharmonicity in clathrate hydrates. The European Physical Journal E, 2003, 12(1): 41-49.
Shi, Q., Cao, P., Han, Z., et al. Role of guest molecules in the mechanical properties of clathrate hydrates. Crystal Growth & Design, 2018, 18(11): 6729-6741.
Song, Z., Li, Y., Shi, Q., et al. Diffusion, mechanical and thermal properties of sT hydrogen hydrate by machine learning potential. Journal of Physics: Condensed Matter, 2025, 37(11): 115102.
Sun, Z., Wang, Y., Li, W., et al. A high accuracy machinelearning potential model for Mo-Re binary alloy. Computational Materials Science, 2025, 254: 113870.
Takeuchi, F., Hiratsuka, M., Ohmura, R., et al. Water proton configurations in structures I, II, and H clathrate hydrate unit cells. The Journal of Chemical Physics, 2013, 138(12): 124504.
Targ, S., Almeida, D., Lyman, K. Resnet in resnet: Generalizing residual architectures. arXiv preprint arXiv:1603.08029, 2016.
Thomas, J. A., Turney, J. E., Iutzi, R. M., et al. Predicting phonon dispersion relations and lifetimes from the spectral energy density. Physical Review B, 2010, 81(8): 081411.
Tse, J. S., Klug, D. D., Zhao, J. Y., et al. Anharmonic motions of Kr in the clathrate hydrate. Nature Materials, 2005, 4(12): 917-921.
Udachin, K. A., Ratcliffe, C. I., Ripmeester, J. A. Structure, Dynamics and Ordering in Structure I Ether Clathrate Hydrates from Single-Crystal X-ray Diffraction and 2H NMR Spectroscopy. The Journal of Physical Chemistry B, 2007, 111(39): 11366-11372.
Wan, L., Liang, D., Li, D., et al. Characteristics of thermal conductivity and thermal diffusivity of carbon dioxide hydrate. CIESC Journal, 2016, 67(10): 7.
Wan, L. H., Liang, D. Q., Guan, J. A. Molecular dynamics study of thermal conduction in carbon dioxide hydrates. Advanced Materials Research, 2014, 1008-1009: 861-872.
Wang, H., Zhang, L. F., Han, J. Q., et al. Deepmd-kit: A deep learning package for many-body potential energy representation and molecular dynamics. Computer Physics Communications, 2018, 228: 178-184.
Warrier, P., Naveed Khan, M., Carreon, M. A., et al. Integrated gas hydrate-membrane system for natural gas purification. Journal of Renewable and Sustainable Energy, 2018, 10(3): 034701.
Xia, Y., Elsworth, D., Xu, S., et al. Pore-scale gas–water twophase flow and relative permeability characteristics of disassociated hydrate reservoir. Petroleum Science, 2025, 22(8): 3344-3356.
Xie, S. R., Rupp, M., Hennig, R. G. Ultra-fast interpretable machine-learning potentials. npj Computational Materials, 2023, 9(1): 162.
Xu, K., Hao, Y., Liang, T., et al. Accurate prediction of heat conductivity of water by a neuroevolution potential. The Journal of Chemical Physics, 2023, 158(20): 204114.
Xu, K., Liang, T., Zhang, Z., et al. Grain boundary and misorientation angle-dependent thermal transport in single-layer MoS2. Nanoscale, 2022, 14(4): 1241-1249.
Xu, K., Yang, L., Liu, J., et al. Mechanical properties of CH4CO2 heteroclathrate hydrates. Energy & Fuels, 2020, 34(11): 14368-14378.
Yin, Z., Zheng, J., Kim, H., et al. Hydrates for cold energy storage and transport: A review. Advances in Applied Energy, 2021, 2: 100022.
Ying, P. H., Liang, T., Xu, K., et al. Sub-micrometer phonon mean free paths in metal-organic frameworks revealed by machine learning molecular dynamics simulations. ACS Applied Materials & Interfaces, 2023, 15(30): 36412-36422.
Zeng, J., Liang, T., Zhang, J., et al. Correlating young’s modulus with high thermal conductivity in organic conjugated small molecules. Small, 2024, 20(21): 2309338.
Zhang, F., Ni, H., Wang, Y., et al. Molecular dynamics study on mechanical properties of CO2-N2 heteroclathrate hydrates. Crystal Growth & Design, 2023, 23(4): 2239-2247.
Zhang, J., Fu, H. -Q., Guo, M. -Z., et al. New insights into the deposition of natural gas hydrate on pipeline surfaces: A molecular dynamics simulation study. Petroleum Science, 2024a, 21(1): 694-704.
Zhang, Y., Liu, X. T., Shi, Q., et al. Mechanical properties and cage transformations in CO2-CH4 heterohydrates: A molecular dynamics and machine learning study. Journal of Physics D-Applied Physics, 2024b, 57(46): 465302.
Zhang, Y., Song, Z. X., Lin, Y. W., et al. Predicting mechanical properties of CO2 hydrates: Machine learning insights from molecular dynamics simulations. Journal of Physics-Condensed Matter, 2024c, 36(1): 015101.
Zhang, Y., Wang, H., Chen, W., et al. Dp-gen: A concurrent learning platform for the generation of reliable deep learning based potential energy models. Computer Physics Communications, 2020, 253: 107206.
Zhang, Z., Duan, Z. An optimized molecular potential for carbon dioxide. The Journal of Chemical Physics, 2005, 122(21): 214507.
Zhou, M., Liang, T., Wu, B., et al. Phonon transport in antisite-substituted hexagonal boron nitride nanosheets: A molecular dynamics study. Journal of Applied Physics, 2020, 128(23): 234304.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Author(s)
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.