EUVIMEDEUVIMED entdecken
Crossref

ResNet-assisted coarse-grained modeling of CH4–CO2 hydrates: Linking structural descriptors to interaction potentials

Gaoyang Luo iD, Yongchao Hao, Yongxiao Qu, Yuequn Fu, Zhisen Zhang iD, Jianyang Wu iD

The Journal of Chemical Physics · 07.09.2026 · 165 (9)

DOI: 10.1063/5.0336071 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of Chemical Physics, online erschienen am 01.09.2026. Verfasst von Gaoyang Luo und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics, Research Institute for Biomimetics and Soft Matter, Jiujiang Research Institute and Fujian Provincial Key Laboratory for Soft …. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: Natural Science Foundation of Fujian Province, National Natural Science Foundation of China, 111 Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gas hydrates are promising for energy storage, gas separation, and carbon sequestration. However, atomistic simulations of hydrate systems are computationally expensive at large scales. In this work, a machine-learning-assisted coarse-grained (CG) force field is developed for CH4–CO2 hydrate systems based on the Stillinger–Weber (SW) potential. A deep residual convolutional neural network (ResNet) is employed to establish a nonlinear mapping between structural descriptors and cross-species SW interaction parameters. The trained model achieves high accuracy (R2 > 0.99) and reproduces key structural and thermodynamic properties of the reference atomistic systems, including radial distribution functions, diffusion coefficients, interfacial tension, and gas solubility. With the enhanced computational efficiency of the CG model, large-scale simulations were conducted to explore hydrate dissociation and defect-controlled mechanical behavior. Results reveal distinct bubble nucleation and growth characteristics among CH4 hydrate, CO2 hydrate, and mixed hydrate systems, arising from differences in gas–water interactions. Structural defects, particularly in the water framework, weaken the hydrate lattice most significantly. The ResNet-assisted parameterization method provides an efficient strategy for constructing CG force fields for multicomponent hydrate systems, enabling simulations at scales beyond conventional atomistic methods.

Autor:innen und Institutionen

  • Department of Physics, Research Institute for Biomimetics and Soft Matter, Jiujiang Research Institute and Fujian Provincial Key Laboratory for Soft Functional Materials Research, Xiamen University, Xiamen 361005, Peopl…
  • Carbon-Rich Natural Gas Chemical Engineering Technology Center, China BlueChemical Ltd., Beijing 100010, China.

ORCID-Profile: Gaoyang Luo, Zhisen Zhang, Jianyang Wu

Förderung

  • Natural Science Foundation of Fujian Province
  • National Natural Science Foundation of China
  • 111 Project
  • China-Gansu Provincial Development Project

Zitieren

APA

Luo, G., Hao, Y., Qu, Y., Fu, Y., Zhang, Z., & Wu, J. (2026). ResNet-assisted coarse-grained modeling of CH4–CO2 hydrates: Linking structural descriptors to interaction potentials. The Journal of Chemical Physics, 165(9). https://doi.org/10.1063/5.0336071

Vancouver

Luo G, Hao Y, Qu Y, Fu Y, Zhang Z, Wu J. ResNet-assisted coarse-grained modeling of CH4–CO2 hydrates: Linking structural descriptors to interaction potentials. The Journal of Chemical Physics. 2026;165(9). doi:10.1063/5.0336071

BibTeX
@article{Luo2026,
  author = {Luo, Gaoyang and Hao, Yongchao and Qu, Yongxiao and Fu, Yuequn and Zhang, Zhisen and Wu, Jianyang},
  title = {ResNet-assisted coarse-grained modeling of CH4–CO2 hydrates: Linking structural descriptors to interaction potentials},
  journal = {The Journal of Chemical Physics},
  year = {2026},
  volume = {165},
  number = {9},
  doi = {10.1063/5.0336071}
}
Kostenlos starten →