Predicting mechanical properties of CO2 hydrates: machine learning insights from molecular dynamics simulations

Y Zhang and ZX Song and YW Lin and Q Shi and YC Hao and YQ Fu and JY Wu and ZS Zhang, JOURNAL OF PHYSICS-CONDENSED MATTER, 36, 015101 (2024).

DOI: 10.1088/1361-648X/acfa55

Understanding the mechanical properties of CO2 hydrate is crucial for its diverse sustainable applications such as CO2 geostorage and natural gas hydrate mining. In this work, classic molecular dynamics (MD) simulations are employed to explore the mechanical characteristics of CO2 hydrate with varying occupancy rates and occupancy distributions of guest molecules. It is revealed that the mechanical properties, including maximum stress, critical strain, and Young's modulus, are not only affected by the cage occupancy rate in both large 5(12)6(2) and small 5(12) cages, but also by the distribution of guest molecules within the cages. Specifically, the presence of vacancies in the 5(12)6(2) large cages significantly impacts the overall mechanical stability compared to 5(12) small cages. Furthermore, four distinct machine learning (ML) models trained using MD results are developed to predict the mechanical properties of CO2 hydrate with different cage occupancy rates and cage occupancy distributions. Through analyzing ML results, as-developed ML models highlight the importance of the distribution of guest molecules within the cages, as crucial contributor to the overall mechanical stability of CO2 hydrate. This study contributes new knowledge to the field by providing insights into the mechanical properties of CO2 hydrates and their dependence on cage occupancy rates and cage occupancy distributions. The findings have implications for the sustainable applications of CO2 hydrate, and as- developed ML models offer a practical framework for predicting the mechanical properties of CO2 hydrate in different scenarios.

Return to Publications page