Abstract
This study determined the machine-learning (ML) models for the discovery of efficient metal-organic framework (MOF) materials to improve hydrogen storage. We selected a sample of 5047 MOFs from the CoRE MOFs database and employed grand canonical Monte Carlo simulation results from the Hydrogen Materials Advanced Research Consortium (HyMARC) data center to evaluate the useable gravimetric (UG) capacities and useable volumetric (UV) capacities of these materials. ML models were employed to analyze the data. Seven key features were focused upon density, gravimetric surface area, volumetric surface area, void fraction (VF), pore volume (PV), largest cavity diameter, and pore-limiting diameter, and used to predict the UG and UV. The CatBoost model provided the most accurate predictions. In addition, SHapley Additive exPlanations analysis based on the CatBoost model revealed that the PV and VF significantly affected the hydrogen storage performance. A comprehensive analysis confirmed that the CatBoost model exhibited the highest prediction accuracy and identified specific combinations of structural features that significantly improved the hydrogen storage efficiency of the MOFs.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
