Two-dimensional interaction parameter histograms as a simple and versatile nanoporous material representation for machine learning prediction of adsorption properties

Key Points

• This research aims to create a simple representation of nanoporous materials for improving machine learning predictions related to adsorption properties.
• Developed two-dimensional interaction parameter histograms as a representation method.
• Applied physics-based representations for nanoporous material screening.
• Utilized machine learning algorithms to predict adsorption performance of materials.
• Enhanced the accuracy of predictions for adsorption properties using the new material representation.
• Demonstrated applicability across various types of nanoporous materials including metal-organic frameworks.