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

Molecular Systems Design & Engineering 2026 Open access

Read full text
Authors: Tatiane Gercina de Vilas, Jair Fernando Fajardo-Rojas, Omar Mansurov, Ruby Devaisher, Eric Toberer, Diego Gomez-Gualdron
DOI: 10.1039/d6me00034g
Cited by: 1
References: 90

Abstract

We present a simple, scalable, physics-based porous material representation for ML models to predict adsorption properties. We envision this representation will help democratize the ML-assisted design and development of porous materials.

Fields of Study & Subjects

Metal-Organic Frameworks: Synthesis and Applications Machine Learning in Materials Science Mesoporous Materials and Catalysis

Publication details

Journal / source
Molecular Systems Design & Engineering
Publisher
Royal Society of Chemistry (RSC)
Volume
11
Issue
8
Pages
722–737
Publication date
1 January 2026
Language
EN