An interpretable machine learning framework for prediction of adsorption energies and generative design of active sites on arbitrary catalysts

Matthew S. Johnson; Richard Henry West; Judit Zádor

doi:10.1039/d5fd00143a

An interpretable machine learning framework for prediction of adsorption energies and generative design of active sites on arbitrary catalysts

Faraday Discussions 2026

View at publisher

Authors: Matthew S. Johnson, Richard Henry West, Judit Zádor

DOI: 10.1039/d5fd00143a

Cited by: 1

References: 37

Abstract

We present a highly interpretable and efficient machine learning framework for predictive and generative modeling of adsorption energies on surfaces using subgraph isomorphic decision trees (SIDTs).

Fields of Study & Subjects

Machine Learning in Materials Science Catalysis and Oxidation Reactions CO2 Reduction Techniques and Catalysts

Publication details

Journal / source: Faraday Discussions
Publisher: Royal Society of Chemistry (RSC)
Volume: 267
Pages: 386–404
Publication date: 1 January 2026
Language: EN

References 37