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

January 1, 2026Faraday Discussions

An Interpretable Machine Learning Framework for Prediction of Adsorption Energies and Generative Design of Active Sites on Arbitrary Catalysts

View Full Paper

Ask AI

Bookmark

Share

Key Points

The aim is to develop a machine learning framework that accurately predicts adsorption energies and aids in designing active sites on catalysts.
Utilized subgraph isomorphic decision trees for modeling
Extracted graph representations of catalyst surfaces
Implemented generative design capabilities for active sites
Ensured interpretability of the machine learning models
Achieved high accuracy in predicting adsorption energies
Demonstrated effective design of active sites for improved catalytic performance
Provided a toolkit for easier interpretation of results

Implication

Reports an interpretable machine learning framework modeling adsorption energies on catalysts, suggesting improved design of active sites.

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). Extracting graph representations of...

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Johnson et al. (2026) studied this question.

synapsesocial.com/papers/698979a6f0ec2af6756e7754 https://doi.org/10.1039/d5fd00143a

View Full Paper

Ask AI

Bookmark

Share

An Interpretable Machine Learning Framework for Prediction of Adsorption Energies and Generative Design of Active Sites on Arbitrary Catalysts

Key Points

Implication

Abstract

Discussion

Cite This Study

An Interpretable Machine Learning Framework for Prediction of Adsorption Energies and Generative Design of Active Sites on Arbitrary Catalysts

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

More related papers

More from Faraday Discussions

Keep reading

More related papers

More from Faraday Discussions