Accelerated design of nickel-cobalt based catalysts for CO2 hydrogenation with human-in-the-loop active machine learning

2024/01/01 by Yasemen Kuddusi, Maarten R. Dobbelaere, Kevin M. Van Geem +1 · 1 voice
Materials Science · Chemical Engineering · #Machine Learning in Materials Science #Catalytic Processes in Materials Science #Catalysts for Methane Reforming

paper · pdf · doi:10.1039/d4cy00873a

openalex publication_date 2024/01/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/03

Abstract

> 0.9) for untested catalysts and reaction conditions. New experiments and catalysts were selected with this methodology, leading to experimental conditions that improved the methane space-time yield by nearly 50% in comparison to the previously obtained maximum in the dataset. Interpretation of the model predictions unveiled the effect of each catalyst descriptor and reaction condition on the outcome. Particularly, the strong predicted inverse trend between the calcination temperature and the catalytic activity was validated experimentally, and characterization implied an underlying structure-performance relationship. Finally, it is demonstrated that the deployed active learning model is excellently suited to predict and fit kinetic trends with a minimal amount of data. This data-driven framework is a first step to faster, model-based, and interpretable design of catalysts and holds promise for broader applications across catalytic processes.

Citations

• Curve Fitting Analysis of ESCA Ni 2p Spectra of Nickel-Oxygen Compounds and Ni/Al 2 O 3 Catalysts
• A Survey of Methods for Explaining Black Box Models
• From local explanations to global understanding with explainable AI for trees
• The reverse water gas shift reaction: a process systems engineering perspective

Discussions

• What we learned with this approach was that with "smarter" experimentation using available equiment, we had the access to a very large search space of heterogeneous catalysts while needing only minima [bsky, 0 points, 0 comments]