Download file (5.05 MB)
Download as zip (4.49 MB)

Collection

Citation

Description:

Solid catalyst development has traditionally relied on trial-and-error approaches, limiting the broader application of valuable insights across different catalyst families. To overcome this fragmentation, we introduce a framework that integrates high-throughput experimentation (HTE) and automatic feature engineering (AFE) with active learning to acquire comprehensive catalyst knowledge. The framework is demonstrated for oxidative coupling of methane (OCM), where active learning is continued until the machine learning model achieves robustness for each of the BaO-, CaO-, La2O3-, TiO2-, and ZrO2-supported catalysts, with 333 catalysts newly tested. The resulting models are utilized to extract catalyst design rules, revealing key synergistic combinations in high-performing catalysts. Moreover, we propose a method for transferring knowledge between supports, showing that features refined on one support can improve predictions on others. This framework advances the understanding of catalyst design and promotes reliable machine learning.

Rights:

• Creative Commons BY-NC Attribution-NonCommercial 4.0 International
  

Keyword: Catalyst informatics, machine learning, high-throughput experimentation, descriptor, oxidative coupling of methane

Date published: 2025-12-31

Publisher: Taylor & Francis

Journal:

• Science and Technology of Advanced Materials (ISSN: 14686996) vol. 26 2454219

Funding:

Manuscript type: Author's version (Accepted manuscript)

MDR DOI: https://doi.org/10.48505/nims.5291

First published URL: https://doi.org/10.1080/14686996.2025.2454219

Related item:

Other identifier(s):

Contact agent:

Updated at: 2025-07-16 16:17:04 +0900

Published on MDR: 2025-01-24 08:30:14 +0900