A Data-Science Approach to Experimental Catalyst Discovery: Integrating Exploration, Exploitation, and Serendipity

TAKAHASHI Keisuke

Department of Chemistry

May. 27, 2025

本研究のイメージ。ハイスループット実験データを基に学習した AI によって探索・活⽤・予期せぬ発⾒をバランスした触媒推薦を⾏います。推薦された触媒はハイスループット実験によって評価されるという再帰的なループによって、AIは⾼性能触媒の推薦効率を上げていきます。

Joint press release (in Japanese) by Japan Advanced Institute of Science and Technology and Hokkaido University

Abstract
Predicting the performance of heterogeneous catalysts is difficult because it involves complex interactions and unknown elementary reactions; hence, traditional catalyst development relies on trial and error. Machine learning offers a structured approach to address these issues. However, this approach is limited by challenges such as descriptor design, sparse data, and context-dependent interactions. In this study, two machine learning systems were developed to address these challenges in catalyst discovery: a recommender system that balances exploration and exploitation, and a serendipiter that identifies unexpected discoveries for the recommender─catalysts expected to exhibit high performance despite being predicted as most likely non-high-performing. These systems were tested on the oxidative coupling of methane, ……

Read the original article on ACS Catalysis

Article inforamation
Sunao Nakanowatari, Keisuke Takahashi, Hieu Chi Dam, Toshiaki Taniike
A Data-Science Approach to Experimental Catalyst Discovery: Integrating Exploration, Exploitation, and Serendipity, ACS Catalysis, 2025, 15, 8691−8705
DOI: 10.1021/acscatal.5c00100