|
|
Hokkaido University Collection of Scholarly and Academic Papers >
Institute for Catalysis >
Peer-reviewed Journal Articles, etc >
Analysis of Updated Literature Data up to 2019 on the Oxidative Coupling of Methane Using an Extrapolative Machine-Learning Method to Identify Novel Catalysts
| Title: | Analysis of Updated Literature Data up to 2019 on the Oxidative Coupling of Methane Using an Extrapolative Machine-Learning Method to Identify Novel Catalysts |
| Authors: | Mine, Shinya Browse this author | | Takao, Motoshi Browse this author | | Yamaguchi, Taichi Browse this author | | Toyao, Takashi Browse this author →KAKEN DB | | Maeno, Zen Browse this author →KAKEN DB | | Siddiki, S. M. A. Hakim Browse this author →KAKEN DB | | Takakusagi, Satoru Browse this author →KAKEN DB | | Shimizu, Ken-ichi Browse this author →KAKEN DB | | Takigawa, Ichigaku Browse this author →KAKEN DB |
| Keywords: | Machine learning | | Catalysis informatics | | Oxidative coupling of methane (OCM) | | SHapley Additive exPlanations (SHAP) | | Sequential model-based optimization (SMBO) |
| Issue Date: | 1-Sep-2021 |
| Publisher: | Wiley-Blackwell |
| Journal Title: | ChemCatChem |
| Volume: | 13 |
| Issue: | 16 |
| Start Page: | 3636 |
| End Page: | 3655 |
| Publisher DOI: | 10.1002/cctc.202100495 |
| Abstract: | We have constructed and analyzed an updated dataset consisting of 4759 experimental datapoints for the oxidative coupling of methane (OCM) reaction based on literature data reported before 2020 (similar to 2019) using machine learning (ML) methods. Several ML methods, including random forest regression (RFR), extra trees regression (ETR), and gradient boosting regression with XGBoost (XGB), were used in conjunction with our proposed approach, in which elemental features are used as input representations rather than inputting the catalyst compositions directly. A recent research trend, namely, the extensive exploration of Mn/Na2WO4/SiO2 catalyst systems in recent years due to their high activity and durability, was clearly reflected in the dataset analysis. An ML model for the prediction of the reaction outcome (C-2 yield) was success- fully developed, and feature importance scores and SHapley Additive exPlanations (SHAP) values were calculated based on ETR and XGB, respectively, to identify the input variables with the greatest influence on the catalyst performance and observe how these important variables affect the C-2, yield in the OCM. The discovery and optimization of catalytic processes using ML as a "surrogate" model were explored, and promising catalytic system candidates for the OCM reaction were identified. Notably, the developed ML model predicted catalysts containing elements that do not appear in the OCM dataset. This clearly demonstrates desirably high potential of our ML model to enable extrapolative predictions for ML-aided future catalysis research. |
| Type: | article |
| URI: | http://hdl.handle.net/2115/82570 |
| Appears in Collections: | 触媒科学研究所 (Institute for Catalysis) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)
|
|
