JAIST Repository >
d. 融合科学系 >
d10. 学術雑誌論文等 >
d10-1. 雑誌掲載論文 >

このアイテムの引用には次の識別子を使用してください: http://hdl.handle.net/10119/18866

タイトル: High-Throughput Screening and Literature Data Driven Machine Learning Assisting Investigation of Multi-component La2O3-based Catalysts for Oxidative Coupling of Methane
著者: Nishimura, Shun
Le, Son Dinh
Miyazato, Itsuki
Fujima, Jun
Taniike, Toshiaki
Ohyama, Junya
Takahashi, Keisuke
発行日: 2022-02-10
出版者: Royal Society of Chemistry
誌名: Catalysis Science & Technology
巻: 12
号: 9
開始ページ: 2766
終了ページ: 2774
DOI: 10.1039/D1CY02206G
抄録: Multi-component La2O3-based catalysts for oxidative coupling of methane (OCM) were designed based on high-throughput screening (HTS) and literature datasets with multi-output machine learning (ML) approaches including random forest regression (RFR), support vector regression (SVR), Gaussian process regression (Bayesian), and Item set mining (LCM). Combined use of HTS data and SVR successively assisted the finding of multi-component La2O3-based OCM catalysts of 11 types in 20 validations with C2 yields appearing at 450°C based on indirect ML assistance. The appropriate multi-component predicted from ML contributes to determination of a characteristic feature of the lower onset temperature for a La2O3-based OCM catalyst. The LCM application on the SVR extended HTS data area supports spotting of the effective elements in the HTS area. However, a challenging subject remains: multi-component La2O3-based catalysts of two types afford effective C2 yield (>5.0%) at 450°C, as inferred from the 20 selected types of catalyst validation. To predict unique multi-component La2O3-based OCM catalysts further, a combination of HTS and literature data was applied for four ML approaches. These were helpful to discover 17 additional combinations of multi-component La2O3-based catalysts affording effective C2 yield (>5.0%) at 450°C in the 38 selected types of predictions. Completely, 30 multi-component La2O3-based catalysts of new types with C2 yield greater than 5.0% at 450°C in CH4/O2 = 2.0 condition were found based on the indirect ML assistance driven by HTS and literature data.
Rights: Copyright (C) 2022 Royal Society of Chemistry. Shun Nishimura, Son Dinh Le, Itsuki Miyazato, Jun Fujima, Toshiaki Taniike, Junya Ohyama, and Keisuke Takahashi, Catalysis Science & Technology, 2022, 12(9), 2766-2774. https://doi.org/10.1039/D1CY02206G - Reproduced by permission of the Royal Society of Chemistry
URI: http://hdl.handle.net/10119/18866
資料タイプ: author
出現コレクション:d10-1. 雑誌掲載論文 (Journal Articles)

このアイテムのファイル:

ファイル 記述 サイズ形式
S-NISHIMURA-T-0501-2.pdf588KbAdobe PDF見る/開く

当システムに保管されているアイテムはすべて著作権により保護されています。

 


お問い合わせ先 : 北陸先端科学技術大学院大学 研究推進課図書館情報係