|
JAIST Repository >
School of Transdisciplinary Science >
Conference Papers >
Conference Papers >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10119/18175
|
| Title: | High-Throughput Screening and Literature Data Driven Machine Learning Assisting Discovery of La_2O_3-based Catalysts for Low-Temperature Oxidative Coupling of Methane |
| Authors: | Nishimura, Shun |
| Issue Date: | 2022-12-12 |
| Publisher: | Japan Cooperation Center for Petroleum and Sustainable Energy |
| Magazine name: | 31st Annual Saudi-Japan Symposium 2022 |
| Abstract: | Three-element component La_2O_3-based catalysts for the oxidative coupling of methane (OCM) are examined for this study using machine learning (ML) approaches such as support vector regression (SVR) and random forest regression (RFR). This validation was conducted while assuming that the three-element component (M1–M2–M3) resulting in high C_2 yield predicted by ML is helpful to ascertain the appropriate component to promote the unique nature of La_2O_3 itself: the low-temperature OCM feature. The combined use of an open-source high-throughput screening (HTS) database and SVR assisted the discovery of three-element component La_2O_3-based OCM catalysts of 11 types with C_2 yield (> 5.0%) appearing at 450℃. Then, to predict more unique component La_2O_3-based OCM catalysts from the outer field of screening elements at HTS experimentation, HTS and literature databases were applied for SVR and RFR. This combined approach discovered 11 additional combinations of three-element component La_2O_3-based OCM catalysts affording C_2 yield (> 5.0%) appearing at 450℃. |
| Rights: | This is the author's version of the work. Copyright (C) 2022 JCCP. Shun Nishimura, 31st Annual Saudi-Japan Symposium. This material is posted here by permission of JCCP 国際石油・ガス・持続可能エネルギー協力機関(Japan Cooperation Center for Petroleum and Sustainable Energy). |
| URI: | http://hdl.handle.net/10119/18175 |
| Material Type: | author |
| Appears in Collections: | d11-1. 会議発表論文 (Conference Papers)
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| 1020_sn7.pdf | | 403Kb | Adobe PDF | View/Open |
|
All items in DSpace are protected by copyright, with all rights reserved.
|
