Use of metamodels for rapid discovery of narrow bandgap oxide photocatalysts
Summary: New photocatalysts are traditionally identified through trial-and-error methods. Machine learning has shown considerable promise for improving the efficiency of photocatalyst discovery from a large potential pool. Here, we describe a multi-step, target-driven consensus method using a stacki...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-09-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004221010361 |
| _version_ | 1818364458658955264 |
|---|---|
| author | Haoxin Mai Tu C. Le Takashi Hisatomi Dehong Chen Kazunari Domen David A. Winkler Rachel A. Caruso |
| author_facet | Haoxin Mai Tu C. Le Takashi Hisatomi Dehong Chen Kazunari Domen David A. Winkler Rachel A. Caruso |
| author_sort | Haoxin Mai |
| collection | DOAJ |
| description | Summary: New photocatalysts are traditionally identified through trial-and-error methods. Machine learning has shown considerable promise for improving the efficiency of photocatalyst discovery from a large potential pool. Here, we describe a multi-step, target-driven consensus method using a stacking meta-learning algorithm that robustly predicts bandgaps and H2 evolution activities of photocatalysts. Trained on small datasets, these models can rapidly screen a large space (>10 million materials) to identify promising, non-toxic compounds as candidate water splitting photocatalysts. Two effective compounds and two controls possessing optimal bandgap values (∼2 eV) but not photoactivity as predicted by the models were synthesized. Their experimentally measured bandgaps and H2 evolution activities were consistent with the predictions. Conspicuously, the two compounds with strong photoactivities under UV and visible light are promising visible-light-driven water splitting photocatalysts. This study demonstrates the power of machine learning and the potential of big data to accelerate discovery of next-generation photocatalysts. |
| first_indexed | 2024-12-13T22:04:42Z |
| format | Article |
| id | doaj.art-dcc5430c83ac485ca28d3d79e07aef57 |
| institution | Directory Open Access Journal |
| issn | 2589-0042 |
| language | English |
| last_indexed | 2024-12-13T22:04:42Z |
| publishDate | 2021-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | iScience |
| spelling | doaj.art-dcc5430c83ac485ca28d3d79e07aef572022-12-21T23:29:54ZengElsevieriScience2589-00422021-09-01249103068Use of metamodels for rapid discovery of narrow bandgap oxide photocatalystsHaoxin Mai0Tu C. Le1Takashi Hisatomi2Dehong Chen3Kazunari Domen4David A. Winkler5Rachel A. Caruso6Applied Chemistry and Environmental Science, School of Science, STEM College, RMIT University, GPO Box 2476, Melbourne, VIC 3001, AustraliaSchool of Engineering, STEM College, RMIT University, GPO Box 2476, Melbourne, VIC 3001, AustraliaResearch Initiative for Supra-Materials (RISM), Shinshu University, 4-17-1 Wakasato, Nagano 380-8553, JapanApplied Chemistry and Environmental Science, School of Science, STEM College, RMIT University, GPO Box 2476, Melbourne, VIC 3001, Australia; Corresponding authorResearch Initiative for Supra-Materials (RISM), Shinshu University, 4-17-1 Wakasato, Nagano 380-8553, Japan; Office of University Professors, the University of Tokyo, 2-11-16 Yayoi, Bunkyo-ku, Tokyo 113-8656, JapanMonash Institute of Pharmaceutical Sciences, Monash University, Parkville, VIC 3052, Australia; School of Biochemistry and Genetics, La Trobe University, Kingsbury Drive, 3042 Bundoora, Australia; School of Pharmacy, University of Nottingham, NG7 2RD Nottingham, UK; Corresponding authorApplied Chemistry and Environmental Science, School of Science, STEM College, RMIT University, GPO Box 2476, Melbourne, VIC 3001, Australia; Corresponding authorSummary: New photocatalysts are traditionally identified through trial-and-error methods. Machine learning has shown considerable promise for improving the efficiency of photocatalyst discovery from a large potential pool. Here, we describe a multi-step, target-driven consensus method using a stacking meta-learning algorithm that robustly predicts bandgaps and H2 evolution activities of photocatalysts. Trained on small datasets, these models can rapidly screen a large space (>10 million materials) to identify promising, non-toxic compounds as candidate water splitting photocatalysts. Two effective compounds and two controls possessing optimal bandgap values (∼2 eV) but not photoactivity as predicted by the models were synthesized. Their experimentally measured bandgaps and H2 evolution activities were consistent with the predictions. Conspicuously, the two compounds with strong photoactivities under UV and visible light are promising visible-light-driven water splitting photocatalysts. This study demonstrates the power of machine learning and the potential of big data to accelerate discovery of next-generation photocatalysts.http://www.sciencedirect.com/science/article/pii/S2589004221010361chemistrycatalysiscomputational chemistry |
| spellingShingle | Haoxin Mai Tu C. Le Takashi Hisatomi Dehong Chen Kazunari Domen David A. Winkler Rachel A. Caruso Use of metamodels for rapid discovery of narrow bandgap oxide photocatalysts iScience chemistry catalysis computational chemistry |
| title | Use of metamodels for rapid discovery of narrow bandgap oxide photocatalysts |
| title_full | Use of metamodels for rapid discovery of narrow bandgap oxide photocatalysts |
| title_fullStr | Use of metamodels for rapid discovery of narrow bandgap oxide photocatalysts |
| title_full_unstemmed | Use of metamodels for rapid discovery of narrow bandgap oxide photocatalysts |
| title_short | Use of metamodels for rapid discovery of narrow bandgap oxide photocatalysts |
| title_sort | use of metamodels for rapid discovery of narrow bandgap oxide photocatalysts |
| topic | chemistry catalysis computational chemistry |
| url | http://www.sciencedirect.com/science/article/pii/S2589004221010361 |
| work_keys_str_mv | AT haoxinmai useofmetamodelsforrapiddiscoveryofnarrowbandgapoxidephotocatalysts AT tucle useofmetamodelsforrapiddiscoveryofnarrowbandgapoxidephotocatalysts AT takashihisatomi useofmetamodelsforrapiddiscoveryofnarrowbandgapoxidephotocatalysts AT dehongchen useofmetamodelsforrapiddiscoveryofnarrowbandgapoxidephotocatalysts AT kazunaridomen useofmetamodelsforrapiddiscoveryofnarrowbandgapoxidephotocatalysts AT davidawinkler useofmetamodelsforrapiddiscoveryofnarrowbandgapoxidephotocatalysts AT rachelacaruso useofmetamodelsforrapiddiscoveryofnarrowbandgapoxidephotocatalysts |