Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties
The experimental search for new thermoelectric materials remains largely confined to a limited set of successful chemical and structural families, such as chalcogenides, skutterudites, and Zintl phases. In principle, computational tools such as density functional theory (DFT) offer the possibility o...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIP Publishing LLC
2016-05-01
|
| Series: | APL Materials |
| Online Access: | http://dx.doi.org/10.1063/1.4952607 |
| _version_ | 1819101916220620800 |
|---|---|
| author | Michael W. Gaultois Anton O. Oliynyk Arthur Mar Taylor D. Sparks Gregory J. Mulholland Bryce Meredig |
| author_facet | Michael W. Gaultois Anton O. Oliynyk Arthur Mar Taylor D. Sparks Gregory J. Mulholland Bryce Meredig |
| author_sort | Michael W. Gaultois |
| collection | DOAJ |
| description | The experimental search for new thermoelectric materials remains largely confined to a limited set of successful chemical and structural families, such as chalcogenides, skutterudites, and Zintl phases. In principle, computational tools such as density functional theory (DFT) offer the possibility of rationally guiding experimental synthesis efforts toward very different chemistries. However, in practice, predicting thermoelectric properties from first principles remains a challenging endeavor [J. Carrete et al., Phys. Rev. X 4, 011019 (2014)], and experimental researchers generally do not directly use computation to drive their own synthesis efforts. To bridge this practical gap between experimental needs and computational tools, we report an open machine learning-based recommendation engine (http://thermoelectrics.citrination.com) for materials researchers that suggests promising new thermoelectric compositions based on pre-screening about 25 000 known materials and also evaluates the feasibility of user-designed compounds. We show this engine can identify interesting chemistries very different from known thermoelectrics. Specifically, we describe the experimental characterization of one example set of compounds derived from our engine, RE12Co5Bi (RE = Gd, Er), which exhibits surprising thermoelectric performance given its unprecedentedly high loading with metallic d and f block elements and warrants further investigation as a new thermoelectric material platform. We show that our engine predicts this family of materials to have low thermal and high electrical conductivities, but modest Seebeck coefficient, all of which are confirmed experimentally. We note that the engine also predicts materials that may simultaneously optimize all three properties entering into zT; we selected RE12Co5Bi for this study due to its interesting chemical composition and known facile synthesis. |
| first_indexed | 2024-12-22T01:26:16Z |
| format | Article |
| id | doaj.art-d75a4df39e484a6fa29aaeb5731efa9f |
| institution | Directory Open Access Journal |
| issn | 2166-532X |
| language | English |
| last_indexed | 2024-12-22T01:26:16Z |
| publishDate | 2016-05-01 |
| publisher | AIP Publishing LLC |
| record_format | Article |
| series | APL Materials |
| spelling | doaj.art-d75a4df39e484a6fa29aaeb5731efa9f2022-12-21T18:43:36ZengAIP Publishing LLCAPL Materials2166-532X2016-05-0145053213053213-1110.1063/1.4952607015693APMPerspective: Web-based machine learning models for real-time screening of thermoelectric materials propertiesMichael W. Gaultois0Anton O. Oliynyk1Arthur Mar2Taylor D. Sparks3Gregory J. Mulholland4Bryce Meredig5Department of Chemistry, University of Cambridge, Cambridge CB2 1EW, United KingdomDepartment of Chemistry, University of Alberta, Edmonton, Alberta T6G 2G2, CanadaDepartment of Chemistry, University of Alberta, Edmonton, Alberta T6G 2G2, CanadaDepartment of Materials Science and Engineering, University of Utah, Salt Lake City, Utah 84112, USACitrine Informatics, Redwood City, California 94063, USACitrine Informatics, Redwood City, California 94063, USAThe experimental search for new thermoelectric materials remains largely confined to a limited set of successful chemical and structural families, such as chalcogenides, skutterudites, and Zintl phases. In principle, computational tools such as density functional theory (DFT) offer the possibility of rationally guiding experimental synthesis efforts toward very different chemistries. However, in practice, predicting thermoelectric properties from first principles remains a challenging endeavor [J. Carrete et al., Phys. Rev. X 4, 011019 (2014)], and experimental researchers generally do not directly use computation to drive their own synthesis efforts. To bridge this practical gap between experimental needs and computational tools, we report an open machine learning-based recommendation engine (http://thermoelectrics.citrination.com) for materials researchers that suggests promising new thermoelectric compositions based on pre-screening about 25 000 known materials and also evaluates the feasibility of user-designed compounds. We show this engine can identify interesting chemistries very different from known thermoelectrics. Specifically, we describe the experimental characterization of one example set of compounds derived from our engine, RE12Co5Bi (RE = Gd, Er), which exhibits surprising thermoelectric performance given its unprecedentedly high loading with metallic d and f block elements and warrants further investigation as a new thermoelectric material platform. We show that our engine predicts this family of materials to have low thermal and high electrical conductivities, but modest Seebeck coefficient, all of which are confirmed experimentally. We note that the engine also predicts materials that may simultaneously optimize all three properties entering into zT; we selected RE12Co5Bi for this study due to its interesting chemical composition and known facile synthesis.http://dx.doi.org/10.1063/1.4952607 |
| spellingShingle | Michael W. Gaultois Anton O. Oliynyk Arthur Mar Taylor D. Sparks Gregory J. Mulholland Bryce Meredig Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties APL Materials |
| title | Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties |
| title_full | Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties |
| title_fullStr | Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties |
| title_full_unstemmed | Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties |
| title_short | Perspective: Web-based machine learning models for real-time screening of thermoelectric materials properties |
| title_sort | perspective web based machine learning models for real time screening of thermoelectric materials properties |
| url | http://dx.doi.org/10.1063/1.4952607 |
| work_keys_str_mv | AT michaelwgaultois perspectivewebbasedmachinelearningmodelsforrealtimescreeningofthermoelectricmaterialsproperties AT antonooliynyk perspectivewebbasedmachinelearningmodelsforrealtimescreeningofthermoelectricmaterialsproperties AT arthurmar perspectivewebbasedmachinelearningmodelsforrealtimescreeningofthermoelectricmaterialsproperties AT taylordsparks perspectivewebbasedmachinelearningmodelsforrealtimescreeningofthermoelectricmaterialsproperties AT gregoryjmulholland perspectivewebbasedmachinelearningmodelsforrealtimescreeningofthermoelectricmaterialsproperties AT brycemeredig perspectivewebbasedmachinelearningmodelsforrealtimescreeningofthermoelectricmaterialsproperties |