DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ren, Zekun | ko |
dc.contributor.author | Tian, Siyu Isaac Parker | ko |
dc.contributor.author | Noh, Juhwan | ko |
dc.contributor.author | Oviedo, Felipe | ko |
dc.contributor.author | Xing, Guangzong | ko |
dc.contributor.author | Li, Jiali | ko |
dc.contributor.author | Liang, Qiaohao | ko |
dc.contributor.author | Zhu, Ruiming | ko |
dc.contributor.author | Aberle, Armin G. | ko |
dc.contributor.author | Sun, Shijing | ko |
dc.contributor.author | Wang, Xiaonan | ko |
dc.contributor.author | Liu, Yi | ko |
dc.contributor.author | Li, Qianxiao | ko |
dc.contributor.author | Jayavelu, Senthilnath | ko |
dc.contributor.author | Hippalgaonkar, Kedar | ko |
dc.contributor.author | Jung, Yousung | ko |
dc.contributor.author | Buonassisi, Tonio | ko |
dc.date.accessioned | 2022-01-24T06:41:24Z | - |
dc.date.available | 2022-01-24T06:41:24Z | - |
dc.date.created | 2022-01-24 | - |
dc.date.created | 2022-01-24 | - |
dc.date.created | 2022-01-24 | - |
dc.date.created | 2022-01-24 | - |
dc.date.created | 2022-01-24 | - |
dc.date.issued | 2022-01 | - |
dc.identifier.citation | MATTER, v.5, no.1, pp.314 - 335 | - |
dc.identifier.issn | 2590-2393 | - |
dc.identifier.uri | http://hdl.handle.net/10203/292010 | - |
dc.description.abstract | Realizing general inverse design could greatly accelerate the discovery of new materials with user-defined properties. However, stateof-the-art generative models tend to be limited to a specific composition or crystal structure. Herein, we present a framework capable of general inverse design (not limited to a given set of elements or crystal structures), featuring a generalized invertible representation that encodes crystals in both real and reciprocal space, and a property-structured latent space from a variational autoencoder (VAE). In three design cases, the framework generates 142 new crystals with user-defined formation energies, bandgap, thermoelectric (TE) power factor, and combinations thereof. These generated crystals, absent in the training database, are validated by first-principles calculations. The success rates (number of first-principles-validated target-satisfying crystals/number of designed crystals) ranges between 7.1% and 38.9%. These results represent a significant step toward property-driven general inverse design using generative models, although practical challenges remain when coupled with experimental synthesis. | - |
dc.language | English | - |
dc.publisher | ELSEVIER | - |
dc.title | An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties | - |
dc.type | Article | - |
dc.identifier.wosid | 000742104900004 | - |
dc.identifier.scopusid | 2-s2.0-85121929536 | - |
dc.type.rims | ART | - |
dc.citation.volume | 5 | - |
dc.citation.issue | 1 | - |
dc.citation.beginningpage | 314 | - |
dc.citation.endingpage | 335 | - |
dc.citation.publicationname | MATTER | - |
dc.identifier.doi | 10.1016/j.matt.2021.11.032 | - |
dc.contributor.localauthor | Jung, Yousung | - |
dc.contributor.nonIdAuthor | Ren, Zekun | - |
dc.contributor.nonIdAuthor | Tian, Siyu Isaac Parker | - |
dc.contributor.nonIdAuthor | Oviedo, Felipe | - |
dc.contributor.nonIdAuthor | Xing, Guangzong | - |
dc.contributor.nonIdAuthor | Li, Jiali | - |
dc.contributor.nonIdAuthor | Liang, Qiaohao | - |
dc.contributor.nonIdAuthor | Zhu, Ruiming | - |
dc.contributor.nonIdAuthor | Aberle, Armin G. | - |
dc.contributor.nonIdAuthor | Sun, Shijing | - |
dc.contributor.nonIdAuthor | Wang, Xiaonan | - |
dc.contributor.nonIdAuthor | Liu, Yi | - |
dc.contributor.nonIdAuthor | Li, Qianxiao | - |
dc.contributor.nonIdAuthor | Jayavelu, Senthilnath | - |
dc.contributor.nonIdAuthor | Hippalgaonkar, Kedar | - |
dc.contributor.nonIdAuthor | Buonassisi, Tonio | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | general inverse design | - |
dc.subject.keywordAuthor | generalized crystallographic representation | - |
dc.subject.keywordAuthor | generative model | - |
dc.subject.keywordAuthor | invertible crystallographic representation | - |
dc.subject.keywordAuthor | machine learning | - |
dc.subject.keywordAuthor | MAP2: Benchmark | - |
dc.subject.keywordAuthor | property-structured latent space | - |
dc.subject.keywordAuthor | solid-state materials | - |
dc.subject.keywordAuthor | thermoelectrics | - |
dc.subject.keywordAuthor | variational autoencoder | - |
dc.subject.keywordPlus | SOLAR-CELLS | - |
dc.subject.keywordPlus | MACHINE | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.