Learning Centre

Compositional engineering of perovskites with machine learning

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.author Laakso, Jarno
dc.contributor.author Todorovic, Milica
dc.contributor.author Li, Jingrui
dc.contributor.author Zhang, Guo-Xu
dc.contributor.author Rinke, Patrick
dc.date.accessioned 2022-12-14T10:17:28Z
dc.date.available 2022-12-14T10:17:28Z
dc.date.issued 2022-11-07
dc.identifier.citation Laakso , J , Todorovic , M , Li , J , Zhang , G-X & Rinke , P 2022 , ' Compositional engineering of perovskites with machine learning ' , Physical Review Materials , vol. 6 , no. 11 , 113801 , pp. 1-10 . https://doi.org/10.1103/PhysRevMaterials.6.113801 en
dc.identifier.issn 2475-9953
dc.identifier.other PURE UUID: 7a567b69-6c52-4372-acb4-fc1e68207967
dc.identifier.other PURE ITEMURL: https://research.aalto.fi/en/publications/7a567b69-6c52-4372-acb4-fc1e68207967
dc.identifier.other PURE FILEURL: https://research.aalto.fi/files/94628387/Compositional_engineering_of_perovskites_with_machine_learning.pdf
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/118166
dc.description.abstract Perovskites are promising materials candidates for optoelectronics, but their commercialization is hindered by toxicity and materials instability. While compositional engineering can mitigate these problems by tuning perovskite properties, the enormous complexity of the perovskite materials space aggravates the search for an optimal optoelectronic material. We conducted compositional space exploration through Monte Carlo (MC) convex hull sampling, which we made tractable with machine learning (ML). The ML model learns from density functional theory calculations of perovskite atomic structures, and can be used for quick predictions of energies, atomic forces, and stresses. We employed it in structural relaxations combined with MC sampling to gain access to low-energy structures and compute the convex hull for CsPb(Br1−xClx)3. The trained ML model achieves an energy prediction accuracy of 0.1 meV per atom. The resulting convex hull exhibits two stable mixing concentrations at 1/6 and 1/3 Cl contents. Our data-driven approach offers a pathway towards studies of more complex perovskites and other alloy materials with quantum mechanical accuracy. en
dc.format.extent 10
dc.format.extent 1-10
dc.format.mimetype application/pdf
dc.language.iso en en
dc.publisher American Physical Society
dc.relation.ispartofseries Physical Review Materials en
dc.relation.ispartofseries Volume 6, issue 11 en
dc.rights openAccess en
dc.title Compositional engineering of perovskites with machine learning en
dc.type A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä fi
dc.description.version Peer reviewed en
dc.contributor.department Computational Electronic Structure Theory
dc.contributor.department University of Turku
dc.contributor.department Xi'an Jiaotong University
dc.contributor.department Harbin Institute of Technology
dc.contributor.department Department of Applied Physics en
dc.identifier.urn URN:NBN:fi:aalto-202212146906
dc.identifier.doi 10.1103/PhysRevMaterials.6.113801
dc.type.version publishedVersion

Files in this item

Files Size Format View

There are no open access files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search archive

Advanced Search

article-iconSubmit a publication