Structure of an Ultrathin Oxide on Pt3Sn(111) Solved by Machine Learning Enhanced Global Optimization

Determination of the atomic structure of solid surfaces typically depends on comparison of measured properties with simulations based on hypothesized structural models. For simple structures, the models may be guessed, but for more complex structures there is a need for reliable theory‐based search...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Angewandte Chemie International Edition Ročník 61; číslo 25
Hlavní autoři: Merte, Lindsay R., Bisbo, Malthe Kjær, Sokolović, Igor, Setvín, Martin, Hagman, Benjamin, Shipilin, Mikhail, Schmid, Michael, Diebold, Ulrike, Lundgren, Edvin, Hammer, Bjørk
Médium: Journal Article
Jazyk:angličtina
Vydáno: Weinheim Wiley Subscription Services, Inc 20.06.2022
John Wiley and Sons Inc
Vydání:International ed. in English
Témata:
Algorithms
Atomic structure
Chemical Sciences
Combinatorial analysis
Complexity
Computer applications
Density Functional Calculations
Evolutionary algorithms
Global optimization
Intermetallic compounds
Kemi
Learning algorithms
Machine Learning
Natural Sciences
Naturvetenskap
Search algorithms
Solid surfaces
Structural models
Structure Elucidation
Surface Chemistry
Surface structure
Teoretisk kemi (Här ingår: Beräkningskemi)
Theoretical Chemistry (including Computational Chemistry)
ISSN:1433-7851, 1521-3773
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Determination of the atomic structure of solid surfaces typically depends on comparison of measured properties with simulations based on hypothesized structural models. For simple structures, the models may be guessed, but for more complex structures there is a need for reliable theory‐based search algorithms. So far, such methods have been limited by the combinatorial complexity and computational expense of sufficiently accurate energy estimation for surfaces. However, the introduction of machine learning methods has the potential to change this radically. Here, we demonstrate how an evolutionary algorithm, utilizing machine learning for accelerated energy estimation and diverse population generation, can be used to solve an unknown surface structure—the (4×4) surface oxide on Pt3Sn(111)—based on limited experimental input. The algorithm is efficient and robust, and should be broadly applicable in surface studies, where it can replace manual, intuition based model generation. Machine learning techniques can be implemented to accelerate surface structure determination based on density functional theory. The application of such an algorithm is demonstrated here for a surface oxide on Pt3Sn(111) which had eluded determination by experimental methods.
Bibliografie:https://doi.org/10.26434/chemrxiv‐2021‐mtbq2
.
A previous version of this manuscript has been deposited on a preprint server
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
A previous version of this manuscript has been deposited on a preprint server (https://doi.org/10.26434/chemrxiv‐2021‐mtbq2).
ISSN:1433-7851
1521-3773
DOI:10.1002/anie.202204244