Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

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

Merte, Lindsay R. LU ; Bisbo, Malthe Kjær ; Sokolović, Igor ; Setvín, Martin ; Hagman, Benjamin LU ; Shipilin, Mikhail LU ; Schmid, Michael ; Diebold, Ulrike ; Lundgren, Edvin LU and Hammer, Bjørk (2022) In Angewandte Chemie - International Edition 61(25).
Abstract

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... (More)

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.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Density Functional Calculations, Machine Learning, Structure Elucidation, Surface Chemistry
in
Angewandte Chemie - International Edition
volume
61
issue
25
article number
e202204244
publisher
John Wiley & Sons Inc.
external identifiers
  • scopus:85128515339
  • pmid:35384213
ISSN
1433-7851
DOI
10.1002/anie.202204244
language
English
LU publication?
yes
id
ab6d7c96-3111-49ca-a9e0-e5c7a954baf0
date added to LUP
2022-07-05 14:34:42
date last changed
2024-04-16 12:56:35
@article{ab6d7c96-3111-49ca-a9e0-e5c7a954baf0,
  abstract     = {{<p>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 Pt<sub>3</sub>Sn(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.</p>}},
  author       = {{Merte, Lindsay R. and Bisbo, Malthe Kjær and Sokolović, Igor and Setvín, Martin and Hagman, Benjamin and Shipilin, Mikhail and Schmid, Michael and Diebold, Ulrike and Lundgren, Edvin and Hammer, Bjørk}},
  issn         = {{1433-7851}},
  keywords     = {{Density Functional Calculations; Machine Learning; Structure Elucidation; Surface Chemistry}},
  language     = {{eng}},
  month        = {{06}},
  number       = {{25}},
  publisher    = {{John Wiley & Sons Inc.}},
  series       = {{Angewandte Chemie - International Edition}},
  title        = {{Structure of an Ultrathin Oxide on Pt<sub>3</sub>Sn(111) Solved by Machine Learning Enhanced Global Optimization**}},
  url          = {{http://dx.doi.org/10.1002/anie.202204244}},
  doi          = {{10.1002/anie.202204244}},
  volume       = {{61}},
  year         = {{2022}},
}