Charting the energy landscape of metal/organic interfaces via machine learning

Michael Scherbela, Lukas Hörmann, Andreas Jeindl, Veronika Obersteiner, Oliver Hofmann

Publikation: Beitrag in einer Fachzeitschrift › Artikel › Forschung › Begutachtung

Abstract

The rich polymorphism exhibited by inorganic/organic interfaces is a major challenge for materials design. In this work, we present a method to efficiently explore the potential energy surface and predict the formation energies of polymorphs and defects. This is achieved by training a machine learning model on a list of only 100 candidate structures that are evaluated via dispersion-corrected density functional theory (DFT) calculations. We demonstrate the power of this approach for tetracyanoethylene on Ag(100) and explain the anisotropic ordering that is observed experimentally.
Originalspracheenglisch
Seiten (von - bis)043803
FachzeitschriftPhysical Review Materials
Jahrgang2
Ausgabenummer4
DOIs
PublikationsstatusVeröffentlicht - 17 Apr 2018

Fingerprint

Polymorphism
Learning systems
Metals
Potential energy surfaces
Density functional theory
Defects
tetracyanoethylene

Fields of Expertise

  • Advanced Materials Science

Dies zitieren

Charting the energy landscape of metal/organic interfaces via machine learning. / Scherbela, Michael; Hörmann, Lukas; Jeindl, Andreas; Obersteiner, Veronika; Hofmann, Oliver.

in: Physical Review Materials, Jahrgang 2, Nr. 4, 17.04.2018, S. 043803.

Publikation: Beitrag in einer Fachzeitschrift › Artikel › Forschung › Begutachtung

Scherbela, M, Hörmann, L, Jeindl, A, Obersteiner, V & Hofmann, O 2018, 'Charting the energy landscape of metal/organic interfaces via machine learning' Physical Review Materials, Jg. 2, Nr. 4, S. 043803. https://doi.org/10.1103/PhysRevMaterials.2.043803
Scherbela M, Hörmann L, Jeindl A, Obersteiner V, Hofmann O. Charting the energy landscape of metal/organic interfaces via machine learning. Physical Review Materials. 2018 Apr 17;2(4):043803. https://doi.org/10.1103/PhysRevMaterials.2.043803
Scherbela, Michael ; Hörmann, Lukas ; Jeindl, Andreas ; Obersteiner, Veronika ; Hofmann, Oliver. / Charting the energy landscape of metal/organic interfaces via machine learning. in: Physical Review Materials. 2018 ; Jahrgang 2, Nr. 4. S. 043803.
@article{8708ce3be36a497c866bb282123a2c2f,
title = "Charting the energy landscape of metal/organic interfaces via machine learning",
abstract = "The rich polymorphism exhibited by inorganic/organic interfaces is a major challenge for materials design. In this work, we present a method to efficiently explore the potential energy surface and predict the formation energies of polymorphs and defects. This is achieved by training a machine learning model on a list of only 100 candidate structures that are evaluated via dispersion-corrected density functional theory (DFT) calculations. We demonstrate the power of this approach for tetracyanoethylene on Ag(100) and explain the anisotropic ordering that is observed experimentally.",
author = "Michael Scherbela and Lukas H{\"o}rmann and Andreas Jeindl and Veronika Obersteiner and Oliver Hofmann",
year = "2018",
month = "4",
day = "17",
doi = "10.1103/PhysRevMaterials.2.043803",
language = "English",
volume = "2",
pages = "043803",
journal = "Physical Review Materials",
issn = "2475-9953",
publisher = "American Physical Society",
number = "4",

}

TY - JOUR

T1 - Charting the energy landscape of metal/organic interfaces via machine learning

AU - Scherbela, Michael

AU - Hörmann, Lukas

AU - Jeindl, Andreas

AU - Obersteiner, Veronika

AU - Hofmann, Oliver

PY - 2018/4/17

Y1 - 2018/4/17

N2 - The rich polymorphism exhibited by inorganic/organic interfaces is a major challenge for materials design. In this work, we present a method to efficiently explore the potential energy surface and predict the formation energies of polymorphs and defects. This is achieved by training a machine learning model on a list of only 100 candidate structures that are evaluated via dispersion-corrected density functional theory (DFT) calculations. We demonstrate the power of this approach for tetracyanoethylene on Ag(100) and explain the anisotropic ordering that is observed experimentally.

AB - The rich polymorphism exhibited by inorganic/organic interfaces is a major challenge for materials design. In this work, we present a method to efficiently explore the potential energy surface and predict the formation energies of polymorphs and defects. This is achieved by training a machine learning model on a list of only 100 candidate structures that are evaluated via dispersion-corrected density functional theory (DFT) calculations. We demonstrate the power of this approach for tetracyanoethylene on Ag(100) and explain the anisotropic ordering that is observed experimentally.

U2 - 10.1103/PhysRevMaterials.2.043803

DO - 10.1103/PhysRevMaterials.2.043803

M3 - Article

VL - 2

SP - 043803

JO - Physical Review Materials

JF - Physical Review Materials

SN - 2475-9953

IS - 4

ER -

Zugang zum Dokument