Recommended by

Indexed by

Machine learning for metallurgy V: A neural-network potential for zirconium data of published plots

Manura Liyanage1*, David Reith2, Volker Eyert2, W. A. Curtin1

1 Laboratory for Multiscale Mechanics Modelling, Ecole Polytechnique Fédérale de Lausanne, CH-1015 Lausanne, Switzerland

2 Materials Design SARL, 42 avenue Verdier, 92120 Montrouge, France

* Corresponding authors emails: pandula.liyanage@epfl.ch
DOI10.24435/materialscloud:vy-02 [version v1]

Publication date: Jan 30, 2023

How to cite this record

Manura Liyanage, David Reith, Volker Eyert, W. A. Curtin, Machine learning for metallurgy V: A neural-network potential for zirconium data of published plots, Materials Cloud Archive 2023.21 (2023), doi: 10.24435/materialscloud:vy-02.


The mechanical performance—including deformation, fracture, and radiation damage—of zirconium is determined at the atomic scale. With Zr and its alloys extensively used in the nuclear industry, understanding that atomic-scale behavior is crucial. The defects controlling that performance are at size scales far larger than accessible by first-principles methods, necessitating the use of semi-empirical interatomic potentials. Existing potentials for Zr are not sufficiently quantitative, nor easily extendable to alloys, oxides, or hydrides. To overcome these issues, a neural network machine learning potential (NNP) is developed here within the Behler-Parrinello framework for Zr. With a careful choice of descriptors of the atomic environments and the creation of a first-principles training dataset that includes a wide spectrum of configurations of metallurgical relevance, a very accurate NNP is demonstrated. Specifically, the Zr NNP yields a good description of dislocation structures and their relative energies and fracture behavior, along with bulk, surface, and point-defect properties and structures, and significantly outperforms the best available traditional potentials. Results here will enable large-scale simulations of complex processes and provide the basis for future extensions to alloys, oxides, and hydrides.

Materials Cloud sections using this data

No Explore or Discover sections associated with this archive record.


File name Size Description
105.3 KiB The archive contains the data points for the plots published in the paper. Th files contain the .tex (LaTeX) files used to develop the plots. A description of each figure is given in README.txt.


Files and data are licensed under the terms of the following license: Materials Cloud non-exclusive license to distribute v1.0.
Metadata, except for email addresses, are licensed under the Creative Commons Attribution Share-Alike 4.0 International license.

External references

Journal reference (The archive contains the tex files used to create the plots in Figures 2, 5, 6, 7, and 8.)


machine learning Zirconium Defects Ductility Fracture MARVEL

Version history:

2023.21 (version v1) [This version] Jan 30, 2023 DOI10.24435/materialscloud:vy-02