Journal article · 2021 · Open access

Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations

April M Miksch, Tobias Morawietz, Johannes Kästner, Alexander Urban, Nongnuch Artrith

Machine Learning Science and Technology, 2(3), 031001 · Published 30 April 2021 · DOI 10.1088/2632-2153/abfd96

Open PDFView at the publisherCite this paper

In brief

“Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations” is a 2021 journal article by April M Miksch and 4 co-authors, published in Machine Learning Science and Technology. OpenAlex counts 105 citations as of 19 November 2026, which puts it in the top 2% of works published in 2021 by citations. It is open access under a CC BY licence: the full text is free to read at Machine Learning Science and Technology.

Citations
105
Most cited in
2024 (28)
Field-weighted impact
4.98
References
172
Authors
5

Abstract

Recent advances in machine-learning interatomic potentials have enabled the efficient modeling of complex atomistic systems with an accuracy that is comparable to that of conventional quantum-mechanics based methods. At the same time, the construction of new machine-learning potentials can seem a daunting task, as it involves data-science techniques that are not yet common in chemistry and materials science. Here, we provide a tutorial-style overview of strategies and best practices for the construction of artificial neural network (ANN) potentials. We illustrate the most important aspects of (a) data collection, (b) model selection, (c) training and validation, and (d) testing and refinement of ANN potentials on the basis of practical examples. Current research in the areas of active learning and delta learning are also discussed in the context of ANN potentials. This tutorial review aims at equipping computational chemists and materials scientists with the required background knowledge for ANN potential construction and application, with the intention to accelerate the adoption of the method, so that it can facilitate exciting research that would otherwise be challenging with conventional strategies.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Miksch, A. M., Morawietz, T., Kästner, J., Urban, A., & Artrith, N. (2021). Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations. Machine Learning Science and Technology, 2(3), 031001. https://doi.org/10.1088/2632-2153/abfd96

MLA 9

Miksch, April M, et al. “Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations.” Machine Learning Science and Technology, vol. 2, no. 3, 2021, p. 031001. https://doi.org/10.1088/2632-2153/abfd96.

Chicago

Miksch, April M, Tobias Morawietz, Johannes Kästner, Alexander Urban, and Nongnuch Artrith. 2021. “Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations.” Machine Learning Science and Technology 2 (3): 031001. https://doi.org/10.1088/2632-2153/abfd96.

Harvard

Miksch, A. M. et al. (2021) ‘Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations’, Machine Learning Science and Technology, 2(3), p. 031001. doi:10.1088/2632-2153/abfd96.

IEEE

A. M. Miksch, T. Morawietz, J. Kästner, A. Urban, and N. Artrith, “Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations,” Machine Learning Science and Technology, vol. 2, no. 3, p. 031001, 2021, doi: 10.1088/2632-2153/abfd96.

BibTeX

@article{miksch2021strategies,
  title     = {{Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations}},
  author    = {Miksch, April M and Morawietz, Tobias and Kästner, Johannes and Urban, Alexander and Artrith, Nongnuch},
  journal   = {Machine Learning Science and Technology},
  year      = {2021},
  volume    = {2},
  number    = {3},
  pages     = {031001},
  doi       = {10.1088/2632-2153/abfd96},
  url       = {https://doi.org/10.1088/2632-2153/abfd96}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
202188
20221414
20232525
20242828
20251616
20261414

Its field-weighted citation impact is 4.98: it has been cited 4.98 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science

  • machine learning interatomic potentials
  • neural network potentials
  • potential construction
  • data collection
  • model selection
  • active learning (machine learning)
  • delta learning
  • atomistic simulation

Work with this paper

Most-cited papers in Materials Science

All highly cited Materials Science papers

Questions about this paper

How do I cite this paper in APA style?

Miksch, A. M., Morawietz, T., Kästner, J., Urban, A., & Artrith, N. (2021). Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations. Machine Learning Science and Technology, 2(3), 031001. https://doi.org/10.1088/2632-2153/abfd96

How many times has this paper been cited?

105 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Machine Learning Science and Technology: sign in and open the PDF from this page.

Who wrote this paper?

April M Miksch, Tobias Morawietz, Johannes Kästner, Alexander Urban, Nongnuch Artrith.

What is the DOI of this paper?

10.1088/2632-2153/abfd96, permanently at https://doi.org/10.1088/2632-2153/abfd96. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.