CoChat
Sign Up
Cited by 195Machine Learning in Materials ScienceAdvanced Chemical Physics StudiesHigh-pressure geophysics and materials

The DOI matches its Crossref record; 57 of the 57 references it cites were found in a registry or an index.

Machine-learned interatomic potentials by active learning: amorphous and liquid hafnium dioxide

Open access
Sivaraman, Ganesh, Krishnamoorthy, Anand Narayanan, Baur, Matthias, Holm, Christian, Stan, Marius, Csányi, Gábor, Benmore, Chris, Vázquez-Mayagoitia, Álvaro·2020·npj Computational Materials
DOI 10.1038/s41524-020-00367-7
Open this paper in CoChat — free accountOpen PDF

Abstract

We propose an active learning scheme for automatically sampling a minimum number of uncorrelated configurations for fitting the Gaussian Approximation Potential (GAP). Our active learning scheme consists of an unsupervised machine learning (ML) scheme coupled with a Bayesian optimization technique that evaluates the GAP model. We apply this scheme to a Hafnium dioxide (HfO 2 ) dataset generated from a “melt-quench” ab initio molecular dynamics (AIMD) protocol. Our results show that the active learning scheme, with no prior knowledge of the dataset, is able to extract a configuration that reaches the required energy fit tolerance. Further, molecular dynamics (MD) simulations performed using this active learned GAP model on 6144 atom systems of amorphous and liquid state elucidate the structural properties of HfO 2 with near ab initio precision and quench rates (i.e., 1.0 K/ps) not accessible via AIMD. The melt and amorphous X-ray structural factors generated from our simulation are in good agreement with experiment. In addition, the calculated diffusion constants are in good agreement with previous ab initio studies.

Overview

Integrity signals

Registry

Crossref · 10.1038/s41524-020-00367-7

Cites

57 of 57 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 57 references

Research works printed but not linked: 8

  1. McGreevy, R. L. Reverse Monte Carlo modelling. J. Phys. 13, R877 (2001).
  2. Huan, T. D. et al. A universal strategy for the creation of machine learning-based atomistic force fields. npj Comput. Mater. 3, 37 (2017).
  3. Behler, J. Representing potential energy surfaces by high-dimensional neural network potentials. J. Phys. 26, 183001 (2014).
  4. Matthews, J. N. A. Semiconductor industry switches to hafnium-based transistors. Phys. Today 61, 25 (2008).
  5. Upadhya, K., Yang, J. M. & Hoffman, W. P. Advanced materials for ultrahigh temperature structural applications above 2000 °C. Am. Ceram. Soc. Bull. 76, 51–56 (1997).
  6. Bartók, A. P., Kermode, J., Bernstein, N. & Csányi, G. Machine learning a general-purpose interatomic potential for silicon. Phys. Rev. X 8, 041048 (2018).
  7. Kresse, G. & Furthmüller, J. Software VASP, Vienna. Phys. Rev. B 54, 169 (1999).
  8. Snoek, J. Larochelle, H. & Adams, R. P. Practical bayesian optimization of machine learning algorithms. In Advances in Neural Information Processing Systems, 2951–2959 (Curran Associates, Inc., New York, USA, 2012).

Cited by

Sorted by citations

Items 101–195 of 195

Related

See all

Metadata

Authors
Sivaraman, G., Krishnamoorthy, A. N., Baur, M., Holm, C., Stan, M., Csányi, G., Benmore, C., & Vázquez-Mayagoitia, Á.
Affiliations
  • Argonne National Laboratory (US)
  • University of Stuttgart (DE)
ORCID
Venue
npj Computational Materials
Publisher
Springer Science and Business Media LLC
Published
2020-07-23
Volume
6
Issue
1
ISSN
2057-3960 (ISSN-L)
DOI
10.1038/s41524-020-00367-7
OpenAlex
W2981603605
Cited by
194
References
57
Citations by year
2026: 28 · 2025: 32 · 2024: 43 · 2023: 35 · 2022: 22 · 2021: 27 · 2020: 7
FWCI
8.86
Type
journal article
Language
en
Open access
Licence
Locations
  • npj Computational Materials (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
Funders
  • U.S. Department of Energy (DE‐ AC02‐06CH11357, Contract No. DE-AC02-06CH11357., AC02‐06CH11357, contract DE-AC02-06CH11357, 06CH11357, No. DE-AC02-06CH11357, DE-AC02-)
  • Deutsche Forschungsgemeinschaft (EXC2075390740016, DE-AC02-06CH11357, EXC 2075, 390740016)
  • Office of Science (Contract No. DE-AC02-06CH11357, AC02‐06CH11357, DE-AC02, No. DE-AC02-06CH11357., 06CH11357, DE-AC02-06CH11357)
  • Basic Energy Sciences (DE-AC02, DE-AC- 02-06CH11357, AC02‐06CH11357, Contract No. DE-AC02-06CH11357, 06CH11357)
  • Laboratory Directed Research and Development (DE‐AC02‐06CH11357)
  • Argonne National Laboratory (DE- AC02-06-CH11357, DE-AC02, AC02–06CH11357, Contract DE-AC02-06CH11357, No. DE-AC02-06CH11357, 06CH11357, Contract No. DE-AC02-06CH11357., under contract DE-AC02-06CH11357)
Topics
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Advanced Chemical Physics Studies
  • Physical Sciences › Earth and Planetary Sciences › Geophysics › High-pressure geophysics and materials
Keywords
active learning (machine learning), Gaussian approximation potential, interatomic potentials, hafnium oxide, amorphous HfO2, ab initio molecular dynamics, Bayesian optimization, unsupervised learning, diffusion coefficient, machine learning interatomic potentials

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review