CoChat
Sign Up
Cited by 1,140Machine Learning in Materials ScienceAdvanced Chemical Physics StudiesComputational Drug Discovery Methods

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

A universal graph deep learning interatomic potential for the periodic table

Open access
Chen, Chi, Ong, Shyue Ping·2022·Nature Computational Science
DOI 10.1038/s43588-022-00349-3

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Abstract Interatomic potentials (IAPs), which describe the potential energy surface of a collection of atoms, are a fundamental input for atomistic simulations. However, existing IAPs are either fitted to narrow chemistries or too inaccurate for general applications. Here, we report a universal IAP for materials based on graph neural networks with three-body interactions (M3GNet). The M3GNet IAP was trained on the massive database of structural relaxations performed by the Materials Project over the past 10 years and has broad applications in structural relaxation, dynamic simulations and property prediction of materials across diverse chemical spaces. About 1.8 million potentially stable materials were identified from a screening of 31 million hypothetical crystal structures, demonstrating a machine learning-accelerated pathway to the discovery of synthesizable materials with exceptional properties.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s43588-022-00349-3

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

  • In both training setups, the NequIP potential performs better than the M3GNet models trained with energies and forces (M3GNet-EF) reported in ref. 62.

    “In both cases, we found the NequIP potential to perform better than the M3GNet models trained with energies and forces (M3GNet-EF) reported in ref. 62.”

    From Scaling deep learning for materials discovery (2023) · cites this paper as [62]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 54

  1. Weiner, P. K. & Kollman, P. A. AMBER: assisted model building with energy refinement. A general program for modeling molecules and their interactions. J. Comput. Chem. 2, 287–303 (1981). · DOI
  2. Case, D. A. et al. The AMBER biomolecular simulation programs. J. Comput. Chem. 26, 1668–1688 (2005). · DOI · Paper page
  3. Rappe, A. K., Casewit, C. J., Colwell, K. S., Goddard, W. A. & Skiff, W. M. UFF, a full periodic table force field for molecular mechanics and molecular dynamics simulations. J. Am. Chem. Soc. 114, 10024–10035 (1992). · DOI
  4. Behler, J. & Parrinello, M. Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys. Rev. Lett. 98, 146401 (2007). · DOI · Paper page
  5. Bartók, A. P., Payne, M. C., Kondor, R. & Csányi, G. Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. Phys. Rev. Lett. 104, 136403 (2010). · DOI · Paper page
  6. Thompson, A. P., Swiler, L. P., Trott, C. R., Foiles, S. M. & Tucker, G. J. Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials. J. Comput. Phys. 285, 316–330 (2015). · DOI
  7. Shapeev, A. V. Moment tensor potentials: a class of systematically improvable interatomic potentials. Multiscale Model. Simul. 14, 1153–1173 (2016). · DOI
  8. Zhang, L., Han, J., Wang, H., Car, R. & E, W. Deep potential molecular dynamics: a scalable model with the accuracy of quantum mechanics. Phys. Rev. Lett. 120, 143001 (2018). · DOI
  9. Zuo, Y. et al. Performance and cost assessment of machine learning interatomic potentials. J. Phys. Chem. A 124, 731–745 (2020). · DOI · Paper page
  10. Schütt, K. et al. SchNet: a continuous-filter convolutional neural network for modeling quantum interactions. In Proc. 31st International Conference on Neural Information Processing Systems Advances in Neural Information Processing Systems 992–1002 (NIPS, 2017).
  11. Klicpera, J., Groß, J. & Günnemann, S. Directional message passing for molecular graphs. Preprint at https://arxiv.org/abs/2003.03123 (2020). · arXiv
  12. Haghighatlari, M. et al. NewtonNet: a Newtonian message passing network for deep learning of interatomic potentials and forces. Digit. Discov. 1, 333–343 (2022). · DOI
  13. Park, C. W. et al. Accurate and scalable graph neural network force field and molecular dynamics with direct force architecture. npj Comput. Mater. 7, 1–9 (2021). · DOI
  14. Cheon, G., Yang, L., McCloskey, K., Reed, E. J. & Cubuk, E. D. Crystal structure search with random relaxations using graph networks. Preprint at https://arxiv.org/abs/2012.02920 (2020). · arXiv
  15. Ong, S. P. et al. Python Materials Genomics (pymatgen): a robust, open-source Python library for materials analysis. Comput. Mater. Sci. 68, 314–319 (2013). · DOI · Paper page
  16. Jain, A. et al. FireWorks: a dynamic workflow system designed for high-throughput applications. Concurr. Comput. 27, 5037–5059 (2015). · DOI
  17. Pizzi, G., Cepellotti, A., Sabatini, R., Marzari, N. & Kozinsky, B. AiiDA: automated interactive infrastructure and database for computational science. Comput. Mater. Sci. 111, 218–230 (2016). · DOI
  18. Mathew, K. et al. Atomate: a high-level interface to generate, execute, and analyze computational materials science workflows. Comput. Mater. Sci. 139, 140–152 (2017). · DOI
  19. Curtarolo, S. et al. AFLOWLIB.ORG: a distributed materials properties repository from high-throughput ab initio calculations. Comput. Mater. Sci. 58, 227–235 (2012). · DOI · Paper page
  20. Kirklin, S. et al. The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies. npj Comput. Mater. 1, 1–15 (2015). · DOI
  21. Draxl, C. & Scheffler, M. The NOMAD laboratory: from data sharing to artificial intelligence. J. Phys. Mater. 2, 036001 (2019). · DOI · Paper page
  22. Xie, T. & Grossman, J. C. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys. Rev. Lett. 120, 145301 (2018). · DOI · Paper page
  23. Chen, C., Ye, W., Zuo, Y., Zheng, C. & Ong, S. P. Graph networks as a universal machine learning framework for molecules and crystals. Chem. Mater. 31, 3564–3572 (2019). · DOI · Paper page
  24. Chen, C., Zuo, Y., Ye, W., Li, X. & Ong, S. P. Learning properties of ordered and disordered materials from multi-fidelity data. Nat. Comput. Sci. 1, 46–53 (2021). · DOI
  25. Choudhary, K. & DeCost, B. Atomistic line graph neural network for improved materials property predictions. npj Comput. Mater. 7, 1–8 (2021). · DOI
  26. Tersoff, J. New empirical approach for the structure and energy of covalent systems. Phys. Rev. B 37, 6991–7000 (1988). · DOI
  27. Petretto, G. et al. High-throughput density-functional perturbation theory phonons for inorganic materials. Sci. Data 5, 180065 (2018). · DOI
  28. Perdew, J. P. et al. Restoring the density-gradient expansion for exchange in solids and surfaces. Phys. Rev. Lett. 100, 136406 (2008). · DOI · Paper page
  29. Kresse, G. & Hafner, J. Ab initio molecular dynamics for liquid metals. Phys. Rev. B 47, 558–561 (1993). · DOI
  30. Kresse, G. & Furthmüller, J. Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set. Comput. Mater. Sci. 6, 15–50 (1996). · DOI
  31. Dunn, A., Wang, Q., Ganose, A., Dopp, D. & Jain, A. Benchmarking materials property prediction methods: the Matbench test set and Automatminer reference algorithm. npj Comput. Mater. 6, 1–10 (2020). · DOI
  32. Sun, W. et al. The thermodynamic scale of inorganic crystalline metastability. Sci. Adv. 2, e160022 (2016). · DOI
  33. Qi, J. et al. Bridging the gap between simulated and experimental ionic conductivities in lithium superionic conductors. Mater. Today Phys. 21, 100463 (2021). · DOI
  34. Glass, C. W., Oganov, A. R. & Hansen, N. USPEX—evolutionary crystal structure prediction. Comput. Phys. Commun. 175, 713–720 (2006). · DOI
  35. Wang, Y., Lv, J., Zhu, L. & Ma, Y. CALYPSO: a method for crystal structure prediction. Comput. Phys. Commun. 183, 2063–2070 (2012). · DOI
  36. Xie, T., Fu, X., Ganea, O.-E., Barzilay, R. & Jaakkola, T. Crystal diffusion variational autoencoder for periodic material generation. Preprint at https://arxiv.org/abs/2110.06197 (2021). · arXiv
  37. Chmiela, S. et al. Machine learning of accurate energy-conserving molecular force fields. Sci. Adv. 3, e1603015 (2017). · DOI
  38. Chmiela, S., Sauceda, H. E., Müller, K.-R. & Tkatchenko, A. Towards exact molecular dynamics simulations with machine-learned force fields. Nat. Commun. 9, 3887 (2018). · DOI
  39. Zhang, Y., Hu, C. & Jiang, B. Embedded atom neural network potentials: efficient and accurate machine learning with a physically inspired representation. J. Phys. Chem. Lett. 10, 4962–4967 (2019). · DOI
  40. Anisimov, V. I., Zaanen, J. & Andersen, O. K. Band theory and Mott insulators: Hubbard U instead of stoner I. Phys. Rev. B 44, 943–954 (1991). · DOI
  41. Hellenbrandt, M. The Inorganic Crystal Structure Database (ICSD)—present and future. Crystallogr. Rev. 10, 17–22 (2004). · DOI · Paper page
  42. Wang, L., Maxisch, T. & Ceder, G. Oxidation energies of transition metal oxides within the GGU+U framework. Phys. Rev. B 73, 195107 (2006). · DOI · Paper page
  43. Singraber, A., Behler, J. & Dellago, C. Library-based LAMMPS implementation of high-dimensional neural network potentials. J. Chem. Theory Comput. 15, 1827–1840 (2019). · DOI
  44. Ramachandran, P., Zoph, B. & Le, Q. V. Searching for activation functions. Preprint at https://arxiv.org/abs/1710.05941 (2017). · arXiv
  45. Kocer, E., Mason, J. K. & Erturk, H. A novel approach to describe chemical environments in high-dimensional neural network potentials. J. Chem. Phys. 150, 154102 (2019). · DOI
  46. Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. Preprint https://arxiv.org/abs/1412.6980 (2017). · arXiv
  47. Huber, P. J. Robust estimation of a location parameter. Ann. Math. Stat. 35, 73–101 (1964). · DOI · Paper page
  48. Abadi, M. et al. TensorFlow: a system for large-scale machine learning. In 12th Symposium on Operating Systems Design and Implementation 265–283 (OSDI, 2016).
  49. Bitzek, E., Koskinen, P., Gähler, F., Moseler, M. & Gumbsch, P. Structural relaxation made simple. Phys. Rev. Lett. 97, 170201 (2006). · DOI
  50. Larsen, A. H. et al. The atomic simulation environment—a Python library for working with atoms. J. Phys. 29, 273002 (2017).
  51. Togo, A. & Tanaka, I. First principles phonon calculations in materials science. Scripta Materialia 108, 1–5 (2015). · DOI
  52. Pedregosa, F. et al. Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011).
  53. Seabold, S. & Perktold, J. Statsmodels: econometric and statistical modeling with Python. In Proc. 9th Python in Science Conference 92–96 (SciPy, 2010). · DOI
  54. de Jong, M. et al. Charting the complete elastic properties of inorganic crystalline compounds. Sci. Data 2, 150009 (2015). · DOI

Cited by

Sorted by citations

Metadata

Authors
Chen, C., & Ong, S. P.
Affiliations
University of California San Diego (US)
Corresponding author
  • Chen, Chi
  • Ong, Shyue Ping
ORCID
Venue
Nature Computational Science
Publisher
Springer Science and Business Media LLC
Published
2022-11-28
Volume
2
Issue
11
Pages
718-728
ISSN
2662-8457 (ISSN-L)
DOI
10.1038/s43588-022-00349-3
OpenAlex
W4310135808
Cited by
1,140
References
6
Citations by year
2026: 424 · 2025: 383 · 2024: 259 · 2023: 67 · 2022: 6
FWCI
47.32
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Computational Science (publishedVersion)
  • Research Square (acceptedVersion, cc-by)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University) (cc-by)
Funders
DOE | SC | Basic Energy Sciences (DE-AC02-05-CH11231)
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
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
Keywords
interatomic potentials, graph neural networks, M3GNet, three-body interactions, materials discovery, crystal stability, convex hull, hypothetical crystal structures, Materials Project, structural relaxation, materials property prediction, periodic table

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