Towards universal neural network potential for material discovery applicable to arbitrary combination of 45 elements

Abstract

Computational material discovery is under intense study owing to its ability to explore the vast space of chemical systems. Neural network potentials (NNPs) have been shown to be particularly effective in conducting atomistic simulations for such purposes. However, existing NNPs are generally designed for narrow target materials, making them unsuitable for broader applications in material discovery. Here we report a development of universal NNP called PreFerred Potential (PFP), which is able to handle any combination of 45 elements. Particular emphasis is placed on the datasets, which include a diverse set of virtual structures used to attain the universality. We demonstrated the applicability of PFP in selected domains: lithium diffusion in LiFeSO 4 F, molecular adsorption in metal-organic frameworks, an order–disorder transition of Cu-Au alloys, and material discovery for a Fischer–Tropsch catalyst. They showcase the power of PFP, and this technology provides a highly useful tool for material discovery.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 77

1. 1.

   Reymond J-L. The chemical space project. Acc. Chem. Res. 2015;48:722-730.

   Not in our library10.1021/ar500432k (opens in a new tab)

2. 2.

   Jones JE. On the determination of molecular fields.-i. from the variation of the viscosity of a gas with temperature. Proc. R. Soc. Lond. Ser. A. 1924;106:441-462.

   Not in our library10.1098/rspa.1924.0081 (opens in a new tab)

3. 3.

   Daw MS, Baskes MI. Embedded-atom method: derivation and application to impurities, surfaces and other defects in metals. Phys. Rev. B. 1984;29:6443-6453.

   Not in our library10.1103/physrevb.29.6443 (opens in a new tab)

4. 4.

   Finnis MW, Sinclair JE. A simple empirical n-body potential for transition metals. Philos. Mag. A. 1984;50:45-55.

   Not in our library10.1080/01418618408244210 (opens in a new tab)

5. 5.

   Tersoff J. Modeling solid-state chemistry: Interatomic potentials for multicomponent systems. Phys. Rev. B. 1989;39:5566-5568.

   Not in our library10.1103/physrevb.39.5566 (opens in a new tab)

6. 6.

   van Duin ACT, Dasgupta S, Lorant F, Goddard WA. Reaxff: A reactive force field for hydrocarbons. J. Phys. Chem. A. 2001;105:9396-9409.

   Not in our library10.1021/jp004368u (opens in a new tab)

7. 7.

   Senftle TP, et al. The reaxff reactive force-field: development, applications and future directions. npj Comput. Mater. 2016;2:1-14.

   Not in our library10.1038/npjcompumats.2015.11 (opens in a new tab)

8. 8.

   Bartók AP, Kermode J, Bernstein N, Csányi G. Machine learning a general-purpose interatomic potential for silicon. Phys. Rev. X. 2018;8:041048.

   Not in our library

9. 9.

   Bartók AP, Payne MC, Kondor R, Csányi G. Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. Phys. Rev. Lett. 2010;104:136403.

   Not in our library10.1103/physrevlett.104.136403 (opens in a new tab)

10. 10.

    Rupp M, Tkatchenko A, Müller K-R, von Lilienfeld OA. Fast and accurate modeling of molecular atomization energies with machine learning. Phys. Rev. Lett. 2012;108:058301.

    Not in our library10.1103/physrevlett.108.058301 (opens in a new tab)

11. 11.

    Vitek, A., Stachon, M., Krömer, P. & Snášel, V. Towards the modeling of atomic and molecular clusters energy by support vector regression. In Proc. 2013 5th International Conference on Intelligent Networking and Collaborative Systems, INCOS ’13, USA, 2013 (eds Xhafa, F., Barolli, L. & Chen, X.) (IEEE Computer Society).

    Not in our library

12. 12.

    Ruddigkeit L, van Deursen R, Blum LC, Reymond J-L. Enumeration of 166 billion organic small molecules in the chemical universe database gdb-17. J. Chem. Inf. Model. 2012;52:2864-2875.

    Not in our library10.1021/ci300415d (opens in a new tab)

13. 13.

    Ramakrishnan R, Dral PO, Rupp M, von Lilienfeld OA. Quantum chemistry structures and properties of 134 kilo molecules. Sci. Data. 2014;1:140022.

    Not in our library10.1038/sdata.2014.22 (opens in a new tab)

14. 14.

    Smith JS, Isayev O, Roitberg AE. Ani-1: an extensible neural network potential with dft accuracy at force field computational cost. Chem. Sci. 2017;8:3192-3203.

    Not in our library10.1039/c6sc05720a (opens in a new tab)

15. 15.

    Devereux C, et al. Extending the applicability of the ANI deep learning molecular potential to sulfur and halogens. J. Chem. Theory Comput. 2020;16:4192-4202.

    Not in our library10.1021/acs.jctc.0c00121 (opens in a new tab)

16. 16.

    Xie T, Grossman JC. Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys. Rev. Lett. 2018;120:145301.

    Not in our library10.1103/physrevlett.120.145301 (opens in a new tab)

17. 17.

    Chen C, Ye W, Zuo Y, Zheng C, Ong SP. Graph networks as a universal machine learning framework for molecules and crystals. Chem. Mater. 2019;31:3564-3572.

    Not in our library10.1021/acs.chemmater.9b01294 (opens in a new tab)

18. 18.
    Commentary: The Materials Project: A materials genome approach to accelerating materials innovation · 2013

    Not checked
19. 19.

    Zitnick, C. L. et al. An introduction to electrocatalyst design using machine learning for renewable energy storage. Preprint at 10.48550/arXiv.2010.09435 (2020).

    Not in our library

20. 20.

    Chanussot L, et al. Open catalyst 2020 (oc20) dataset and community challenges. ACS Catal. 2021;11:6059-6072.

    Not in our library10.1021/acscatal.0c04525 (opens in a new tab)

21. 21.

    Kaplan, J. et al. Scaling laws for neural language models. Preprint at 10.48550/arXiv.2001.08361 (2020).

    Not in our library

22. 22.

    Liu, H., Dai, Z., So, D. R. & Le, Q. V. Pay attention to mlps. Preprint at 10.48550/arXiv.2105.08050 (2021).

    Not in our library

23. 23.

    Van der Ven A, Aydinol MK, Ceder G, Kresse G, Hafner J. First-principles investigation of phase stability in Lixcoo2. Phys. Rev. B. 1998;58:2975.

    Not in our library10.1103/physrevb.58.2975 (opens in a new tab)

24. 24.

    Yamada Y, et al. Hydrate-melt electrolytes for high-energy-density aqueous batteries. Nat. Energy. 2016;1:1-9.

    Not in our library10.1038/nenergy.2016.129 (opens in a new tab)

25. 25.

    Morgan D, Van der Ven A, Ceder G. Li conductivity in li x mpo 4 (m= mn, fe, co, ni) olivine materials. Electrochem. Solid State Lett. 2003;7:A30.

    Not in our library10.1149/1.1633511 (opens in a new tab)

26. 26.
    In situ click chemistry generation of cyclooxygenase-2 inhibitors · 2017

    No notice
27. 27.

    Jónsson, H., Mills, G. & Jacobsen, K. W. Nudged Elastic Band Method for Finding Minimum Energy Paths of Transitions 385–404 (World Scientific Pub Co Pte Ltd, 1998).

    Not in our library

28. 28.

    Henkelman G, Uberuaga BP, Jónsson H. A climbing image nudged elastic band method for finding saddle points and minimum energy paths. J. Chem. Phys. 2000;113:9901-9904.

    Not in our library10.1063/1.1329672 (opens in a new tab)

29. 29.

    Recham N, et al. A 3.6 v lithium-based fluorosulphate insertion positive electrode for lithium-ion batteries. Nat. Mater. 2010;9:68-74.

    Not in our library10.1038/nmat2590 (opens in a new tab)

30. 30.

    Mueller T, Hautier G, Jain A, Ceder G. Evaluation of tavorite-structured cathode materials for lithium-ion batteries using high-throughput computing. Chem. Mater. 2011;23:3854-3862.

    Not in our library10.1021/cm200753g (opens in a new tab)

31. 31.

    Momma K, Izumi F. Vesta 3 for three-dimensional visualization of crystal, volumetric and morphology data. J. Appl. Crystallogr. 2011;44:1272-1276.

    Not in our library10.1107/s0021889811038970 (opens in a new tab)

32. 32.

    Dudarev SL, Botton GA, Savrasov SY, Humphreys CJ, Sutton AP. Electron-energy-loss spectra and the structural stability of nickel oxide: an lsda+ u study. Phys. Rev. B. 1998;57:1505.

    Not in our library10.1103/physrevb.57.1505 (opens in a new tab)

33. 33.
    The Cambridge Structural Database · 2016

    No notice
34. 34.

    Fletcher, R. Practical Methods of Optimization, 2nd edn (Wiley, 2000).

    Not in our library

35. 35.

    Paszke, A. et al. Pytorch: an imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems, Vol. 32 (eds, Wallach, H., Larochelle, H., Beygelzimer, A., D’Alché-Buc, F., Fox, E. & Garnett, R.) (Curran Associates, Inc., 2019).

    Not in our library

36. 36.

    Nakago, K. torch-dftd. https://github.com/pfnet-research/torch-dftd (2021).

    Not in our library

37. 37.

    Dietzel PDC, Johnsen RE, Blom R, Fjellvåg H. Structural changes and coordinatively unsaturated metal atoms on dehydration of honeycomb analogous microporous metal-organic frameworks. Chem. - Eur. J. 2008;14:2389-2397.

    Not in our library10.1002/chem.200701370 (opens in a new tab)

38. 38.

    Furukawa, H., Cordova, K. E., O’Keeffe, M. & Yaghi, O. M. The chemistry and applications of metal-organic frameworks. Science341, 1230444 (2013).

    Not in our library10.1126/science.1230444 (opens in a new tab)

39. 39.

    Chui SS-Y, Lo SM-F, Charmant JPH, Orpen AG, Williams ID. A chemically functionalizable nanoporous material [Cu3(TMA)2(H2o)3]n. Science. 1999;283:1148-1150.

    Not in our library10.1126/science.283.5405.1148 (opens in a new tab)

40. 40.

    Liu X, Wang A, Zhang T, Su D-S, Mou C-Y. Au–Cu alloy nanoparticles supported on silica gel as catalyst for co oxidation: effects of Au/Cu ratios. Catal. Today. 2011;160:103-108.

    Not in our library10.1016/j.cattod.2010.05.019 (opens in a new tab)

41. 41.

    Li W, Wang A, Liu X, Zhang T. Silica-supported Au–Cu alloy nanoparticles as an efficient catalyst for selective oxidation of alcohols. Appl. Catal. A: Gen. 2012;433–434:146-151.

    Not in our library10.1016/j.apcata.2012.05.014 (opens in a new tab)

42. 42.

    Najafishirtari S, et al. Nanoscale transformations of alumina-supported AuCu ordered phase nanocrystals and their activity in co oxidation. ACS Catal. 2015;5:2154-2163.

    Not in our library10.1021/cs501923x (opens in a new tab)

43. 43.

    Guisbiers G, et al. Gold-copper nano-alloy, “tumbaga”, in the era of nano: phase diagram and segregation. Nano Lett. 2014;14:6718-6726.

    Not in our library10.1021/nl503584q (opens in a new tab)

44. 44.

    Mendoza-Cruz R, et al. Order–disorder phase transitions in Au–Cu nanocubes: from nano-thermodynamics to synthesis. Nanoscale. 2017;9:9267-9274.

    Not in our library10.1039/c7nr00028f (opens in a new tab)

45. 45.

    Dry ME. The fischer-tropsch process: 1950-2000. Catal. Today. 2002;71:227-241.

    Not in our library10.1016/s0920-5861(01)00453-9 (opens in a new tab)

46. 46.

    Zijlstra B, et al. The vital role of step-edge sites for both co activation and chain growth on cobalt fischer-tropsch catalysts revealed through first-principles-based microkinetic modeling including lateral interactions. ACS Catal. 2020;10:9376-9400.

    Not in our library10.1021/acscatal.0c02420 (opens in a new tab)

47. 47.

    Zijlstra B, Broos RJP, Chen W, Filot IAW, Hensen EJM. First-principles based microkinetic modeling of transient kinetics of co hydrogenation on cobalt catalysts. Catal. Today. 2020;342:131-141.

    Not in our library10.1016/j.cattod.2019.03.002 (opens in a new tab)

48. 48.

    Zijlstra B, et al. Coverage effects in co dissociation on metallic cobalt nanoparticles. ACS Catal. 2019;9:7365-7372.

    Not in our library10.1021/acscatal.9b01967 (opens in a new tab)

49. 49.

    Wang T, et al. Effect of vanadium promotion on activated carbon-supported cobalt catalysts in fischer–tropsch synthesis. Catal. Lett. 2006;107:47-52.

    Not in our library10.1007/s10562-005-9730-1 (opens in a new tab)

50. 50.

    Shimura K, Miyazawa T, Hanaoka T, Hirata S. Fischer–Tropsch synthesis over alumina supported cobalt catalyst: Effect of promoter addition. Appl. Catal. A: Gen. 2015;494:1-11.

    Not in our library10.1016/j.apcata.2015.01.017 (opens in a new tab)

51. 51.

    Yao K, Herr JE, Toth DW, Mckintyre R, Parkhill J. The tensormol-0.1 model chemistry: a neural network augmented with long-range physics. Chem. Sci. 2018;9:2261-2269.

    Not in our library10.1039/c7sc04934j (opens in a new tab)

52. 52.

    Takamoto, S. et al. High-temperature multi-element 2021 (HME21) dataset. figshare 10.6084/m9.figshare.19658538 (2022).

    Not in our library

53. 53.

    Kirklin S, et al. The open quantum materials database (oqmd): assessing the accuracy of dft formation energies. npj Comput. Mater. 2015;1:15010.

    Not in our library10.1038/npjcompumats.2015.10 (opens in a new tab)

54. 54.

    Draxl, C. & Scheffler, M. Nomad: The fair concept for big-data-driven materials science. MRS Bulletin43, 676–682 (2018).

    Not in our library

55. 55.

    Choudhary K, et al. The joint automated repository for various integrated simulations (jarvis) for data-driven materials design. npj Comput. Mater. 2020;6:173.

    Not in our library10.1038/s41524-020-00440-1 (opens in a new tab)

56. 56.

    Curtarolo S, et al. Aflow: an automatic framework for high-throughput materials discovery. Comput. Mater. Sci. 2012;58:218-226.

    Not in our library10.1016/j.commatsci.2012.02.005 (opens in a new tab)

57. 57.

    Nakata M, Shimazaki T. Pubchemqc project: a large-scale first-principles electronic structure database for data-driven chemistry. J. Chem. Inf. Model. 2017;57:1300-1308.

    Not in our library10.1021/acs.jcim.7b00083 (opens in a new tab)

58. 58.

    Chmiela, S. et al. Machine learning of accurate energy-conserving molecular force fields. Sci. Adv.3, e1603015 (2017).

    Not in our library10.1126/sciadv.1603015 (opens in a new tab)

59. 59.

    Unke OT, Meuwly M. Physnet: a neural network for predicting energies, forces, dipole moments and partial charges. J. Chem. Theory Comput. 2019;15:3678-3693.

    Not in our library10.1021/acs.jctc.9b00181 (opens in a new tab)

60. 60.

    Takamoto S, Izumi S, Li J. Teanet: universal neural network interatomic potential inspired by iterative electronic relaxations. Comput. Mater. Sci. 2022;207:111280.

    Not in our library10.1016/j.commatsci.2022.111280 (opens in a new tab)

61. 61.

    Chai J-D, Head-Gordon M. Long-range corrected hybrid density functionals with damped atom–atom dispersion corrections. Phys. Chem. Chem. Phys. 2008;10:6615-6620.

    Not in our library10.1039/b810189b (opens in a new tab)

62. 62.

    Ditchfield R, Hehre WJ, Pople JA. Self-consistent molecular-orbital methods. ix. an extended gaussian-type basis for molecular-orbital studies of organic molecules. J. Chem. Phys. 1971;54:724-728.

    Not in our library10.1063/1.1674902 (opens in a new tab)

63. 63.

    Frisch, M. J. et al. Gaussian16 Revision C.01 (Gaussian Inc., Wallingford, CT, 2016).

    Not in our library

64. 64.

    Perdew JP, Burke K, Ernzerhof M. Generalized gradient approximation made simple. Phys. Rev. Lett. 1996;77:3865.

    Not in our library10.1103/physrevlett.77.3865 (opens in a new tab)

65. 65.

    Kresse G, Hafner J. Ab initio molecular dynamics for liquid metals. Phys. Rev. B. 1993;47:558.

    Not in our library10.1103/physrevb.47.558 (opens in a new tab)

66. 66.

    Kresse G, Hafner J. Ab initio molecular-dynamics simulation of the liquid-metal–amorphous–semiconductor transition in germanium. Phys. Rev. B. 1994;49:14251.

    Not in our library10.1103/physrevb.49.14251 (opens in a new tab)

67. 67.

    Kresse G, Furthmüller J. Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set. Comput. Mater. Sci. 1996;6:15-50.

    Not in our library10.1016/0927-0256(96)00008-0 (opens in a new tab)

68. 68.

    Kresse G, Furthmüller J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys. Rev. B. 1996;54:11169.

    Not in our library10.1103/physrevb.54.11169 (opens in a new tab)

69. 69.

    Hacene M, et al. Accelerating vasp electronic structure calculations using graphic processing units. J. Comput. Chem. 2012;33:2581-2589.

    Not in our library10.1002/jcc.23096 (opens in a new tab)

70. 70.

    Hutchinson M, Widom M. Vasp on a gpu: application to exact-exchange calculations of the stability of elemental boron. Comput. Phys. Commun. 2012;183:1422-1426.

    Not in our library10.1016/j.cpc.2012.02.017 (opens in a new tab)

71. 71.

    Blöchl PE. Projector augmented-wave method. Phys. Rev. B. 1994;50:17953.

    Not in our library10.1103/physrevb.50.17953 (opens in a new tab)

72. 72.

    Kresse G, Joubert D. From ultrasoft pseudopotentials to the projector augmented-wave method. Phys. Rev. B. 1999;59:1758.

    Not in our library10.1103/physrevb.59.1758 (opens in a new tab)

73. 73.

    Tang W, Sanville E, Henkelman G. A grid-based bader analysis algorithm without lattice bias. J. Phys.: Condens. Matter. 2009;21:084204.

    Not in our library10.1088/0953-8984/21/8/084204 (opens in a new tab)

74. 74.

    Sanville E, Kenny SD, Smith R, Henkelman G. Improved grid-based algorithm for bader charge allocation. J. Comput. Chem. 2007;28:899-908.

    Not in our library10.1002/jcc.20575 (opens in a new tab)

75. 75.

    Henkelman G, Arnaldsson A, Jónsson H. A fast and robust algorithm for bader decomposition of charge density. Comput. Mater. Sci. 2006;36:354-360.

    Not in our library10.1016/j.commatsci.2005.04.010 (opens in a new tab)

76. 76.

    Yu M, Trinkle DR. Accurate and efficient algorithm for bader charge integration. J. Chem. Phys. 2011;134:064111.

    Not in our library10.1063/1.3553716 (opens in a new tab)

77. 77.

    Wang L, Maxisch T, Ceder G. Oxidation energies of transition metal oxides within the gga+ u framework. Phys. Rev. B. 2006;73:195107.

    Not in our library10.1103/physrevb.73.195107 (opens in a new tab)

Cited by papers we hold 1

• DeePMD-kit v2: A software package for deep potential models · 2023
  No notice

Questions about this paper

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.