Skip to main content
SpringerLink
Log in

Accelerating training of MLIPs through small-cell training

  • Invited Paper
  • FOCUS ISSUE: Machine-learned Potentials in Materials Research
  • Published:
Journal of Materials Research Aims and scope Submit manuscript

Abstract

While machine-learned interatomic potentials have become a mainstay for modeling materials, designing training sets that lead to robust potentials is challenging. Automated methods, such as active learning and on-the-fly learning, construct reliable training sets, but these processes can be resource-intensive. Current training approaches often use density functional theory calculations that have the same cell size as the simulations that the potential is explicitly trained to model. Here, we demonstrate an easy-to-implement small-cell training protocol and use it to model the Zr-H system. This training leads to a potential that accurately predicts known stable Zr-H phases and reproduces the \(\alpha\)-\(\beta\) pure zirconium phase transition in molecular dynamics simulations. Compared to traditional active learning, small-cell training decreased the training time of the \(\alpha\)-\(\beta\) zirconium phase transition by approximately 20 times. The potential describes the phase transition with a degree of accuracy similar to that of the large-cell training method.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6

Similar content being viewed by others

Data availability

The moment tensor potential file (pot.mtp) and the training set file (train.cfg) are available at https://github.com/jmeziere/Zr-H-Potential.

Notes

  1. The parameters used for the VASP calculations of this training set were not the same as the parameters shown in Table 2. However, the only significant parameter change from the parameters in Table 2 was a change in ENCUT from 400 eV to 500 eV. Because 400 eV is a reasonable value of ENCUT for the Zr system, this should not affect the training results significantly.

References

  1. V.L. Deringer, M.A. Caro, G. Csányi, Adv. Mater. 31, 1902765 (2019)

    Google Scholar 

  2. Y. Lysogorskiy, C.V.D. Oord, A. Bochkarev, S. Menon, M. Rinaldi, T. Hammerschmidt, M. Mrovec, A. Thompson, G. Csányi, C. Ortner, R. Drautz, npj Comput. Mater. 7, 97 (2021). https://doi.org/10.1038/s41524-021-00559-9

    Article  Google Scholar 

  3. A.V. Shapeev, Multisc. Model. Simul. 14, 1153 (2016). https://doi.org/10.1137/15M1054183

    Article  Google Scholar 

  4. J. Behler, Phys. Chem. Chem. Phys. 13, 17930 (2011). https://doi.org/10.1039/C1CP21668F

    Article  Google Scholar 

  5. W.J. Szlachta, A.P. Bartók, G. Csányi, Phys. Rev. B 90, 104108 (2014)

    Google Scholar 

  6. A.P. Bartók, M.C. Payne, R. Kondor, G. Csányi, Phys. Rev. Lett. 104, 136403 (2010)

    Google Scholar 

  7. J.A. Vita, D.R. Trinkle, Comput. Mater. Sci. 200, 110752 (2021)

    Google Scholar 

  8. A.P. Bartók, R. Kondor, G. Csányi, Phys. Rev. B 87, 184115 (2013)

    Google Scholar 

  9. C.W. Rosenbrock, K. Gubaev, A.V. Shapeev, L.B. Pártay, N. Bernstein, G. Csányi, G.L.W. Hart, npj Comput. Mater. 7, 1 (2021). https://doi.org/10.1038/s41524-020-00477-2

    Article  Google Scholar 

  10. M.S. Daw, M.I. Baskes, Phys. Rev. Lett. 50, 1285 (1983). https://doi.org/10.1103/PhysRevLett.50.1285

    Article  Google Scholar 

  11. M.S. Daw, M.I. Baskes, Phys. Rev. B 29, 6443 (1984). https://doi.org/10.1103/PhysRevB.29.6443

    Article  Google Scholar 

  12. A. Takahashi, A. Seko, I. Tanaka, Phys. Rev. Mater. 1, 063801 (2017)

    Google Scholar 

  13. E. Wimmer, M. Christensen, W. Wolf, W.H. Howland, B. Kammenzind, R.W. Smith, J. Nucl. Mater. 532, 152055 (2020)

    Google Scholar 

  14. S. Starikov, D. Smirnova, Comput. Mater. Sci. 197, 110581 (2021)

    Google Scholar 

  15. O.G. Nicholls, D.G. Frost, V. Tuli, J. Smutna, M.R. Wenman, P.A. Burr, J. Nucl. Mater. 584, 154391 (2023)

    Google Scholar 

  16. A.P. Bartók, J. Kermode, N. Bernstein, G. Csányi, Phys. Rev. X 8, 041048 (2018)

    Google Scholar 

  17. E.V. Podryabinkin, A.V. Shapeev, Comput.l Mater. Sci. 140, 171 (2017). https://doi.org/10.1016/j.commatsci.2017.08.031

    Article  Google Scholar 

  18. M. Hodapp, A. Shapeev, Phys. Rev. Mater. 5, 113802 (2021)

    Google Scholar 

  19. E.V. Podryabinkin, E.V. Tikhonov, A.V. Shapeev, A.R. Oganov, Phys. Rev. B 99, 064114 (2019)

    Google Scholar 

  20. L. Zhang, D.Y. Lin, H. Wang, R. Car, Phys. Rev. Mater. 3, 023804 (2019)

    Google Scholar 

  21. I.S. Novikov, K. Gubaev, E.V. Podryabinkin, A.V. Shapeev, Mach. Learn. Sci. Technol. 2, 025002 (2021)

    Google Scholar 

  22. A. Shapeev, K. Gubaev, E. Tsymbalov, E. Podryabinkin, Active Learning and Uncertainty Estimation, in Machine Learning Meets Quantum Physics. ed. by K.T. Schütt, S. Chmiela, O.A. von Lilienfeld, A. Tkatchenko, K. Tsuda, K.R. Müller (Springer, Cham, 2020), pp.309–329

    Google Scholar 

  23. C.J. Pickard, Phys. Rev. B 106, 014102 (2022). https://doi.org/10.1103/PhysRevB.106.014102

    Article  Google Scholar 

  24. S. Kass, J. Electrochem. Soc. 107, 594 (1960)

    Google Scholar 

  25. C.R.F. Azevedo, Eng. Fail. Anal. 18, 1943 (2011). https://doi.org/10.1016/j.engfailanal.2011.06.010

    Article  Google Scholar 

  26. B. Kammenzind, B. Berquist, R. Bajaj, P. Kreyns, D. Franklin, STP 1354, 196 (2000)

    Google Scholar 

  27. J. Kearns, J. Nucl. Mater. 22, 292 (1967)

    Google Scholar 

  28. Z. Duan, H. Yang, Y. Satoh, K. Murakami, S. Kano, Z. Zhao, J. Shen, H. Abe, Nucl. Eng. Des. 316, 131 (2017). https://doi.org/10.1016/j.nucengdes.2017.02.031

    Article  Google Scholar 

  29. A.T. Motta, L. Capolungo, L.-Q. Chen, M.N. Cinbiz, M.R. Daymond, D.A. Koss, E. Lacroix, G. Pastore, P.C.A. Simon, M.R. Tonks, B.D. Wirth, M.A. Zikry, J. Nucl. Mater. 518, 440 (2019). https://doi.org/10.1016/j.jnucmat.2019.02.042

    Article  Google Scholar 

  30. C. Ells, J. Nucl. Mater. 28, 129 (1968)

    Google Scholar 

  31. R. Daum, Y. Chu, A. Motta, J. Nucl. Mater. 392, 453 (2009)

    Google Scholar 

  32. F. Long, N. Badr, Z. Yao, M. Daymond, J. Nucl. Mater. 543, 152540 (2021)

    Google Scholar 

  33. R. Beck, Am. Soc. Metals Trans. Quart. 55, 1–10 (1962)

    Google Scholar 

  34. G. Carpenter, Acta Metall. 26, 1225 (1978)

    Google Scholar 

  35. G. McRae, C. Coleman, J. Nucl. Mater. 499, 622 (2018)

    Google Scholar 

  36. N. Badr, F. Long, Y. Luo, M. Topping, L. Béland, Z. Yao, M. Daymond, Acta Mater. 247, 118729 (2023)

    Google Scholar 

  37. L. Lanzani, M. Ruch, J. Nucl. Mater. 324, 165 (2004). https://doi.org/10.1016/j.jnucmat.2003.09.013

    Article  Google Scholar 

  38. E. Tulk, M. Kerr, M. Daymond, J. Nucl. Mater. 425, 93 (2012)

    Google Scholar 

  39. G. Carpenter, J. Nucl. Mater. 48, 264 (1973)

    Google Scholar 

  40. I.C. Njifon, E. Torres, Acta Mater. 202, 222 (2021)

    Google Scholar 

  41. C. Domain, R. Besson, A. Legris, Acta Mater. 50, 3513 (2002)

    Google Scholar 

  42. Y. Udagawa, M. Yamaguchi, H. Abe, N. Sekimura, T. Fuketa, Acta Mater. 58, 3927 (2010)

    Google Scholar 

  43. W. Zhu, R. Wang, G. Shu, P. Wu, H. Xiao, J. Phys. Chem. C 114, 22361 (2010)

    Google Scholar 

  44. F. Wang, H. Gong, Int. J. Hydrog. Energy 37, 12393 (2012)

    Google Scholar 

  45. P. Olsson, A. Massih, J. Blomqvist, A.M.A. Holston, C. Bjerkén, Comput. Mater. Sci. 86, 211 (2014)

    Google Scholar 

  46. X. Zhu, D.Y. Lin, J. Fang, X.Y. Gao, Y.F. Zhao, H.F. Song, Comput. Mater. Sci. 150, 77 (2018)

    Google Scholar 

  47. M. Christensen, W. Wolf, C. Freeman, E. Wimmer, R. Adamson, L. Hallstadius, P. Cantonwine, E. Mader, J. Phys. Condens. Matter 27, 025402 (2015)

    Google Scholar 

  48. G.Y. Huang, B.D. Wirth, J. Appl. Phys. 126, 135105 (2019)

    Google Scholar 

  49. G.L.W. Hart, R.W. Forcade, Phys. Rev. B 77, 224115 (2008). https://doi.org/10.1103/PhysRevB.77.224115

    Article  Google Scholar 

  50. G.L.W. Hart, R.W. Forcade, Phys. Rev. B 80, 014120 (2009)

    Google Scholar 

  51. L. Zhang, Y.H. Li, Y.Q. Gu, L.C. Cai, Sci. Rep. 9, 16889 (2019). https://doi.org/10.1038/s41598-019-53088-3

    Article  Google Scholar 

  52. E. Zuzek, J. Abriata, A. San-Martin, F. Manchester, Phase Diagrams of Binary Hydrogen Alloys (ASM International, Almere, 2000), p.309

    Google Scholar 

  53. E. Zuzek, J. Abriata, A. San-Martin, F. Manchester, Phase Diagrams of Binary Hydrogen Alloys (ASM International, Almere, 1990), p.385

    Google Scholar 

  54. C. Nyshadham, C. Oses, J.E. Hansen, I. Takeuchi, S. Curtarolo, G.L.W. Hart, Acta Mater. 122, 438 (2017). https://doi.org/10.1016/j.actamat.2016.09.017

    Article  Google Scholar 

  55. O. Levy, G.L.W. Hart, S. Curtarolo, Acta Mater. 58, 2887 (2010). https://doi.org/10.1016/j.actamat.2010.01.017

    Article  Google Scholar 

  56. O. Levy, G.L.W. Hart, S. Curtarolo, J. Am. Chem. Soc. 132, 4830 (2010). https://doi.org/10.1021/ja9105623

    Article  Google Scholar 

  57. K. Gubaev, E.V. Podryabinkin, G.L.W. Hart, A.V. Shapeev, Comput. Mater. Sci. 156, 148 (2019). https://doi.org/10.1016/j.commatsci.2018.09.031

    Article  Google Scholar 

  58. W.S. Morgan, G.L.W. Hart, R.W. Forcade, Comput. Mater. Sci. 136, 144 (2017). https://doi.org/10.1016/j.commatsci.2017.04.015

    Article  Google Scholar 

  59. G. Kresse, J. Furthmüller, Comput. Mater. Sci. 6, 15 (1996). https://doi.org/10.1016/0927-0256(96)00008-0

    Article  Google Scholar 

  60. G. Kresse, J. Furthmüller, Phys. Rev. B 54, 11169 (1996b). https://doi.org/10.1103/PhysRevB.54.11169

    Article  Google Scholar 

  61. Y. Li, R. Rogge, R. Holt, J. Nuclear Mater. 437, 10 (2006)

    Google Scholar 

  62. A.P. Thompson, H.M. Aktulga, R. Berger, D.S. Bolintineanu, W.M. Brown, P.S. Crozier, P.J. Int Veld, A. Kohlmeyer, S.G. Moore, T.D. Nguyen, R. Shan, M.J. Stevens, J. Tranchida, C. Trott, S.J. Plimpton, Comput. Phys. Commun. 271, 108171 (2022). https://doi.org/10.1016/j.cpc.2021.108171

    Article  Google Scholar 

  63. P. Liu, C. Verdi, F. Karsai, G. Kresse, Phys. Rev. Mater. 5, 053804 (2021)

    Google Scholar 

  64. The parameters used for the VASP calculations of this training set were not the same as the parameters shown in Table 2. However, the only significant parameter change from the parameters in Table 2 was a change in ENCUT from 400 eV to 500 eV. Because 400 eV is a reasonable value of ENCUT for the Zr system, this should not affect the training results significantly

  65. S.P. Ong, W.D. Richards, A. Jain, G. Hautier, M. Kocher, S. Cholia, D. Gunter, V.L. Chevrier, K.A. Persson, G. Ceder, Comput. Mater. Sci. 68, 314 (2013). https://doi.org/10.1016/j.commatsci.2012.10.028

    Article  Google Scholar 

  66. A. Togo, L. Chaput, T. Tadano, I. Tanaka, J. Phys. Condens. Matter 35, 353001 (2023). https://doi.org/10.1088/1361-648X/acd831

    Article  Google Scholar 

Download references

Funding

This work was funded by the Advanced Materials Simulation Engineering Tool (AMSET) project, sponsored by the US Naval Nuclear Laboratory (NNL) and directed by Materials Design, Inc. YL, MRD, and LKB thank the Digital Research Alliance of Canada (formerly known as Compute Canada) for generous allocation of compute resources, and the Natural Sciences and Engineering Research Council of Canada (NSERC) and the NSERC/UNENE Industrial Research Chair in Nuclear Materials at Queen’s for financial support.

Author information

Authors and Affiliations

  1. Department of Physics, Brigham Young University, Provo, UT, 84602, USA

    Jason A. Meziere & Gus L. W. Hart

  2. Department of Mechanical and Materials Engineering, Queen’s University, Kingston, ON, K7L 2N8, Canada

    Yu Luo, Laurent Karim Béland & Mark R. Daymond

  3. Department of Mechanical and Materials Engineering, Portland State University, Portland, OR, 97201, USA

    Yi Xia

Authors
  1. Jason A. Meziere
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yu Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yi Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Laurent Karim Béland
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mark R. Daymond
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Gus L. W. Hart
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

JM: Conceptualization, Methodology, Formal analysis and investigation, Writing—original draft preparation, Writing—review and editing. YL: Formal analysis and investigation, Writing—review and editing. YX: Formal analysis and investigation, Writing—review and editing. LKB: Formal analysis and investigation, Writing—review and editing. MD: Formal Analysis and investigation, Writing—review and edition, Funding acquisition. GLWH: Conceputalization, Methodology, Formal analysis and investigation, Writing—review and edition, Funding acquisition, Resources, Supervision.

Corresponding author

Correspondence to Jason A. Meziere.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Meziere, J.A., Luo, Y., Xia, Y. et al. Accelerating training of MLIPs through small-cell training. Journal of Materials Research 38, 5095–5105 (2023). https://doi.org/10.1557/s43578-023-01194-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1557/s43578-023-01194-4

Search

Navigation