journal article·2022-01-17Open access

Machine learned interatomic potentials using random features

Gurjot Dhaliwal, Prasanth B. Nair, Chandra Veer Singh

npj Computational Materials· Volume 8· Issue 1

Abstract

Abstract We present a method to model interatomic interactions such as energy and forces in a computationally efficient way. The proposed model approximates the energy/forces using a linear combination of random features, thereby enabling fast parameter estimation by solving a linear least-squares problem. We discuss how random features based on stationary and non-stationary kernels can be used for energy approximation and provide results for three classes of materials, namely two-dimensional materials, metals and semiconductors. Force and energy predictions made using the proposed method are in close agreement with density functional theory calculations, with training time that is 96% lower than standard kernel models. Molecular Dynamics calculations using random features based interatomic potentials are shown to agree well with experimental and density functional theory values. Phonon frequencies as computed by random features based interatomic potentials are within 0.1% of the density functional theory results. Furthermore, the proposed random features-based potential addresses scalability issues encountered in this class of machine learning problems.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Machine Learning in Materials Science · X-ray Diffraction in Crystallography · Computational Drug Discovery Methods

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (78)

Show source-provided references
1. Allen, M. P. & Tildesley, D. J. Computer Simulation of Liquids (Oxford University Press, 2017).10.1093/oso/9780198803195.001.0001 ↗
2. Griebel, M., Knapek, S. & Zumbusch, G. Numerical Simulation in Molecular Dynamics Vol. 5 (Society for Industrial and Applied Mathematics, 2007).
3. Becker, C. A., Tavazza, F. & Levine, L. E. Implications of the choice of interatomic potential on calculated planar faults and surface properties in nickel. Philos. Mag. 91, 3578–3597 (2011).10.1080/14786435.2011.587839 ↗
4. Becker, C. A., Tavazza, F., Trautt, Z. T. & de Macedo, R. A. B. Considerations for choosing and using force fields and interatomic potentials in materials science and engineering. Curr. Opin. Solid State Mater. Sci. 17, 277–283 (2013).10.1016/j.cossms.2013.10.001 ↗
5. Dhaliwal, G., Nair, P. B. & Singh, C. V. Uncertainty analysis and estimation of robust airebo parameters for graphene. Carbon 142, 300–310 (2019).10.1016/j.carbon.2018.10.020 ↗
6. Dhaliwal, G., Nair, P. B. & Singh, C. V. Uncertainty and sensitivity analysis of mechanical and thermal properties computed through embedded atom method potential. Comput. Mater. Sci. 166, 30–41 (2019).10.1016/j.commatsci.2019.03.060 ↗
7. 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).10.1103/PhysRevLett.104.136403 ↗
8. Behler, J. & Parrinello, M. Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys. Rev. Lett. 98, 146401 (2007).10.1103/PhysRevLett.98.146401 ↗
9. Nyshadham, C. Machine-learned multi-system surrogate models for materials prediction. npj Comput. Mater. 5, 51 (2019).10.1038/s41524-019-0189-9 ↗
10. Ramprasad, R., Batra, R., Pilania, G., Mannodi-Kanakkithodi, A. & Kim, C. Machine learning in materials informatics: Recent applications and prospects. npj Comput. Mater. 3, 54 (2017).10.1038/s41524-017-0056-5 ↗
11. Behler, J. Representing potential energy surfaces by high-dimensional neural network potentials. J. Phys.: Condens. Matter 26, 183001 (2014).
12. 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).10.1016/j.jcp.2014.12.018 ↗
13. Podryabinkin, E. V. & Shapeev, A. V. Active learning of linearly parametrized interatomic potentials. Comput. Mater. Sci. 140, 171–180 (2017).10.1016/j.commatsci.2017.08.031 ↗
14. Shapeev, A. V. Moment tensor potentials: A class of systematically improvable interatomic potentials. Multiscale Modeling Simul. 14, 1153–1173 (2016).10.1137/15M1054183 ↗
15. Botu, V., Batra, R., Chapman, J. & Ramprasad, R. Machine learning force fields: Construction, validation, and outlook. J. Phys. Chem. C. 121, 511–522 (2016).10.1021/acs.jpcc.6b10908 ↗
16. Hansen, K. Assessment and validation of machine learning methods for predicting molecular atomization energies. J. Chem. Theory Comput. 9, 3404–3419 (2013).10.1021/ct400195d ↗
17. Mueller, T., Kusne, A. G. & Ramprasad, R. Machine learning in materials science: Recent progress and emerging applications. Rev. Comput. Chem. 29, 186–273 (2016).
18. Behler, J. Perspective: Machine learning potentials for atomistic simulations. J. Chem. Phys. 145, 170901 (2016).10.1063/1.4966192 ↗
19. Behler, J. Atom-centered symmetry functions for constructing high-dimensional neural network potentials. J. Chem. Phys. 134, 074106 (2011).10.1063/1.3553717 ↗
20. Bartók, A. P., Kondor, R. & Csányi, G. On representing chemical environments. Phys. Rev. B 87, 184115 (2013).10.1103/PhysRevB.87.184115 ↗
21. Zhang, L. et al. End-to-end symmetry preserving inter-atomic potential energy model for finite and extended systems. Proceedings of the 32nd International Conference on Neural Information Processing Systems, 4441–4451 (2018).
22. Jia, W. et al. In SC20: International Conference for High Performance Computing, Networking, Storage and Analysis 1–14 (IEEE, 2020).
23. Rupp, M. Machine learning for quantum mechanics in a nutshell. Int. J. Quantum Chem. 115, 1058–1073 (2015).10.1002/qua.24954 ↗
24. Liu, Y., Zhao, T., Ju, W. & Shi, S. Materials discovery and design using machine learning. J. Materiomics 3, 159–177 (2017).10.1016/j.jmat.2017.08.002 ↗
25. Mishin, Y. Machine-learning interatomic potentials for materials science. Acta Mater. 214, 116980 (2021).10.1016/j.actamat.2021.116980 ↗
26. Deringer, V. L., Caro, M. A. & Csányi, G. Machine learning interatomic potentials as emerging tools for materials science. Adv. Mater. 31, 1902765 (2019).10.1002/adma.201902765 ↗
27. Behler, J. Four generations of high-dimensional neural network potentials. Chem. Rev. 121, 10037–10072 (2021).10.1021/acs.chemrev.0c00868 ↗
28. Rowe, P., Csányi, G., Alfè, D. & Michaelides, A. Development of a machine learning potential for graphene. Phys. Rev. B 97, 054303 (2018).10.1103/PhysRevB.97.054303 ↗
29. Deringer, V. L. & Csányi, G. Machine learning based interatomic potential for amorphous carbon. Phys. Rev. B 95, 094203 (2017).10.1103/PhysRevB.95.094203 ↗
30. Bartók, A. P., Kermode, J., Bernstein, N. & Csányi, G. Machine learning a general-purpose interatomic potential for silicon. Phys. Rev. X 8, 041048 (2018).
31. Szlachta, W. J., Bartók, A. P. & Csányi, G. Accuracy and transferability of Gaussian approximation potential models for tungsten. Phys. Rev. B 90, 104108 (2014).10.1103/PhysRevB.90.104108 ↗
32. Rosenbrock, C. W. Machine-learned interatomic potentials for alloys and alloy phase diagrams. npj Comput. Mater. 7, 1–9 (2021).10.1038/s41524-020-00477-2 ↗
33. Li, Z., Kermode, J. R. & De Vita, A. Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces. Phys. Rev. Lett. 114, 096405 (2015).10.1103/PhysRevLett.114.096405 ↗
34. Stuart, S. J., Tutein, A. B. & Harrison, J. A. A reactive potential for hydrocarbons with intermolecular interactions. J. Chem. Phys. 112, 6472–6486 (2000).10.1063/1.481208 ↗
35. Zhou, X. Atomic scale structure of sputtered metal multilayers. Acta Mater. 49, 4005–4015 (2001).10.1016/S1359-6454(01)00287-7 ↗
36. Xiong, K. & Wang, S. The online random Fourier features conjugate gradient algorithm. IEEE Signal Process. Lett. 26, 740–744 (2019).10.1109/LSP.2019.2907480 ↗
37. Nelsen, N. H. & Stuart, A. M. The random feature model for input-output maps between Banach spaces. SIAM J. Sci. Comput. 43, A3212–A3243 (2021).10.1137/20M133957X ↗
38. Hung, T. H. & Chien, P. A random Fourier feature method for emulating computer models with gradient information. Technometrics 63, 1–10 (2020).
39. Rahimi, A. & Recht, B. Random Features for Large-Scale Kernel Machines. Adv. Neural. Inf. Process. Syst. 1177–1184 (2008).
40. Rahimi, A. & Recht, B. In 2008 46th Annual Allerton Conference on Communication, Control, and Computing 555–561 (IEEE, 2008).
41. Avron, H., Kapralov, M., Musco, C., Musco, C., Velingker, A., & Zandieh, A. In Proceedings of the 34th International Conference on Machine Learning Vol. 70, 253–262 (JMLR. org, 2017).
42. Kar, P. & Karnick, H., Random feature maps for dot product kernels. Artif. Intell. Stat. 583–591 (2012).
43. Niederreiter, H. Random Number Generation and Quasi-Monte Carlo Methods (SIAM, 1992).10.1137/1.9781611970081 ↗
44. Yu, F. X. X., Suresh, A. T., Choromanski, K. M., Holtmann-Rice, D. N. & Kumar, S. Orthogonal random features. Adv. Neural. Inf. Process. Syst. 1975–1983 (2016).
45. Choromanski, K. M., Rowland, M. & Weller, A. The Unreasonable Effectiveness of Structured Random Orthogonal Embeddings. Adv. Neural. Inf. Process. Syst. 219–228 (2017).
46. Choromanski, K. et al. The geometry of random features. Int. Conf. Artif. Intell. Stat. 1–9 (2018).
47. Larsen, A. H. The atomic simulation environment-a python library for working with atoms. J. Phys.: Condens. Matter 29, 273002 (2017).
48. Birch, F. Finite elastic strain of cubic crystals. Phys. Rev. 71, 809 (1947).10.1103/PhysRev.71.809 ↗
49. O’Connor, T. C., Andzelm, J. & Robbins, M. O. Airebo-m: A reactive model for hydrocarbons at extreme pressures. J. Chem. Phys. 142, 024903 (2015).10.1063/1.4905549 ↗
50. Tersoff, J. Modeling solid-state chemistry: Interatomic potentials for multicomponent systems. Phys. Rev. B 39, 5566 (1989).10.1103/PhysRevB.39.5566 ↗
51. Huang, J. et al. Deep potential generation scheme and simulation protocol for the li10gep2s12-type superionic conductors. J. Chem. Phys. 154, 094703 (2021).10.1063/5.0041849 ↗
52. Evans, T. W. & Nair, P. B. Scalable Gaussian processes with grid-structured eigenfunctions (GP-GRIEF) Int. Conf. Mach. Learn. 1416–1425 (2018).
53. Kresse, G. & Hafner, J. Ab initio molecular dynamics for liquid metals. Phys. Rev. B 47, 558 (1993).10.1103/PhysRevB.47.558 ↗
54. Kresse, G. & Furthmüller, J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys. Rev. B 54, 11169 (1996).10.1103/PhysRevB.54.11169 ↗
55. Perdew, J. P., Burke, K. & Ernzerhof, M. Generalized gradient approximation made simple. Phys. Rev. Lett. 77, 3865 (1996).10.1103/PhysRevLett.77.3865 ↗
56. Blöchl, P. E. Projector augmented-wave method. Phys. Rev. B 50, 17953 (1994).10.1103/PhysRevB.50.17953 ↗
57. Kresse, G. & Joubert, D. From ultrasoft pseudopotentials to the projector augmented-wave method. Phys. Rev. B 59, 1758 (1999).10.1103/PhysRevB.59.1758 ↗
58. Monkhorst, H. J. & Pack, J. D. Special points for Brillouin-zone integrations. Phys. Rev. B 13, 5188 (1976).10.1103/PhysRevB.13.5188 ↗
59. Li, L., Reich, S. & Robertson, J. Defect energies of graphite: Density-functional calculations. Phys. Rev. B 72, 184109 (2005).10.1103/PhysRevB.72.184109 ↗
60. Behera, H. & Mukhopadhyay, G. In AIP Conference Proceedings, Vol. 1313, 152–155 (AIP, 2010).10.1063/1.3530474 ↗
61. Baskin, Y. & Meyer, L. Lattice constants of graphite at low temperatures. Phys. Rev. 100, 544 (1955).10.1103/PhysRev.100.544 ↗
62. Shulenburger, L. & Mattsson, T. R. Quantum monte carlo applied to solids. Phys. Rev. B 88, 245117 (2013).10.1103/PhysRevB.88.245117 ↗
63. Shin, H. et al. Cohesion energetics of carbon allotropes: Quantum Monte Carlo study. J. Chem. Phys. 140, 114702 (2014).10.1063/1.4867544 ↗
64. Lee, C., Wei, X., Kysar, J. W. & Hone, J. Measurement of the elastic properties and intrinsic strength of monolayer graphene. Science 321, 385–388 (2008).10.1126/science.1157996 ↗
65. Wei, X., Fragneaud, B., Marianetti, C. A. & Kysar, J. W. Nonlinear elastic behavior of graphene: Ab initio calculations to continuum description. Phys. Rev. B 80, 205407 (2009).10.1103/PhysRevB.80.205407 ↗
66. Wang, R., Wang, S., Wu, X. & Liang, X. First-principles calculations on third-order elastic constants and internal relaxation for monolayer graphene. Phys. B: Condens. Matter 405, 3501–3506 (2010).10.1016/j.physb.2010.05.032 ↗
67. Lide, D. R. CRC Handbook of Chemistry and Physics Vol. 85 (CRC Press, 2004).
68. Ochs, T., Beck, O., Elsässer, C. & Meyer, B. Symmetrical tilt grain boundaries in body-centred cubic transition metals: An ab initio local-density-functional study. Philos. Mag. A 80, 351–372 (2000).10.1080/01418610008212057 ↗
69. Wang, J., Zhou, Y., Li, M. & Hou, Q. A modified w–w interatomic potential based on ab initio calculations. Model. Simul. Mater. Sci. Eng. 22, 015004 (2013).10.1088/0965-0393/22/1/015004 ↗
70. Marinica, M. C. Interatomic potentials for modelling radiation defects and dislocations in tungsten. J. Phys.: Condens. Matter 25, 395502 (2013).
71. Grünwald, E. et al. Young’s modulus and Poisson’s ratio characterization of tungsten thin films via laser ultrasound. Mater. Today.: Proc. 2, 4289–4294 (2015).
72. Donohue, J. Structures of the Elements (John Wiley and Sons, Inc., 1974).
73. Mounet, N. & Marzari, N. First-principles determination of the structural, vibrational and thermodynamic properties of diamond, graphite, and derivatives. Phys. Rev. B 71, 205214 (2005).10.1103/PhysRevB.71.205214 ↗
74. McSkimin, H. & Andreatch Jr, P. Elastic moduli of diamond as a function of pressure and temperature. J. Appl. Phys. 43, 2944–2948 (1972).10.1063/1.1661636 ↗
75. McSkimin, H., Andreatch Jr, P. & Glynn, P. The elastic stiffness moduli of diamond. J. Appl. Phys. 43, 985–987 (1972).10.1063/1.1661318 ↗
76. Hebbache, M. First-principles calculations of the bulk modulus of diamond. Solid State Commun. 110, 559–564 (1999).10.1016/S0038-1098(99)00122-2 ↗
77. Klein, C. A. & Cardinale, G. F. Young’s modulus and Poisson’s ratio of CVD diamond. Diam. Relat. Mater. 2, 918–923 (1993).10.1016/0925-9635(93)90250-6 ↗
78. Finnis, M. & Sinclair, J. A simple empirical n-body potential for transition metals. Philos. Mag. A 50, 45–55 (1984).10.1080/01418618408244210 ↗