Hostname: page-component-89b8bd64d-nlwjb Total loading time: 0 Render date: 2026-05-07T00:37:23.880Z Has data issue: false hasContentIssue false
  • English
  • Français

Parameterization of empirical forcefields for glassy silica using machine learning

Published online by Cambridge University Press:  23 May 2019

Han Liu ,
Zipeng Fu ,
Yipeng Li ,
Nazreen Farina Ahmad Sabri  and
Mathieu Bauchy
Han Liu
Affiliation:
Physics of AmoRphous and Inorganic Solids Laboratory (PARISlab), Department of Civil and Environmental Engineering, University of California, Los Angeles, CA 90095, USA
Zipeng Fu
Affiliation:
Physics of AmoRphous and Inorganic Solids Laboratory (PARISlab), Department of Civil and Environmental Engineering, University of California, Los Angeles, CA 90095, USA Department of Computer Science, University of California, Los Angeles, CA 90095, USA
Yipeng Li
Affiliation:
Physics of AmoRphous and Inorganic Solids Laboratory (PARISlab), Department of Civil and Environmental Engineering, University of California, Los Angeles, CA 90095, USA
Nazreen Farina Ahmad Sabri
Affiliation:
Physics of AmoRphous and Inorganic Solids Laboratory (PARISlab), Department of Civil and Environmental Engineering, University of California, Los Angeles, CA 90095, USA
Mathieu Bauchy*
Affiliation:
Physics of AmoRphous and Inorganic Solids Laboratory (PARISlab), Department of Civil and Environmental Engineering, University of California, Los Angeles, CA 90095, USA
*
Address all correspondence to Mathieu Bauchy at bauchy@ucla.edu
Get access

Abstract

The development of reliable, yet computationally efficient interatomic forcefields is key to facilitate the modeling of glasses. However, the parameterization of novel forcefields is challenging as the high number of parameters renders traditional optimization methods inefficient or subject to bias. Here, we present a new parameterization method based on machine learning, which combines ab initio molecular dynamics simulations and Bayesian optimization. By taking the example of glassy silica, we show that our method yields a new interatomic forcefield that offers an unprecedented agreement with ab initio simulations. This method offers a new route to efficiently parameterize new interatomic forcefields for disordered solids in a non-biased fashion.

Information

Type
Artificial Intelligence Research Letters
Information
MRS Communications , Volume 9 , Issue 2 , June 2019 , pp. 593 - 599
Copyright
Copyright © Materials Research Society 2019 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

1.Huang, P.Y., Kurasch, S., Alden, J.S., Shekhawat, A., Alemi, A.A., McEuen, P.L., Sethna, J.P., Kaiser, U., and Muller, D.A.: Imaging atomic rearrangements in two-dimensional silica glass: watching silica's dance. Science 342, 224–227 (2013). https://doi.org/10.1126/science.1242248.Google Scholar
2.Huang, L. and Kieffer, J.: Challenges in modeling mixed ionic-covalent glass formers. In Molecular Dynamics Simulations of Disordered Materials, edited by Massobrio, C., Du, J., Bernasconi, M., Salmon, P.S. (Springer Series in Materials Science; Springer International Publishing: New York, 2015), pp. 87–112. https://doi.org/10.1007/978-3-319-15675-0_4Google Scholar
3.Du, J.: Challenges in molecular dynamics simulations of multicomponent oxide glasses. In Molecular Dynamics Simulations of Disordered Materials, edited by Massobrio, C., Du, J., Bernasconi, M. and Salmon, P.S. (Springer Series in Materials Science; Springer International Publishing: New York, 2015), pp. 157–180Google Scholar
4.Bauchy, M.: Deciphering the atomic genome of glasses by topological constraint theory and molecular dynamics: a review. Comput. Mater. Sci. 159, 95–102 (2019). https://doi.org/10.1016/j.commatsci.2018.12.004.Google Scholar
5.Yu, Y., Wang, B., Wang, M., Sant, G., and Bauchy, M.: Revisiting silica with ReaxFF: towards improved predictions of glass structure and properties via reactive molecular dynamics. J. Non-Cryst. Solids 443, 148–154 (2016). https://doi.org/10.1016/j.jnoncrysol.2016.03.026.Google Scholar
6.Li, X., Song, W., Yang, K., Krishnan, N.M.A., Wang, B., Smedskjaer, M.M., Mauro, J.C., Sant, G., Balonis, M., and Bauchy, M.: Cooling rate effects in sodium silicate glasses: bridging the gap between molecular dynamics simulations and experiments. J. Chem. Phys. 147, 074501 (2017), https://doi.org/10.1063/1.4998611.Google Scholar
7.Ganster, P., Benoit, M., Delaye, J.-M., and Kob, W.: Structural and vibrational properties of a calcium aluminosilicate glass: classical force-fields vs. first-principles. Mol. Simul. 33, 1093–1103 (2007).Google Scholar
8.Behler, J.: Perspective: machine learning potentials for atomistic simulations. J. Chem. Phys. 145, 170901 (2016). https://doi.org/10.1063/1.4966192.Google Scholar
9.Carré, A., Ispas, S., Horbach, J., and Kob, W.: Developing empirical potentials from Ab initio simulations: the case of amorphous silica. Comput. Mater. Sci. 124, 323–334 (2016), https://doi.org/10.1016/j.commatsci.2016.07.041.Google Scholar
10.Bartók, A.P., Kermode, J., Bernstein, N., and Csányi, G.: Machine learning a general-purpose interatomic potential for silicon. Phys. Rev. X 8, 1–32 (2018). https://doi.org/10.1103/PhysRevX.8.041048 .Google Scholar
11.Sundararaman, S., Huang, L., Ispas, S., and Kob, W.: New optimization scheme to obtain interaction potentials for oxide glasses. J. Chem. Phys. 148, 194504 (2018), https://doi.org/10.1063/1.5023707.Google Scholar
12.Wang, M., Anoop Krishnan, N.M., Wang, B., Smedskjaer, M.M., Mauro, J.C., and Bauchy, M.: A new transferable interatomic potential for molecular dynamics simulations of borosilicate glasses. J. Non-Cryst. Solids 498, 294–304 (2018), https://doi.org/10.1016/j.jnoncrysol.2018.04.063.Google Scholar
13.Lane, J.M.D.: Cooling rate and stress relaxation in silica melts and glasses via microsecond molecular dynamics. Phys. Rev. E 92, 012320 (2015). https://doi.org/10.1103/PhysRevE.92.012320.Google Scholar
14.van Beest, B.W.H., Kramer, G.J., and van Santen, R.A.: Force fields for silicas and aluminophosphates based on Ab initio calculations. Phys. Rev. Lett. 64, 1955–1958 (1990), https://doi.org/10.1103/PhysRevLett.64.1955.Google Scholar
15.Carré, A., Horbach, J., Ispas, S., and Kob, W.: New fitting scheme to obtain effective potential from Car–Parrinello molecular-dynamics simulations: application to silica. EPL 82, 17001 (2008). https://doi.org/10.1209/0295-5075/82/17001.Google Scholar
16.Ercolessi, F. and Adams, J.B.: Interatomic potentials from first-principles calculations: the force-matching method. EPL 26, 583 (1994). https://doi.org/10.1209/0295-5075/26/8/005.Google Scholar
17.Shewchuk, J.R.: An Introduction to the Conjugate Gradient Method Without the Agonizing Pain (Carnegie Mellon University, 1994). https://www.cs.cmu.edu/~quake-papers/painless-conjugate-gradient.pdf.Google Scholar
18.Gubernatis, J.E. and Lookman, T.: Machine learning in materials design and discovery: examples from the present and suggestions for the future. Phys. Rev. Mater. 2, 1–15 (2018). https://doi.org/10.1103/PhysRevMaterials.2.120301.Google Scholar
19.Ramprasad, R., Batra, R., Pilania, G., Mannodi-Kanakkithodi, A., and Kim, C.: Machine learning in materials informatics: recent applications and prospects. NPJ Computat. Mater. 3, 54 (2017). https://doi.org/10.1038/s41524-017-0056-5.Google Scholar
20.Huan, T.D., Batra, R., Chapman, J., Krishnan, S., Chen, L., and Ramprasad, R.: A universal strategy for the creation of machine learning-based atomistic force fields. NPJ Computat. Mater. 3, 37 (2017). https://doi.org/10.1038/s41524-017-0042-y.Google Scholar
21.Li, Y., Li, H., Pickard, F.C., Narayanan, B., Sen, F.G., Chan, M.K.Y., Sankaranarayanan, S.K.R.S., Brooks, B.R., and Roux, B.: Machine learning force field parameters from Ab initio data. J. Chem. Theory Comput. 13, 4492–4503 (2017). https://doi.org/10.1021/acs.jctc.7b00521.Google Scholar
22.Hellström, M. and Behler, J.: Neural network potentials in materials modeling. In Handbook of Materials Modeling, edited by Andreoni, W. and Yip, S. (Springer International Publishing: Cham, 2018), pp. 1–20. https://doi.org/10.1007/978-3-319-42913-7_56-1.Google Scholar
23.Deringer, V.L. and Csányi, G.: Machine learning based interatomic potential for amorphous carbon. Phys. Rev. B 95, 094203 (2017), https://doi.org/10.1103/PhysRevB.95.094203.Google Scholar
24.Car, R. and Parrinello, M.: Unified approach for molecular dynamics and density-functional theory. Phys. Rev. Lett. 55, 2471–2474 (1985). https://doi.org/10.1103/PhysRevLett.55.2471.Google Scholar
25.Bansal, N.P. and Doremus, R.H.: Handbook of Glass Properties (Elsevier: New York, 2013).Google Scholar
26.Fennell, C.J. and Gezelter, J.D.: Is the Ewald summation still necessary? Pairwise alternatives to the accepted standard for long-range electrostatics. J. Chem. Phys. 124, 234104 (2006). https://doi.org/10.1063/1.2206581.Google Scholar
27.Wright, A.C.: The comparison of molecular dynamics simulations with diffraction experiments. J. Non-Cryst. Solids 159, 264–268 (1993). https://doi.org/10.1016/0022-3093(93)90232-M.Google Scholar
28.Frazier, P.I. and Wang, J.: Bayesian optimization for materials design. In Information Science for Materials Discovery and Design, edited by (Springer Series in Materials Science; Springer, Cham, 2016), pp 45–75. https://doi.org/10.1007/978-3-319-23871-5_3.Google Scholar
29.Rasmussen, C.E. and Williams, C.K.I.: Gaussian Processes for Machine Learning, 3. print. Adaptive computation and machine learning (MIT Press: Cambridge, MA, 2008).Google Scholar
30.Liu, H., Fu, Z., Li, Y., Sabri, N.F.A., and Bauchy, M.: Balance between accuracy and simplicity in empirical forcefields for glass modeling: insights from machine learning. J. Non-Cryst. Solids (2019). https://doi.org/10.1016/j.jnoncrysol.2019.04.020.Google Scholar
31.Wang, B., Yu, Y., Lee, Y.J., and Bauchy, M.: Intrinsic nano-ductility of glasses: the critical role of composition. Front. Mater. 2, 11 (2015). https://doi.org/10.3389/fmats.2015.00011.Google Scholar