Abstract
Training an interatomic potential (IP) to predict material properties requires appropriate experimental or first principles, e.g. density functional theory (DFT), ground truth values, along with an efficient optimization algorithm to select parameter values. Atomistic simulations are required to check each proposed parameter set, which can be costly depending on the desired property. We present an optimization algorithm that leverages existing model parameter data with a dual neural network approach to accelerate the fitting process. We extract model parameters from OpenKIM and identify correlations between them and select material properties. We then create a surrogate model and couple it with an optimization algorithm to determine the desired IP parameters. This information can be leveraged, along with DFT training data and additional atomistic simulations, to further optimize the parameters. We believe this framework can be used to expedite the optimization process and enable better models for large scale properties.
Graphic abstract
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The python code and data used for this paper will be made available at: https://github.com/bjasperson/MEAM-Opt.
References
J.A. Martinez, D.E. Yilmaz, T. Liang, S.B. Sinnott, S.R. Phillpot, Fitting empirical potentials: Challenges and methodologies. Curr. Opin. Solid State Mater. Sci. 17(6), 263–270 (2023). https://doi.org/10.1016/j.cossms.2013.09.001
F. Ercolessi, J.B. Adams, Interatomic potentials from first-principles calculations: The force-matching method. Europhys. Lett. (EPL) 26(8), 583–588 (2022). https://doi.org/10.1209/0295-5075/26/8/005
P. Brommer, A. Kiselev, D. Schopf, P. Beck, J. Roth, H.-R. Trebin, Classical interaction potentials for diverse materials from ab initio data: a review of potfit. Modell. Simul. Mater. Sci. Eng. 23(7), 074002 (2023). https://doi.org/10.1088/0965-0393/23/7/074002
R. Kobayashi, Nap: a molecular dynamics package with parameter-optimization programs for classical and machine-learning potentials. J. Open Source Softw. 6(57), 2768 (2023)
M. Wen, Y. Afshar, R.S. Elliott, E.B. Tadmor, KLIFF: A framework to develop physics-based and machine learning interatomic potentials. Comput. Phys. Commun. 272, 108218 (2023). https://doi.org/10.1016/j.cpc.2021.108218
V.L. Deringer, M.A. Caro, G. Csányi, Machine learning interatomic potentials as emerging tools for materials science. Adv. Mater. 31(46), 1902765 (2023). https://doi.org/10.1002/adma.201902765
P. Friederich, F. Häse, J. Proppe, A. Aspuru-Guzik, Machine-learned potentials for next-generation matter simulations. Nat. Mater. 20(6), 750–761 (2023). https://doi.org/10.1038/s41563-020-0777-6
A.M. Miksch, T. Morawietz, J. Kästner, A. Urban, N. Artrith, Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations. Mach. Learn.: Sci. Technol. 2(3), 031001 (2023). https://doi.org/10.1088/2632-2153/abfd96
M.F. Langer, A. Goeßmann, M. Rupp, Representations of molecules and materials for interpolation of quantum-mechanical simulations via machine learning. NPJ Comput. Mater. 8(1), 41 (2023). https://doi.org/10.1038/s41524-022-00721-x
S.R. Xie, M. Rupp, R.G. Hennig, Ultra-fast interpretable machine-learning potentials. NPJ Comput. Mater. 9(1), 162 (2023). https://doi.org/10.1038/s41524-023-01092-7
L.A. Zepeda-Ruiz, A. Stukowski, T. Oppelstrup, V.V. Bulatov, Probing the limits of metal plasticity with molecular dynamics simulations. Nature 550(7677), 492–495 (2022). https://doi.org/10.1038/nature23472
T.P. Senftle, S. Hong, M.M. Islam, S.B. Kylasa, Y. Zheng, Y.K. Shin, C. Junkermeier, R. Engel-Herbert, M.J. Janik, H.M. Aktulga, T. Verstraelen, A. Grama, A.C.T. Duin, The ReaxFF reactive force-field: development, applications and future directions. NPJ Comput. Mater. 2(1), 15011 (2021). https://doi.org/10.1038/npjcompumats.2015.11
M. Dittner, J. Müller, H.M. Aktulga, B. Hartke, Efficient global optimization of reactive force-field parameters. J. Comput. Chem. 36(20), 1550–1561 (2023). https://doi.org/10.1002/jcc.23966
A. Jain, S.P. Ong, G. Hautier, W. Chen, W.D. Richards, S. Dacek, S. Cholia, D. Gunter, D. Skinner, G. Ceder, K.A. Persson, Commentary: the materials project: a materials genome approach to accelerating materials innovation. APL Mater. 1(1), 011002 (2023). https://doi.org/10.1063/1.4812323
K. Choudhary, K.F. Garrity, A.C.E. Reid, B. DeCost, A.J. Biacchi, A.R. Hight Walker, Z. Trautt, J. Hattrick-Simpers, A.G. Kusne, A. Centrone, A. Davydov, J. Jiang, R. Pachter, G. Cheon, E. Reed, A. Agrawal, X. Qian, V. Sharma, H. Zhuang, S.V. Kalinin, B.G. Sumpter, G. Pilania, P. Acar, S. Mandal, K. Haule, D. Vanderbilt, K. Rabe, F. Tavazza, The joint automated repository for various integrated simulations (JARVIS) for data-driven materials design. NPJ Comput. Mater. 6(1), 173 (2023). https://doi.org/10.1038/s41524-020-00440-1
E.B. Tadmor, R.S. Elliott, J.P. Sethna, R.E. Miller, C.A. Becker, The potential of atomistic simulations and the knowledgebase of interatomic models. JOM 63(7), 17–17 (2023). https://doi.org/10.1007/s11837-011-0102-6
B.A. Jasperson, M.G. Wood, H.T. Johnson, A dual neural network approach to topology optimization for thermal-electromagnetic device design. Comput. Aided Des. (2023). https://doi.org/10.1016/j.cad.2023.103665
M.I. Baskes, Modified embedded-atom potentials for cubic materials and impurities. Phys. Rev. B 46(5), 2727–2742 (2023). https://doi.org/10.1103/PhysRevB.46.2727
A.P. Thompson, H.M. Aktulga, R. Berger, D.S. Bolintineanu, W.M. Brown, P.S. Crozier, P.J. Veld, A. Kohlmeyer, S.G. Moore, T.D. Nguyen, R. Shan, M.J. Stevens, J. Tranchida, C. Trott, S.J. Plimpton, LAMMPS - a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales. Comput. Phys. Commun. 271, 108171 (2021). https://doi.org/10.1016/j.cpc.2021.108171
M.I. Baskes, J.S. Nelson, A.F. Wright, Semiempirical modified embedded-atom potentials for silicon and germanium. Phys. Rev. B 40(9), 6085–6100 (2023). https://doi.org/10.1103/PhysRevB.40.6085
R.S. Elliott, E.B. Tadmor, Knowledgebase of interatomic models (KIM) application programming interface (API). OpenKIM (2023). https://doi.org/10.25950/FF8F563A
Y. Afshar, S. Hütter, R. Rudd, A. Stukowski, W. Tipton, D. Trinkle, G. Wagner, P. Zhang, E. Alonso, M. Baskes, V. Bulatov, T. Rubia, J. Kim, J. Kress, B.-J. Lee, T. Lenosky, J. Nelson, B. Sadigh, A. Voter, A. Wright, The modified embedded atom method (MEAM) potential v002. OpenKIM (2023). https://doi.org/10.25950/EE5EBA52
A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., An imperative style, high-performance deep learning library. Adv. Neural. Inform. Process. Syst. 32, 1 (2019)
S. Kavousi, B.R. Novak, M.I. Baskes, M.A. Zaeem, D. Moldovan, Modified embedded-atom method potential for high-temperature crystal-melt properties of ti-ni alloys and its application to phase field simulation of solidification. Modell. Simul. Mater. Sci. Eng. 28(1), 015006 (2023). https://doi.org/10.1088/1361-651X/ab580c
A.C.E. Silva, J. Agren, M.T. Clavaguera-Mora, D. Djurovic, T. Gomez-Acebo, B.-J. Lee, Z.-K. Liu, P. Miodownik, H.J. Seifert, Applications of computational thermodynamics—the extension from phase equilibrium to phase transformations and other properties. Calphad 31(1), 53–74 (2023). https://doi.org/10.1016/j.calphad.2006.02.006
D. Liu, Y. Tan, E. Khoram, Z. Yu, Training deep neural networks for the inverse design of nanophotonic structures. ACS Photonics 5(4), 1365–1369 (2022). https://doi.org/10.1021/acsphotonics.7b01377
X. Zheng, P. Zheng, R.-Z. Zhang, Machine learning material properties from the periodic table using convolutional neural networks. Chem. Sci. 9(44), 8426–8432 (2018). https://doi.org/10.1039/c8sc02648c
Acknowledgments
The authors acknowledge helpful comments from the OpenKIM team (Dr. Ilia Nikiforov, Professor Ellad Tadmor, Dr. Brendon Waters and others).
Funding
This material is based in part upon work supported by the National Science Foundation under Grant No. 1922758.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by BJ. The first draft of the manuscript was written by BJ and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
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.
Supplementary Information
Below is the link to the electronic supplementary material.
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.
About this article
Cite this article
Jasperson, B.A., Johnson, H.T. A data-driven method for optimization of classical interatomic potentials. MRS Advances 9, 863–869 (2024). https://doi.org/10.1557/s43580-024-00802-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1557/s43580-024-00802-7