Abstract
We use graph convolutional neural networks (GCNNs) to produce fast and accurate predictions of the total energy of solid solution binary alloys. GCNNs allow us to abstract the lattice structure of a solid material as a graph, whereby atoms are modeled as nodes and metallic bonds as edges. This representation naturally incorporates information about the structure of the material, thereby eliminating the need for computationally expensive data pre-processing which would be required with standard neural network (NN) approaches. We train GCNNs on ab-initio density functional theory (DFT) for copper-gold (CuAu) and iron-platinum (FePt) data that has been generated by running the LSMS-3 code, which implements a locally self-consistent multiple scattering method, on OLCF supercomputers Titan and Summit. GCNN outperforms the ab-initio DFT simulation by orders of magnitude in terms of computational time to produce the estimate of the total energy for a given atomic configuration of the lattice structure. We compare the predictive performance of GCNN models against a standard NN such as dense feedforward multi-layer perceptron (MLP) by using the root-mean-squared errors to quantify the predictive quality of the deep learning (DL) models. We find that the attainable accuracy of GCNNs is at least an order of magnitude better than that of the MLP.
This manuscript has been authored in part by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Curtarolo, S., et al.: AFLOW: an automatic framework for high-throughput materials discovery. Comput. Mater. Sci. 58, 218–226 (2012)
Jain, A., et al.: Commentary: the materials project: a materials genome approach to accelerating materials innovation. APL Mater. 1(1), 1–11 (2013)
Saal, J.E., Kirklin, S., Aykol, M., Meredig, B., Wolverton, C.: Materials design and discovery with high-throughput density functional theory: the Open Quantum Materials Database (OQMD). JOM 65(11), 1501–1509 (2013). https://doi.org/10.1007/s11837-013-0755-4
Nityananda, R., Hohenberg, P., Kohn, W.: Inhomogeneous electron gas. Resonance 22(8), 809–811 (2017). https://doi.org/10.1007/s12045-017-0529-3
Kohn, W., Sham, L.J.: Self-consistent equations including exchange and correlation effects. Phys. Rev. 140, A1133–A1138 (1965)
Nightingale, M.P., Umrigar., J.C.: Self-Consistent Equations Including Exchange and Correlation Effects. Springer (1999)
Hammond, B.L., Lester, W.A., Reynolds, P.J.: Monte Carlo Methods in Ab Initio Quantum Chemistry. World Scientific, Singapore (1994)
Car, R., Parrinello, M.: Unified approach for molecular dynamics and density-functional theory. Phys. Rev. Lett. 55, 2471–2474 (1985)
Marx, D., Hutter, J.: Ab Initio Molecular Dynamics, Basic Theory and Advanced Methods. Cambridge University Press, New York (2012)
Aarons, J., Sarwar, M., Thompsett, D., Skylaris, C.K.: Perspective: methods for large-scale density functional calculations on metallic systems. J. Chem. Phys. 145(22), 220901 (2016)
Sanchez, J.M., Ducastelle, F., Gratias, D.: Generalized cluster description of multicomponent systems. Phys. A Stat. Mech. Appl. 128, 334–350 (1984)
De Fontaine, D.: Cluster approach to order-disorder transformations in alloys. Phys. A Stat. Mech. Appl. 47, 33–176 (1994)
Levy, O., Hart, G.L.W., Curtarolo, S.: Uncovering compounds by synergy of cluster expansion and high-throughput methods. J. Am. Chem. Soc. 132(13), 4830–4833 (2010)
Alder, B.J., Wainwright, T.E.: Phase transition for a hard sphere system. J. Chem. Phys. 27(5), 1208–1209 (1957)
Rahman, A.: Correlations in the motion of atoms in liquid argon. Phys. Rev. 136(2A), A405–A411 (1964)
Ercolessi, F., Adams, J.B.: Interatomic potentials from first-principles calculations: the force-matching method. Europhys. Lett. 26(8), 583–588 (1994)
Brockherde, F., Vogt, L., Tuckerman, M.E., Burke, K., Müller, K.R.: Bypassing the Kohn-Sham equations with machine learning. Nat. Commun. 8(872), 1–10 (2017)
Wang, C., Tharval, A., Kitchin, J.R.: A density functional theory parameterised neural network model of zirconia. Mol. Simul. 44(8), 623–630 (2018)
Sinitskiy, A.V., Pande, V.S.: Deep neural network computes electron densities and energies of a large set of organic molecules faster than density functional theory (DFT). https://arxiv.org/abs/1809.02723
Custódio, C.A., Filletti, É.R., França, V.V.: Artificial neural networks for density-functional optimizations in fermionic systems. Sci. Rep. 9(1886), 1–7 (2019)
Ryczko, K., Strubbe, D., Tamblyn, I.: Deep learning and density functional theory. Phys. Rev. A 100, 022512 (2019)
Behler, J., Parrinello, M.: Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys. Rev. Lett. 98(14), 146401 (2007)
Schütt, K., et al.: SchNet: a continuous-filter convolutional neural network for modeling quantum interactions. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems 30, pp. 991–1001. Curran Associates Inc. (2017)
Smith, J.S., Isayev, O., Roitberg, A.E.: ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost. Chem. Sci. 8(4), 3192–3203 (2017)
Zhang, L., Han, J., Wang, H., Car, R., Weinan, E.: Deep potential molecular dynamics: a scalable model with the accuracy of quantum mechanics. Phys. Rev. Lett. 120(14), 143001 (2018)
Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The graph neural network model. IEEE Trans. Neural Netw. 20(1), 61–80 (2009)
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 29. Curran Associates Inc. (2016)
Xie, T., Grossman, J.C.: Crystal graph convolutional neural networks for an accurate and interpretable prediction of material properties. Phys. Rev. Lett. 120(14), 145301 (2018)
Chen, C., Ye, W., Zuo, Y., Zheng, C., Ong, S.P.: Graph networks as a universal machine learning framework for molecules and crystals. Chem. Mater. 31(9), 3564–3572 (2019)
Pasini, M.L., Eisenbach, M.: CuAu binary alloy with 32 atoms - LSMS-3 data, February 2021. https://doi.org/10.13139/OLCF/1765349
Pasini, M.L., Eisenbach, M.: FePt binary alloy with 32 atoms - LSMS-3 data, February 2021. https://doi.org/10.13139/OLCF/1762742
Murty, U.S.R., Bondy, J.A.: Graphs and subgraphs. In: Graph Theory with Applications. North-Holland
Xu, K., Hu, W., Leskovec, J., Jegelka, S.: How powerful are graph neural networks? arXiv:1810.00826 [cs, stat], February 2019
Kipf, T.N., Welling, M.: Graph attention networks. arXiv:1609.02907 [cs, stat], February 2017. arXiv: 1710.10903
Corso, G., Cavalleri, L., Beaini, D., Liò, P., Veličković., P.: Principal neighbourhood aggregation for graph nets. arXiv:2004.05718 [cs, stat], December 2020
Hamilton, W.L.: Graph representation learning. Synth. Lect. Artif. Intell. Mach. Learn. 14(3), 1–159 (2020)
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’ Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32, pp. 8024–8035. Curran Associates Inc. (2019)
Fey, M., Lenssen, J.E.: Fast graph representation learning with PyTorch geometric. In: ICLR Workshop on Representation Learning on Graphs and Manifolds (2019)
PyTorch Geometric. https://pytorch-geometric.readthedocs.io/en/latest/
Pasini, M.L., Reeve, S.T., Zhang, P., Choi, J.Y.: HydraGNN. Comput. Softw. (2021). https://doi.org/10.11578/dc.20211019.2
Liaw, R., Liang, E., Nishihara, R., Moritz, P., Gonzalez, J.E., Stoica, I.: Tune: a research platform for distributed model selection and training. arXiv preprint arXiv:1807.05118 (2018)
Ray Tune: Hyperparameter Optimization Framework. https://docs.ray.io/en/latest/tune/index.html
Eisenbach, M., Larkin, J., Lutjens, J., Rennich, S., Rogers, J.H.: GPU acceleration of the locally self-consistent multiple scattering code for first principles calculation of the ground state and statistical physics of materials. Comput. Phys. Commun. 211, 2–7 (2017)
Wang, Y., Stocks, G.M., Shelton, W.A., Nicholson, D.M.C., Szotek, Z., Temmerman, W.M.: Order-N multiple scattering approach to electronic structure calculations. Phys. Rev. Lett. 75, 2867–2870 (1995)
Yang, Y., et al.: Quantitative evaluation of an epitaxial silicon-germanium layer on silicon. Nature 542(7639), 75–79 (2017)
Eisenbach, M., Li, Y.W., Odbadrakh, O.K., Pei, Z., Stocks, G.M., Yin, J.: LSMS. https://github.com/mstsuite/lsms
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980 [cs], January 2017
OLCF Supercomputer Titan. https://www.olcf.ornl.gov/for-users/system-user-guides/titan/
OLCF Supercomputer Summit. https://www.olcf.ornl.gov/olcf-resources/compute-systems/summit/
Acknowledgements
Massimiliano Lupo Pasini thanks Dr. Vladimir Protopopescu for his valuable feedback in the preparation of this manuscript.
This work was supported in part by the Office of Science of the Department of Energy and by the Laboratory Directed Research and Development (LDRD) Program of Oak Ridge National Laboratory. This research is sponsored by the Artificial Intelligence Initiative as part of the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory, managed by UT-Battelle, LLC, for the US Department of Energy under contract DE-AC05-00OR22725. This work used resources of the Oak Ridge Leadership Computing Facility, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Lupo Pasini, M., Burc̆ul, M., Reeve, S.T., Eisenbach, M., Perotto, S. (2022). Fast and Accurate Predictions of Total Energy for Solid Solution Alloys with Graph Convolutional Neural Networks. In: Nichols, J., et al. Driving Scientific and Engineering Discoveries Through the Integration of Experiment, Big Data, and Modeling and Simulation. SMC 2021. Communications in Computer and Information Science, vol 1512. Springer, Cham. https://doi.org/10.1007/978-3-030-96498-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-96498-6_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96497-9
Online ISBN: 978-3-030-96498-6
eBook Packages: Computer ScienceComputer Science (R0)