Abstract
Machine learning (ML)-based models have greatly enhanced the traditional materials discovery and design pipeline. Specifically, in recent years, surrogate ML models for material property prediction have demonstrated success in predicting discrete scalar-valued target properties to within reasonable accuracy of their DFT-computed values. However, accurate prediction of spectral targets, such as the electron density of states (DOS), poses a much more challenging problem due to the complexity of the target, and the limited amount of available training data. In this study, we present an extension of the recently developed atomistic line graph neural network to accurately predict DOS of a large set of material unit cell structures, trained to the publicly available JARVIS-DFT dataset. Furthermore, we evaluate two methods of representation of the target quantity: a direct discretized spectrum, and a compressed low-dimensional representation obtained using an autoencoder. Through this work, we demonstrate the utility of graph-based featurization and modeling methods in the prediction of complex targets that depend on both chemistry and directional characteristics of material structures.
Similar content being viewed by others
References
J. Lee, A. Seko, K. Shitara, K. Nakayama, and I. Tanaka, Phys. Rev. B. https://doi.org/10.1103/PhysRevB.93.115104 (2016).
G. Pilania, A. Mannodi-Kanakkithodi, B.P. Uberuaga, R. Ramprasad, J.E. Gubernatis, and T. Lookman, Sci. Rep. 6, 19375. https://doi.org/10.1038/srep19375 (2016).
S. Kirklin, J.E. Saal, B. Meredig, A. Thompson, J.W. Doak, M. Aykol, S. Rühl, and C. Wolverton, npj Comput. Mater. https://doi.org/10.1038/npjcompumats.2015.10 (2015).
K. Choudhary, B. DeCost, and F. Tavazza, Phys. Rev. Mater. https://doi.org/10.1103/physrevmaterials.2.083801 (2018).
A.M. Deml, R. O’Hayre, C. Wolverton, and V. Stevanović, Phys. Rev. B. https://doi.org/10.1103/PhysRevB.93.085142 (2016).
F. Faber, A. Lindmaa, O.A. von Lilienfeld, and R. Armiento, Int. J. Quantum Chem. 115, 1094. https://doi.org/10.1002/qua.24917 (2015).
P.R. Kaundinya, K. Choudhary, and S.R. Kalidindi, Phys. Rev. Mater. 5, 063802. https://doi.org/10.1103/PhysRevMaterials.5.063802 (2021).
W. Ye, C. Chen, Z. Wang, I.H. Chu, and S.P. Ong, Nat Commun 9, 3800. https://doi.org/10.1038/s41467-018-06322-x (2018).
L. Ward, R. Liu, A. Krishna, V.I. Hegde, A. Agrawal, A. Choudhary, and C. Wolverton, Phys. Rev. B. https://doi.org/10.1103/PhysRevB.96.024104 (2017).
A.N. Filanovich and A.A. Povzner, in 2020 Ural Symposium on Biomedical Engineering, Radioelectronics and Information Technology (USBEREIT), (2020), pp. 0414–0416.
M. Rupp, A. Tkatchenko, K.R. Muller, and O.A. von Lilienfeld, Phys. Rev. Lett. 108, 058301. https://doi.org/10.1103/PhysRevLett.108.058301 (2012).
H. Huo and M. Rupp (2017).
L. Ward, B. Blaiszik, I. Foster, R.S. Assary, B. Narayanan, and L. Curtiss, MRS Commun. 9, 891. https://doi.org/10.1557/mrc.2019.107 (2019).
G. Montavon, K. Hansen, S. Fazli, M. Rupp, F. Biegler, A. Ziehe, A. Tkatchenko, A. von Lilienfeld and K.-R. Müller (2012), pp. 449–457
D.M. Wilkins, A. Grisafi, Y. Yang, K.U. Lao, R.A. DiStasio, and M. Ceriotti, Proc. Natl. Acad. Sci. 116, 3401. https://doi.org/10.1073/pnas.1816132116 (2019).
L. Zhang, M. Chen, X. Wu, H. Wang, and R. Car, Phys. Rev. B 102, 041121. https://doi.org/10.1103/PhysRevB.102.041121 (2020).
A. Grisafi, A. Fabrizio, B. Meyer, D.M. Wilkins, C. Corminboeuf, and M. Ceriotti, ACS Cent. Sci. 5, 57–64. https://doi.org/10.1021/acscentsci.8b00551 (2019).
J.M. Alred, K.V. Bets, Y. Xie, and B.I. Yakobson, Compos. Sci. Technol. 166, 3–9. https://doi.org/10.1016/j.compscitech.2018.03.035 (2018).
A. Chandrasekaran, D. Kamal, R. Batra, C. Kim, L. Chen, and R. Ramprasad, npj Comput. Mater. 5, 22. https://doi.org/10.1038/s41524-019-0162-7 (2019).
F. Brockherde, L. Vogt, L. Li, M.E. Tuckerman, K. Burke, and K.-R. Müller, Nat. Commun. 8, 872. https://doi.org/10.1038/s41467-017-00839-3 (2017).
S. Gong, T. Xie, T. Zhu, S. Wang, E.R. Fadel, Y. Li, and J.C. Grossman, Phys. Rev. B 100, 184103. https://doi.org/10.1103/PhysRevB.100.184103 (2019).
C. Ben Mahmoud, A. Anelli, G. Csányi, and M. Ceriotti, Phys. Rev. B 102, 235130. https://doi.org/10.1103/PhysRevB.102.235130 (2020).
B.C. Yeo, D. Kim, C. Kim, and S.S. Han, Sci. Rep. 9, 5879. https://doi.org/10.1038/s41598-019-42277-9 (2019).
K. Bang, B.C. Yeo, D. Kim, S.S. Han, and H.M. Lee, Sci. Rep. 11, 11604. https://doi.org/10.1038/s41598-021-91068-8 (2021).
P. Borlido, J. Schmidt, A.W. Huran, F. Tran, M.A.L. Marques, and S. Botti, npj Comput. Mater. 6, 96. https://doi.org/10.1038/s41524-020-00360-0 (2020).
J. Singh, J. Non-Cryst. Solids 299–302, 444. https://doi.org/10.1016/S0022-3093(01)00957-7 (2002).
K.F. Garrity, Phys. Rev. B 94, 045122. https://doi.org/10.1103/PhysRevB.94.045122 (2016).
G. Hamaoui, N. Horny, Z. Hua, T. Zhu, J.-F. Robillard, A. Fleming, H. Ban, and M. Chirtoc, Sci. Rep. 8, 11352. https://doi.org/10.1038/s41598-018-29505-4 (2018).
Z. Lin, L.V. Zhigilei, and V. Celli, Phys. Rev. B 77, 075133. https://doi.org/10.1103/PhysRevB.77.075133 (2008).
K.T. Schütt, H. Glawe, F. Brockherde, A. Sanna, K.R. Müller, and E.K.U. Gross, Phys. Rev. B 89, 205118. https://doi.org/10.1103/PhysRevB.89.205118 (2014).
S.R. Broderick, and K. Rajan, EPL (Europhysics Letters) 95, 57005. https://doi.org/10.1209/0295-5075/95/57005 (2011).
A.P. Bartók, R. Kondor, and G. Csányi, Phys. Rev. B 87, 184115. https://doi.org/10.1103/PhysRevB.87.184115 (2013).
A. Cecen, T. Fast, and S.R. Kalidindi, Integr. Mater. Manuf. Innov. 5, 1. https://doi.org/10.1186/s40192-015-0044-x (2016).
S. Kalidindi, Hierarchical Materials Informatics: Novel Analytics for Materials Data, (2015).
S.R. Kalidindi, ISRN Mater. Sci. 2012, 305692. https://doi.org/10.5402/2012/305692 (2012).
T. Xie, and J.C. Grossman, Phys. Rev. Lett. 120, 145301. (2018).
C.W. Park, and C. Wolverton, Phys. Rev. Mat. 4, 063801. https://doi.org/10.1103/PhysRevMaterials.4.063801 (2020).
M. Karamad, R. Magar, Y. Shi, S. Siahrostami, I.D. Gates, and A. Barati Farimani, Phys. Rev. Mater. 4, 093801. https://doi.org/10.1103/PhysRevMaterials.4.093801 (2020).
S.-Y. Louis, Y. Zhao, A. Nasiri, X. Wang, Y. Song, F. Liu, and J. Hu, Phys. Chem. Chem. Phys. 22, 18141. https://doi.org/10.1039/D0CP01474E (2020).
K. Choudhary, and B. DeCost, npj Comput. Mater. 7, 185. https://doi.org/10.1038/s41524-021-00650-1 (2021).
K. Choudhary, I. Kalish, R. Beams, and F. Tavazza, Sci. Rep. 7, 1. (2017).
K. Choudhary, and F. Tavazza, Comput. Mater. Sci. 161, 300. (2019).
K. Choudhary, Q. Zhang, A.C. Reid, S. Chowdhury, N. Van Nguyen, Z. Trautt, M.W. Newrock, F.Y. Congo, and F. Tavazza, Sci. Data 5, 180082. (2018).
K. Choudhary, K.F. Garrity, and F. Tavazza, J. Phys. Condens. Matter 32, 475501. https://doi.org/10.1088/1361-648x/aba06b (2020).
K. Choudhary, K.F. Garrity, A.C.E. Reid, B. De Cost, 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 and F. Tavazza, npj Comput. Mater. 6, 173 (2020). doi:https://doi.org/10.1038/s41524-020-00440-1
Y. Wang, H. Yao, and S. Zhao, Neurocomput 184, 232–242. https://doi.org/10.1016/j.neucom.2015.08.104 (2016).
Acknowledgements
P.R.K. and S.R.K. gratefully acknowledge support from ONR N00014-18-1-2879. The Hive cluster at Georgia Institute of Technology (supported by NSF 1828187) was used for this work. We would like to thank Brian DeCost for the helpful discussion.
Funding
The authors declare that no known competing financial interests have influenced the work reported in this paper.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare 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.
Rights and permissions
About this article
Cite this article
Kaundinya, P.R., Choudhary, K. & Kalidindi, S.R. Prediction of the Electron Density of States for Crystalline Compounds with Atomistic Line Graph Neural Networks (ALIGNN). JOM 74, 1395–1405 (2022). https://doi.org/10.1007/s11837-022-05199-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11837-022-05199-y