Abstract
We briefly summarize the kernel regression approach, as used recently in materials modelling, to fitting functions, particularly potential energy surfaces, and highlight how the linear algebra framework can be used to both predict and train from linear functionals of the potential energy, such as the total energy and atomic forces. We then give a detailed account of the smooth overlap of atomic positions (SOAP) representation and kernel, showing how it arises from an abstract representation of smooth atomic densities, and how it is related to several popular density-based representations of atomic structure. We also discuss recent generalizations that allow fine control of correlations between different atomic species, prediction and fitting of tensorial properties, and also how to construct structural kernels—applicable to comparing entire molecules or periodic systems—that go beyond an additive combination of local environments. (This chapter is adapted with permission from Ceriotti et al. (Handbook of materials modeling. Springer, Cham, 2019).)
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
M. Ceriotti, M.J. Willatt, G. Csányi, Machine-learning of atomic-scale properties based on physical principles, in Handbook of Materials Modeling, ed. by W. Andreoni, S. Yip (Springer, Cham, 2019)
M.W. Finnis, Interatomic Forces in Condensed Matter (Oxford University Press, Oxford, 2004)
D.W. Brenner, Phys. Status Solidi B 217, 23 (2000)
B.J. Braams, J.M. Bowman, Int. Rev. Phys. Chem. 28(4), 577–606 (2009)
M. Rupp, A. Tkatchenko, K.R. Müller, O.A. von Lilienfeld, Phys. Rev. Lett. 108, 058301 (2012)
F. Faber, A. Lindmaa, O.A. von Lilienfeld, R. Armiento, Int. J. Quantum Chem. 115(16), 1094–1101 (2015)
L. Zhang, J. Han, H. Wang, R. Car, E. Weinan, Phys. Rev. Lett. 120(14), 143001 (2018)
C.M. Bishop, Pattern Recognition and Machine Learning (Springer, Berlin, 2016)
C.E. Rasmussen, C.K.I. Williams, Gaussian Processes for Machine Learning (MIT Press, Cambridge, 2006)
B. Schölkopf, A.J. Smola, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond (MIT Press, Cambridge, 2002)
W.J. Szlachta, A.P. Bartók, G. Csányi, Phys. Rev. B Condens. Matter 90(10), 104108 (2014). https://doi.org/10.1103/PhysRevB.90.104108
D. Dragoni, T.D. Daff, G. Csányi, N. Marzari, Phys. Rev. Mater. 2(1), 013808 (2018)
N. Bernstein, J.R. Kermode, G. Csányi, Rep. Prog. Phys. 72(2), 026501 (2009). https://doi.org/10.1088/0034-4885/72/2/026501
V.L. Deringer, G. Csányi, Phys. Rev. B 95(9), 094203 (2017). https://doi.org/10.1103/physrevb.95.094203
S. Fujikake, V.L. Deringer, T.H. Lee, M. Krynski, S.R. Elliott, G. Csányi, J. Chem. Phys. 148, 241714 (2018)
A.N. Tikhonov, A. Goncharsky, V.V. Stepanov, A.G. Yagola, Numerical Methods for the Solution of Ill-Posed Problems (Kluwer Academic, Dordrecht, 1995)
J.A. Hartigan, M.A. Wong, J. R. Stat. Soc. Ser. C Appl. Stat. 28(1), 100 (1979)
S. Prabhakaran, S. Raman, J.E. Vogt, V. Roth, Joint DAGM (German Association for Pattern Recognition) and OAGM Symposium (Springer, Berlin, 2012), pp. 458–467
E.V. Podryabinkin, A.V. Shapeev, Comput. Mater. Sci. 140, 171 (2017). https://doi.org/10.1016/j.commatsci.2017.08.031.
B. Huang, O.A. von Lilienfeld (2017). arxiv:1707.04146 . http://arxiv.org/abs/1707.04146v3
T.F. Gonzalez, Theor. Comput. Sci. 38, 293 (1985)
M. Ceriotti, G.A. Tribello, M. Parrinello, J. Chem. Theory Comput. 9, 1521 (2013)
A.A.P. Bartók, S. De, C. Poelking, N. Bernstein, J.R.J. Kermode, G. Csányi, M. Ceriotti, Sci. Adv. 3, e1701816 (2017)
S. De, A.A.P. Bartók, G. Csányi, M. Ceriotti, Phys. Chem. Chem. Phys. 18, 13754 (2016)
M.W. Mahoney, P. Drineas, Proc. Natl. Acad. Sci. USA 106, 697 (2009)
G. Imbalzano, A. Anelli, D. Giofré, S. Klees, J. Behler, M. Ceriotti, J. Chem. Phys. 148, 241730 (2018)
J.Q. Quinonero-Candela, C.E. Rasmussen, J. Mach. Learn. Res. 6, 1939–1959 (2005)
E. Snelson, Z. Ghahramani, Advances in Neural Information Processing Systems (2005)
E. Solak, C.E. Rasmussen, D.J. Leith, R. Murray-Smith, W.E. Leithead, Advances in Neural Information Processing Systems (2003)
A.P. Bartók, M.C. Payne, R. Kondor, G. Csányi, Phys. Rev. Lett. 104(13), 136403 (2010)
A.P. Bartók, M.J. Gillan, F.R. Manby, G. Csányi, Phys. Rev. B 88(5), 054104 (2013). https://doi.org/10.1103/PhysRevB.88.054104
A.P. Bartók, G. Csányi, Int. J. Quant. Chem. 116(13), 1051 (2015). https://doi.org/10.1002/qua.24927
S.T. John, G. Csányi, J. Phys. Chem. B 121(48), 10934 (2017). https://doi.org/10.1021/acs.jpcb.7b09636
V.L. Deringer, C.J. Pickard, G. Csányi, Phys. Rev. Lett. 120(15), 156001 (2018). https://doi.org/10.1103/PhysRevLett.120.156001
M.A. Caro, V.L. Deringer, J. Koskinen, T. Laurila, G. Csányi, Phys. Rev. Lett. 120(16), 166101 (2018). https://doi.org/10.1103/PhysRevLett.120.166101
P. Rowe, G. Csányi, D. Alfè, A. Michaelides, Phys. Rev. B 97(5), 054303 (2018). https://doi.org/10.1103/PhysRevB.97.054303
T.T. Nguyen, E. Szekely, G. Imbalzano, J. Behler, G. Csányi, M. Ceriotti, A.W. Götz, F. Paesani, J. Chem. Phys. 148, 241725 (2018)
S. Chmiela, A. Tkatchenko, H.E. Sauceda, I. Poltavsky, K.T. Schütt, K.R. Müller, Sci. Adv. 3(5), e1603015 (2017). https://doi.org/10.1126/sciadv.1603015
A. Glielmo, C. Zeni, A.D. Vita, Phys. Rev. B 97(18) (2018). https://doi.org/10.1103/physrevb.97.184307
C. Zeni, K. Rossi, A. Glielmo, A. Fekete, N. Gaston, F. Baletto, A. Dr Vita, J. Chem. Phys. 148(23), 234106 (2018)
M.J. Willatt, F. Musil, M. Ceriotti, J. Chem. Phys. 150, 154110 (2019)
A.P. Bartók, R. Kondor, G. Csányi, Phys. Rev. B 87, 184115 (2013)
J. Behler, M. Parrinello, Phys. Rev. Lett. 98, 146401 (2007)
S. Kajita, N. Ohba, R. Jinnouchi, R. Asahi, Sci. Rep. 7, 1 (2017)
K.T. Schütt, H. Glawe, F. Brockherde, A. Sanna, K.R. Müller, E.K.U. Gross, Phys. Rev. B 89, 205118 (2014)
W. Yang, Phys. Rev. Lett. 66, 1438 (1991)
G. Galli, M. Parrinello, Phys. Rev. Lett. 69, 3547 (1992)
S. Goedecker, Rev. Mod. Phys. 71, 1085 (1999)
E. Prodan, W. Kohn, Proc. Natl. Acad. Sci. USA 102, 11635 (2005)
H. Eshet, R.Z. Khaliullin, T.D. Kühne, J. Behler, M. Parrinello, Phys. Rev. Lett. 108, 115701 (2012)
T. Morawietz, A. Singraber, C. Dellago, J. Behler, Proc. Natl. Acad. Sci. USA 113, 8368 (2016)
B. Cheng, J. Behler, M. Ceriotti, J. Phys. Chem. Lett. 7, 2210 (2016)
J.S. Smith, O. Isayev, A.E. Roitberg, Chem. Sci. 8, 3192 (2017)
A.P. Thompson, L.P. Swiler, C.R. Trott, S.M. Foiles, G.J. Tucker, J. Comput. Phys. 285, 316 (2015)
A. Haar, Ann. Math. 34, 147 (1933)
J. Tersoff, Phys. Rev. B 39, 5566 (1989)
G.R. Medders, V. Babin, F. Paesani, J. Chem. Theory Comput. 10, 2906 (2014)
J.A. Moriarty, Phys. Rev. B 42, 1609 (1990)
R. Drautz, Phys. Rev. B 99, 014104 (2019)
F.A. Faber, L. Hutchison, B. Huang, J. Gilmer, S.S. Schoenholz, G.E. Dahl, O. Vinyals, S. Kearnes, P.F. Riley, O.A. von Lilienfeld, J. Chem. Theory Comput. 13, 5255 (2017)
M.J. Willatt, F. Musil, M. Ceriotti, Phys. Chem. Chem. Phys. 20, 29661 (2018)
B. Huang, O.A. von Lilienfeld, J. Chem. Phys. 145(16), 161102 (2016). https://doi.org/10.1063/1.4964627
F.A. Faber, A.S. Christensen, B. Huang, O.A. von Lilienfeld, J. Chem. Phys. 148, 241717 (2018)
D.A. Varshalovich, A.N. Moskalev, V.K. Khersonskii, Quantum Theory of Angular Momentum (World Scientific, Singapore, 1988)
A. Glielmo, P. Sollich, A. De Vita, Phys. Rev. B 95, 214302 (2017)
A. Grisafi, D.D.M. Wilkins, G. Csányi, M. Ceriotti, Phys. Rev. Lett. 120, 036002 (2018)
D.M. Wilkins, A. Grisafi, Y. Yang, K.U. Lao, R.A. DiStasio, M. Ceriotti, Proc. Natl. Acad. Sci. USA 116, 3401 (2019)
F.M. Paruzzo, A. Hofstetter, F. Musil, S. De, M. Ceriotti, L. Emsley, Nat. Commun. 9, 4501 (2018)
M. Cuturi, in Advances in Neural Information Processing Systems, vol. 26, ed. by C.J.C. Burges, L. Bottou, M. Welling, Z. Ghahramani, K.Q. Weinberger (Curran Associates, Inc., Red Hook, 2013), pp. 2292–2300
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Csányi, G., Willatt, M.J., Ceriotti, M. (2020). Machine-Learning of Atomic-Scale Properties Based on Physical Principles. In: Schütt, K., Chmiela, S., von Lilienfeld, O., Tkatchenko, A., Tsuda, K., Müller, KR. (eds) Machine Learning Meets Quantum Physics. Lecture Notes in Physics, vol 968. Springer, Cham. https://doi.org/10.1007/978-3-030-40245-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-40245-7_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-40244-0
Online ISBN: 978-3-030-40245-7
eBook Packages: Physics and AstronomyPhysics and Astronomy (R0)