Abstract
We briefly summarize the kernel regression approach, as used recently in materials modeling, 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 position (SOAP) descriptor and kernel, showing how it arises from an abstract representation of smooth atomic densities and how it is related to several popular density-based descriptors 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 is a preview of subscription content, log in via an institution to check access.
References
Bartók AP, Csányi G (2015) Int J Quant Chem 116:1051
Bartók AP, Payne MC, Kondor R, Csányi G (2010) Phys Rev Lett 104:136403
Bartók AP, Gillan MJ, Manby FR, Csányi G (2013a) Phys Rev B 88:054104
Bartók AP, Kondor R, Csányi G (2013b) Phys Rev B 87:184115
Bartók AP, De S, Poelking C, Bernstein N, Kermode JR, Csányi G, Ceriotti M (2017a) Sci Adv 3:e1701816
Behler J, Parrinello M (2007) Phys Rev Lett 98:146401
Bernstein N, Kermode JR, Csányi G (2009) Rep Prog Phys 72:026501
Bishop CM (2016) Pattern recognition and machine learning. Springer, New York
Braams BJ, Bowman JM (2009) Int Rev Phys Chem 28:577–606
Brenner DW (2000) Phys Status Solidi B 217:23
Caro MA, Deringer VL, Koskinen J, Laurila T, Csányi G (2018) Phys Rev Lett 120:166101
Ceriotti M, Tribello GA, Parrinello M (2013) J Chem Theory Comput 9:1521
Cheng B, Behler J, Ceriotti M (2016) J Phys Chem Lett 7:2210
Chmiela S, Tkatchenko A, Sauceda HE, Poltavsky I, Schütt KT, Müller K-R (2017) Sci Adv 3:e1603015
Cuturi M (2013) In: Burges CJC, Bottou L, Welling M, Ghahramani Z, Weinberger KQ (eds) Advances in neural information processing systems 26. Curran Associates, Inc., pp 2292–2300
De S, Bartók AP, Csányi G, Ceriotti M (2016) Phys Chem Chem Phys 18:13754
Deringer VL, Csányi G (2017) Phys Rev B 95:094203
Deringer VL, Pickard CJ, Csányi G (2018) Phys Rev Lett 120:156001
Dragoni D, Daff TD, Csányi G, Marzari N (2018) Phys Rev Mater 2:013808
Eshet H, Khaliullin RZ, Kühne TD, Behler J, Parrinello M (2012) Phys Rev Lett 108:115701
Faber F, Lindmaa A, von Lilienfeld OA, Armiento R (2015) Int J Quant Chem 115:1094–1101
Faber FA, Hutchison L, Huang B, Gilmer J, Schoenholz SS, Dahl GE, Vinyals O, Kearnes S, Riley PF, von Lilienfeld OA (2017) J Chem Theory Comput. https://doi.org/10.1021/acs.jctc.7b00577
Finnis MW (2004) Interatomic forces in condensed matter. Oxford University Press, Oxford
Fujikake S, Deringer VL, Lee TH, Krynski M, Elliott SR, Csányi G (2018) J Chem Phys 148:241714
Galli G, Parrinello M (1992) Phys Rev Lett 69:3547
Glielmo A, Sollich P, De Vita A (2017) Phys Rev B 95:214302
Glielmo A, Zeni C, Vita AD (2018) Phys Rev B 97. https://doi.org/10.1103/physrevb.97.184307
Goedecker S (1999) Rev Mod Phys 71:1085
Gonzalez TF (1985) Theor Comput Sci 38:293
Grisafi A, Wilkins DM, Csányi G, Ceriotti M (2018) Phys Rev Lett 120:036002
Haar A (1933) Ann Math 34:147
Hartigan JA, Wong MA (1979) J R Stat Soc Ser C (Appl Stat) 28:100
Imbalzano G, Anelli A, Giofré D, Klees S, Behler J, Ceriotti M (2018) J Chem Phys 148:241730
John ST, Csányi G (2017) J Phys Chem B 121:10934
Kajita S, Ohba N, Jinnouchi R, Asahi R (2017) Sci Rep 7:1
Kazhdan M, Funkhouser T, Rusinkiewicz S (2003) In: Proceedings of the 2003 Eurographics/ACM SIGGRAPH symposium on geometry processing, SGP’03. Eurographics Association, pp 156–164
Mahoney MW, Drineas P (2009) Proc Natl Acad Sci USA 106:697
Morawietz T, Singraber A, Dellago C, Behler J (2016) Proc Natl Acad Sci USA 113:8368
Nguyen TT, Szekely E, Imbalzano G, Behler J, Csányi G, Ceriotti M, Götz AW, Paesani F (2018) J Chem Phys 148:241725
Prabhakaran S, Raman S, Vogt JE, Roth V (2012) In: Joint DAGM (German Association for pattern recognition) and OAGM symposium. Springer, pp 458–467
Prodan E, Kohn W (2005) Proc Natl Acad Sci USA 102:11635
Quinonero-Candela JQ, Rasmussen CE (2005) J Mach Learn Res 6:19391959
Rasmussen CE, Williams CKI (2006) Gaussian processes for machine learning. MIT Press, Cambridge
Rupp M, Tkatchenko A, Müller K-R, von Lilienfeld OA (2012) Phys Rev Lett 108:058301
Rowe P, Csányi G, Alfè D, Michaelides A (2018) Phys Rev B 97:054303
Schölkopf B, Smola AJ (2002) Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT Press, Cambridge
Schütt KT, Glawe H, Brockherde F, Sanna A, Müller KR, Gross EKU (2014) Phys Rev B 89:205118
Smith JS, Isayev O, Roitberg AE (2017) Chem Sci 8:3192
Snelson E, Ghahramani Z (2005) Advances in neural information processing systems
Solak E, Rasmussen CE, Leith DJ, Murray-Smith R, Leithead WE (2003) Advances in neural information processing systems
Szlachta WJ, Bartók AP, Csányi G (2014) Phys Rev B Condens Matter 90:104108
Thompson AP, Swiler LP, Trott CR, Foiles SM, Tucker GJ (2015) J Comput Phys 285:316
Tikhonov AN, Goncharsky A, Stepanov VV, Yagola AG (1995) Numerical methods for the solution of ill-posed problems. Kluwer Academic, Dordrecht
Varshalovich DA, Moskalev AN, Khersonskii VK (1988) Quantum theory of angular momentum. World Scientific, Singapore
Yang W (1991) Phys Rev Lett 66:1438
Zhang L, Han J, Wang H, Car R, Weinan E (2018) Phys Rev Lett 120:143001
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Section Editor information
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this entry
Cite this entry
Ceriotti, M., Willatt, M.J., Csányi, G. (2018). Machine Learning of Atomic-Scale Properties Based on Physical Principles. In: Andreoni, W., Yip, S. (eds) Handbook of Materials Modeling . Springer, Cham. https://doi.org/10.1007/978-3-319-42913-7_68-1
Download citation
DOI: https://doi.org/10.1007/978-3-319-42913-7_68-1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-42913-7
Online ISBN: 978-3-319-42913-7
eBook Packages: Springer Reference Physics and AstronomyReference Module Physical and Materials ScienceReference Module Chemistry, Materials and Physics