We have reanalyzed the rich plethora of ground state configurations of the asymmetric Wigner bilayer system that we had recently published in a related diagram of states [Antlanger et al., Phys. Rev. Lett. 117, 118002 (2016)], comprising roughly 60 000 state points in the phase space spanned by the distance between the plates and the charge asymmetry parameter of the system. In contrast to this preceding contribution where the classification of the emerging structures was carried out “by hand,” we have used for the present contribution machine learning concepts, notably based on a principal component analysis and a k-means clustering approach: using a 30-dimensional feature vector for each emerging structure (containing relevant information, such as the composition of the configuration as well as the most relevant order parameters), we were able to reanalyze these ground state configurations in a considerably more systematic and comprehensive manner than we could possibly do in the previously published classification scheme. Indeed, we were now able to identify new structures in previously unclassified regions of the parameter space and could considerably refine the previous classification scheme, thereby identifying a rich wealth of new emerging ground state configurations. Thorough consistency checks confirm the validity of the newly defined diagram of states.

1.
P.
Mehta
,
M.
Bukov
,
C.-H.
Wang
,
A. G. R.
Day
,
C.
Richardson
,
C. K.
Fisher
, and
D. J.
Schwab
,
Phys. Rep.
810
,
1
(
2019
).
2.
O.
Maimon
and
L.
Rokach
,
Data Mining and Knowledge Discovery Handbook
(
Springer
,
2010
).
3.
T.
Hastie
,
R.
Tibshirani
, and
J.
Friedman
,
The Elements of Statistical Learning
,
Springer Series in Statistics
(
Springer
,
New York
,
2001
).
4.
G.
James
,
D.
Witten
,
T.
Hastie
, and
R.
Tibshirani
,
An Introduction to Statistical Learning
(
Springer
,
New York
,
2013
).
5.
M.
Ceriotti
,
J. Chem. Phys.
150
,
150901
(
2019
).
6.
P.
Geiger
and
C.
Dellago
,
J. Chem. Phys.
139
,
164105
(
2013
).
7.
R.
van Damme
,
G. M.
Coli
,
R.
van Roij
, and
M.
Dijkstra
,
ACS Nano
14
,
15144
(
2020
).
8.
S.
Becker
,
E.
Devijver
,
R.
Molinier
, and
N.
Jakse
,
Phys. Rev. E
105
,
045304
(
2022
).
9.
S.
Becker
,
E.
Devijver
,
R.
Molinier
, and
N.
Jakse
,
Sci. Rep.
12
,
3195
(
2022
).
10.
M.
Antlanger
,
M.
Mazars
,
L.
Šamaj
,
G.
Kahl
, and
E.
Trizac
,
Mol. Phys.
112
,
1336
(
2014
).
11.
M.
Antlanger
, “
Ordered equilibrium structures in systems with long-range interactions
,” Ph.D. thesis,
TU Wien
,
2015
.
12.
M.
Antlanger
,
G.
Kahl
,
M.
Mazars
,
L.
Šamaj
, and
E.
Trizac
,
Phys. Rev. Lett.
117
,
118002
(
2016
).
13.
M.
Antlanger
,
G.
Kahl
,
M.
Mazars
,
L.
Šamaj
, and
E.
Trizac
,
J. Chem. Phys.
149
,
244904
(
2018
).
14.
D.
Gottwald
,
G.
Kahl
, and
C. N.
Likos
,
J. Chem. Phys.
122
,
204503
(
2005
).
15.
J.
Fornleitner
,
F.
Lo Verso
,
G.
Kahl
, and
C. N.
Likos
,
Soft Matter
4
,
480
(
2008
).
16.
G. J.
Pauschenwein
and
G.
Kahl
,
Soft Matter
4
,
1396
(
2008
).
17.
G. J.
Pauschenwein
and
G.
Kahl
,
J. Chem. Phys.
129
,
174107
(
2008
).
18.
G.
Doppelbauer
,
E.
Bianchi
, and
G.
Kahl
,
J. Phys.: Condens. Matter
22
,
104105
(
2010
).
19.
P. J.
Steinhardt
,
D. R.
Nelson
, and
M.
Ronchetti
,
Phys. Rev. B
28
,
784
(
1983
).
20.
W.
Lechner
and
C.
Dellago
,
J. Chem. Phys.
129
,
114707
(
2008
).
21.

We refer to Ref. 1 to a review on various machine learning tools applied to physical systems.

22.

At this point, it should be mentioned that other related techniques are also available, which may even directly operate on the structural data (i.e., on a data set of coordinates of the particles)—see, for instance, Refs. 64 and 65.

23.

See Ref. 2 for an in-depth discussion on different, problem specific similarity measures in data science problems. Methods from unsupervised machine learning1 can be used to analyze a data set of feature vectors (or of order parameters in our case) for certain similarity measures in the features that may permit us to algorithmically organize the elements of the data set into an initially unknown set of categories.2 

24.
K.
Pearson
,
London, Edinburgh Dublin Philos. Mag. J. Sci.
2
,
559
(
1901
).
25.
I.
Jolliffe
,
Principal Component Analysis
(
Springer
,
New York
,
2002
).
26.
H.
Steinhaus
,
B. Acad. Pol. Sci.
IV
,
801
(
1956
).
27.
E.
Forgy
,
Biometrics
21
,
768
(
1965
).
28.
J.
MacQueen
, in
Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Statistics
(
University of California Press
,
1967
), pp.
281
297
.
29.
S.
Lloyd
,
IEEE Trans. Inf. Theory
28
,
129
(
1982
).
30.
P. Z.
Moghadam
,
S. M.
Rogge
,
A.
Li
,
C.-M.
Chow
,
J.
Wieme
,
N.
Moharrami
,
M.
Aragones-Anglada
,
G.
Conduit
,
D. A.
Gomez-Gualdron
,
V.
Van Speybroeck
, and
D.
Fairen-Jimenez
,
Matter
1
,
219
(
2019
).
31.
E.
Boattini
,
M.
Dijkstra
, and
L.
Filion
,
J. Chem. Phys.
151
,
154901
(
2019
).
32.

Depending on the particularly applied clustering algorithm the number of clusters may be a preset parameter to the algorithm or may even be identified by the algorithm during execution.

33.
M. A.
Kramer
,
AIChE J.
37
,
233
(
1991
).
34.
M. A.
Kramer
,
Comput. Chem. Eng.
16
,
313
(
1992
).
35.
L.
Šamaj
and
E.
Trizac
,
Phys. Rev. B
85
,
205131
(
2012
).
36.
L.
Šamaj
and
E.
Trizac
,
Europhys. Lett.
98
,
36004
(
2012
).
37.
S.
Earnshaw
,
Trans. Cambridge Philos. Soc.
7
,
97
(
1842
).
38.
39.
P. P.
Ewald
,
Ann. Phys.
369
,
253
(
1921
).
40.
B.
Hartl
, “
Confinement-driven self-assembly of charged particles
,” Ph.D. thesis,
TU Wien
,
2020
.
41.

The total number of possible compositions at each value of η is Ntot=1+12n=2N(nnmod2) given that 0<N2N12 for N1 > 1, and only counting the monolayer structure with N2 = 0 and N1 = 1 once. For N = 40, we thus have Ntot = 401.

42.
G.
Lejeune Dirichlet
,
J. Reine Angew. Math.
40
,
209
(
1850
).
43.
G.
Voronoi
,
J. Reine Angew. Math.
133
,
97
(
1908
).
44.
P.
Virtanen
,
R.
Gommers
,
T. E.
Oliphant
,
M.
Haberland
,
T.
Reddy
,
D.
Cournapeau
,
E.
Burovski
,
P.
Peterson
,
W.
Weckesser
,
J.
Bright
,
S. J.
van der Walt
,
M.
Brett
,
J.
Wilson
,
K.
Jarrod Millman
,
N.
Mayorov
,
A. R. J.
Nelson
,
E.
Jones
,
R.
Kern
,
E.
Larson
,
C.
Carey
,
İ.
Polat
,
Y.
Feng
,
E. W.
Moore
,
J.
Vand erPlas
,
D.
Laxalde
,
J.
Perktold
,
R.
Cimrman
,
I.
Henriksen
,
E. A.
Quintero
,
C. R.
Harris
,
A. M.
Archibald
,
A. H.
Ribeiro
,
F.
Pedregosa
,
P.
van Mulbregt
, and
SciPy 1. 0 Contributors
,
Nature Meth.
17
,
261
272
(
2020
).
45.
W.
Mickel
,
S.
Kapfer
,
G.
Schröder-Turk
, and
K.
Mecke
,
J. Chem. Phys.
138
,
044501
(
2013
).
46.

For a discussion about alternative dimensional reduction and clustering tools and a justification for opting for PCA and k-means clustering in this manuscript, we refer to the supplementary material, Sec. III.

47.
J.
Shlens
, arXiv:1404.1100 (
2014
).
48.

The “elbow” in a linear scree plot,66 such as shown in the main panel of Fig. 3, is defined as the point where the contribution of the significant eigenvalues (here realized via the PEVs) seems to level off.4 Notably, this is a subjective measure as multiple elbows can occur in a scree plot. In this contribution, we opted for the second elbow (i.e., for i-values larger than i = 9) in Fig. 3—as opposed to the first elbow (at i = 4)—in an effort to include more information and to be on the safe side in our further analysis (cf., the supplementary material, Figs. 7 and 8, for the significance of PCi>4 in the state diagram of the asymmetric Wigner bilayer system).

49.

It should be noted that we do not claim that the first three PCs are sufficient to fully describe the structural diversity of the asymmetric Wigner bilayer system. We have decided to use PC1 through PC3 in Fig. 5 simply for illustrative purposes in an effort to motivate the need for a more refined investigation of the diagram of states. Using other permutations of PC1 through PC9 will lead to similar plots that differ, however, in significant details, which, in turn, allows for a more systematic classification of structural phases in the system.

50.
L. V. D.
Maaten
and
G.
Hinton
,
J. Mach. Learn. Res
9
,
2579
(
2008
).
51.
M.
Ester
,
H.-P.
Kriegel
,
J.
Sander
, and
X.
Xu
, in
Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, KDD’96
(
AAAI Press
,
1996
), pp.
226
231
.
52.
P.
Stampfli
,
Helv. Phys. Acta
59
,
1260
(
1986
).
53.
M.
Oxborrow
and
C. L.
Henley
,
Phys. Rev. B
48
,
6966
(
1993
).
54.
B.
Grünbaum
and
G. C.
Shephard
,
Tilings and Patterns
(
Courier Dover Publications
,
1987
).
55.
T.
Janssen
,
G.
Chapuis
, and
M.
de Boissieu
,
Aperiodic Crystals–From Modulated Phases to Quasicrystals
(
Oxford University Press
,
Oxford
,
2007
).
56.

Nowadays, it is easily possible to train a neural network in a supervised way with the objective of performing classification tasks.1 For our purposes, such a task would be to classify structural data into a number of K different categories (identified, for instance, by unsupervised clustering), which would allow us to directly classify a structure from its geometric, structural data, e.g., via coordinates and lattice vectors.67 The output of the classifier would then be the probability of a structure falling into any of the K clusters or families (when using “softmax” activation in the output layer of the neural network and “categorical cross-entropy loss” during training1), which may give additional insight when comparing competing structures.

57.

We report at this occasion that for all K-values both k- and k-means clustering results nicely correlate when evaluating the adjusted mutual information scores between the k- and k-means clustering, i.e., IK(ki,kj*) as defined in the  Appendix E; for more details and graphical representations, we refer to Ref. 40.

58.

Although most of the suggested ground state candidates identified by the evolutionary algorithm in Refs. 11–13 are very likely to represent the true ground state configurations of the asymmetric Wigner bilayer system at a given state point, there is no rigorous proof that they are, indeed, the ground states. Thus, whenever we use the term “ground state solutions,” we refer to “ground state candidate solutions” of the asymmetric Wigner bilayer system.

59.

Also, for the k-means clustering, we rely on the set of analytically labeled data, w(sym), of the entire data set, X(asym), which correspond to the ground state solutions of the symmetric case, A = 1, in the evaluation of S(ki*,kj*|w(sym)), given by Eq. (D1): we, respectively, compare in S(ki*,kj*|w(sym)) the labels w(sym) with ki(sym) and kj(sym), i.e., the fraction of the samples ki* and kj*, which, respectively, corresponds to the known ground state structures of the symmetric Wigner bilayer system.

60.
N. X.
Vinh
,
J.
Epps
, and
J.
Bailey
,
J. Mach. Learn. Res.
11
,
2837
(
2010
).
61.
F.
Pedregosa
,
G.
Varoquaux
,
A.
Gramfort
,
V.
Michel
,
B.
Thirion
,
O.
Grisel
,
M.
Blondel
,
P.
Prettenhofer
,
R.
Weiss
,
V.
Dubourg
,
J.
Vanderplas
,
A.
Passos
,
D.
Cournapeau
,
M.
Brucher
,
M.
Perrot
, and
E.
Duchesnay
,
J. Mach. Learn. Res.
12
,
2825
(
2011
).
62.
N. X.
Vinh
,
J.
Epps
, and
J.
Bailey
, in
Proceedings of the 26th Annual International Conference on Machine Learning, ICML’09
(
Association for Computing Machinery
,
2009
), pp.
1073
1080
.
63.
W. M.
Rand
,
J. Am. Stat. Assoc.
66
,
846
(
1971
).
64.
R. B.
Jadrich
,
B. A.
Lindquist
, and
T. M.
Truskett
,
J. Chem. Phys.
149
,
194109
(
2018
).
65.
R. B.
Jadrich
,
B. A.
Lindquist
,
W. D.
Piñeros
,
D.
Banerjee
, and
T. M.
Truskett
,
J. Chem. Phys.
149
,
194110
(
2018
).
66.
R. B.
Cattell
,
Multivar. Behav. Res.
1
,
245
(
1966
).
67.
N.
Guttenberg
,
N.
Virgo
,
O.
Witkowski
,
H.
Aoki
, and
R.
Kanai
, “
Permutation-equivalent neural networks applied to dynamics prediction
,” arXiv:1612.04530 [cs.CV] (
2016
).

Supplementary Material

You do not currently have access to this content.