Precise nanofabrication represents a critical challenge to developing semiconductor quantum-dot qubits for practical quantum computation. Here, we design and train a convolutional neural network to interpret scanning electron micrographs and quantify qualitative features affecting device functionality. The high-throughput strategy is exemplified by optimizing a model lithographic process within a five-dimensional design space and by demonstrating a robust approach to address lithographic proximity effects. The results emphasize the benefits of machine learning for developing stable processes, shortening development cycles, and enforcing quality control during qubit fabrication.

1.
T. D.
Ladd
and
M. S.
Carroll
, “
Silicon qubits
,”
Encyclopedia of Modern Optics
, 2nd ed. (
Elsevier
,
2018
), Vol.
1
.
2.
M.
Veldhorst
,
J. C. C.
Hwang
,
C. H.
Yang
,
A. W.
Leenstra
,
B. D.
Ronde
,
J. P.
Dehollain
,
J. T.
Muhonen
,
F. E.
Hudson
,
K. M.
Itoh
,
A.
Morello
, and
A. S.
Dzurak
, “
An addressable quantum dot qubit with fault-tolerant control-fidelity
,”
Nat. Nanotechnol.
9
,
981
985
(
2014
).
3.
E.
Kawakami
,
P.
Scarlino
,
D. R.
Ward
,
F. R.
Braakman
,
D. E.
Savage
,
M. G.
Lagally
,
M.
Friesen
,
S. N.
Coppersmith
,
M. A.
Eriksson
, and
L. M. K.
Vandersypen
, “
Electrical control of a long-lived spin qubit in a Si/SiGe quantum dot
,”
Nat. Nanotechnol.
9
,
666
670
(
2014
).
4.
K.
Eng
,
T. D.
Ladd
,
A.
Smith
,
M. G.
Borselli
,
A. A.
Kiselev
,
B. H.
Fong
,
K. S.
Holabird
,
T. M.
Hazard
,
B.
Huang
,
P. W.
Deelman
,
I.
Milosavljevic
,
A. E.
Schmitz
,
R. S.
Ross
,
M. F.
Gyure
, and
A. T.
Hunter
, “
Isotopically enhanced triple-quantum-dot qubit
,”
Sci. Adv.
1
,
e1500214
(
2015
).
5.
R. W.
Andrews
,
C.
Jones
,
M. D.
Reed
,
A. M.
Jones
,
S. D.
Ha
,
M. P.
Jura
,
J.
Kerckhoff
,
M.
Levendorf
,
S.
Meenehan
,
S. T.
Merkel
,
A.
Smith
,
B.
Sun
,
A. J.
Weinstein
,
M. T.
Rakher
,
T. D.
Ladd
, and
M. G.
Borselli
, “
Quantifying error and leakage in an encoded Si/SiGe triple-dot qubit
,”
Nat. Nanotechnol.
14
,
747
750
(
2019
).
6.
D. M.
Zajac
,
A. J.
Sigillito
,
M.
Russ
,
F.
Borjans
,
J. M.
Taylor
,
G.
Burkard
, and
J. R.
Petta
, “
Resonantly driven CNOT gate for electron spins
,”
Science
359
,
439
442
(
2018
).
7.
T. F.
Watson
,
S. G. J.
Philips
,
E.
Kawakami
,
D. R.
Ward
,
P.
Scarlino
,
M.
Veldhorst
,
D. E.
Savage
,
M. G.
Lagally
,
M.
Friesen
,
S. N.
Coppersmith
,
M. A.
Eriksson
, and
L. M. K.
Vandersypen
, “
A programmable two-qubit quantum processor in silicon
,”
Nature
555
,
633
637
(
2018
).
8.
C.
Tahan
, “
Democratizing spin qubits
,” arXiv:2001.08251 (
2020
).
9.
S.
Sze
,
Physics of Semiconductor Devices
(
Wiley
,
1981
).
10.
The relatively large effective mass of electrons in Si (mt*=0.19me vs, e.g., m*=0.067me in GaAs) results in weaker tunneling amplitudes, requiring, in turn, closer quantum dot separations ( 150 vs 300 nm in GaAs). me is the electron rest mass in vacuum.
11.
M. D.
Reed
,
B. M.
Maune
,
R. W.
Andrews
,
M. G.
Borselli
,
K.
Eng
,
M. P.
Jura
,
A. A.
Kiselev
,
T. D.
Ladd
,
S. T.
Merkel
,
I.
Milosavljevic
,
E. J.
Pritchett
,
M. T.
Rakher
,
R. S.
Ross
,
A. E.
Schmitz
,
A.
Smith
,
J. A.
Wright
,
M. F.
Gyure
, and
A. T.
Hunter
, “
Reduced sensitivity to charge noise in semiconductor spin qubits via symmetric operation
,”
Phys. Rev. Lett.
116
,
110402
(
2016
).
12.
T.
Thorbeck
and
N. M.
Zimmerman
, “
Formation of strain-induced quantum dots in gated semiconductor nanostructures
,”
AIP Adv.
5
,
087107
(
2015
).
13.
B.
Bunday
,
E.
Solecky
,
A.
Vaid
,
A. F.
Bello
, and
X.
Dai
, “
Metrology capabilities and needs for 7 nm and 5 nm logic nodes
,”
Proc. SPIE
10145
,
101450G
(
2017
).
14.
N. G.
Orji
,
M.
Badaroglu
,
B. M.
Barnes
,
C.
Beitia
,
B. D.
Bunday
,
U.
Celano
,
R. J.
Kline
,
M.
Neisser
,
Y.
Obeng
, and
A. E.
Vladar
, “
Metrology for the next generation of semiconductor devices
,”
Nat. Electron.
1
,
532
547
(
2018
).
15.
O. D.
Patterson
,
J.
Lee
,
M. D.
Monkowski
,
D. A.
Ryan
,
S.-T.
Chen
,
S. C.
Lei
,
F.
Wang
,
C. H.
Lee
,
D.
Tomlinson
,
W.
Fang
, and
J.
Jau
, “
E-beam inspection system for comparison of wafer and design data
,”
Proc. SPIE
8324
,
83242J
(
2012
).
16.
F.
Wang
,
P.
Zhang
,
W.
Fang
,
K.
Liu
,
J.
Jau
,
L.
Wang
,
A.
Wan
,
S.
Hunsche
,
S.
Halder
, and
P.
Leray
, “
Process window and defect monitoring using high-throughput e-beam inspection guided by computational hot spot detection
,”
Proc. SPIE
9778
,
97783F
(
2016
).
17.
Y.
LeCun
,
Y.
Bengio
, and
G.
Hinton
, “
Deep learning
,”
Nature
521
,
436
444
(
2015
).
18.
A.
Oberai
and
J.-S.
Yuan
, “
Smart e-beam for defect identification and analysis in the nanoscale technology nodes: Technical perspectives
,”
Electronics
6
,
87
(
2017
).
19.
M.
Ouchi
,
M.
Ishikawa
,
S.
Shinoda
,
Y.
Toyoda
,
R.
Yumiba
,
H.
Shindo
, and
M.
Izawa
, “
A trainable die-to-database for fast e-beam inspection: Learning normal images to detect defects
,”
Proc. SPIE
11325
,
113252F
(
2020
).
20.
Y.
Ma
,
L.
Hong
,
J.
Word
,
F.
Jiang
,
V.
Liubich
,
L.
Cao
,
S.
Jayaram
,
D.
Kwak
,
Y.
Kim
,
G.
Fenger
,
A.
Raghunathan
, and
J.
Mellmann
, “
Reduction of systematic defects with machine learning from design to fab
,”
Proc. SPIE
11329
,
1132909
(
2020
).
21.
A.
Lazar
and
P. S.
Fodor
, “
Sparsity based noise removal from low dose scanning electron microscopy images
,”
Proc. SPIE
9401
,
940105
(
2015
).
22.
D. M.
Zajac
,
T. M.
Hazard
,
X.
Mi
,
K.
Wang
, and
J. R.
Petta
, “
A reconfigurable gate architecture for Si/SiGe quantum dots
,”
Appl. Phys. Lett.
106
,
223507
(
2015
).
23.
F.
Schaffler
, “
High-mobility Si and Ge structures
,”
Semicond. Sci. Technol.
12
,
1515
1549
(
1997
).
24.
J. R.
Petta
,
A. C.
Johnson
,
J. M.
Taylor
,
E. A.
Laird
,
A.
Yacoby
,
M. D.
Lukin
,
C. M.
Marcus
,
M. P.
Hanson
, and
A. C.
Gossard
, “
Coherent manipulation of coupled electron spins in semiconductor quantum dots
,”
Science
309
,
2180
2184
(
2005
).
25.
J. M.
Elzerman
,
R.
Hanson
,
L. H.
Willems van Beveren
,
B.
Witkamp
,
L. M. K.
Vandersypen
, and
L. P.
Kouwenhoven
, “
Single-shot read-out of an individual electron spin in a quantum dot
,”
Nature
430
,
431
435
(
2004
).
26.
J. Z.
Blumoff
 et al, “Quantifying high-fidelity state preparation and measurement in triple-quantum-dot qubits” (unpublished).
27.
Micrographs are collected using a Hitachi S9380 scanning electron microscope equipped with a Schottky emitter. The primary electron beam is operated at an accelerating voltage of 500 V
and a beam current of 7 pA.
28.
M.
Abadi
,
P.
Barham
,
J.
Chen
,
Z.
Chen
,
A.
Davis
,
J.
Dean
,
M.
Devin
,
S.
Ghemawat
,
G.
Irving
,
M.
Isard
,
M.
Kudlur
,
J.
Levenberg
,
R.
Monga
,
S.
Moore
,
D. G.
Murray
,
B.
Steiner
,
P.
Tucker
,
V.
Vasudevan
,
P.
Warden
,
M.
Wicke
,
Y.
Yu
, and
X.
Zhang
, “
Tensorflow: A system for large-scale machine learning
,” arXiv:1605.08695 (
2016
).
29.
A. G.
Howard
,
M.
Zhu
,
B.
Chen
,
D.
Kalenichenko
,
W.
Wang
,
T.
Weyand
,
M.
Andreetto
, and
H.
Adam
, “
Mobilenets: Efficient convolutional neural networks for mobile vision applications
,” arXiv:1704.04861 (
2017
).
30.
M.
Sandler
,
A.
Howard
,
M.
Zhu
,
A.
Zhmoginov
, and
L.-C.
Chen
, “
Mobilenetv2: Inverted residuals and linear bottlenecks
,” arXiv:1801.04381 (
2018
).
31.
S.
Ioffe
and
C.
Szegedy
, “
Batch normalization: Accelerating deep network training by reducing internal covariate shift
,” arXiv:1502.03167 (
2015
).
32.
P.
Ramachandran
,
B.
Zoph
, and
Q. V.
Le
, “
Searching for activation functions
,” arXiv:1710.05941 (
2017
).
33.
J.
Deng
,
W.
Dong
,
R.
Socher
,
L.
Li
,
K.
Li
, and
L.
Fei-Fei
, “
Imagenet: A large-scale hierarchical image database
,” in
2009 IEEE Conference on Computer Vision and Pattern Recognition
(
2009
), pp.
248
255
.
34.
M.
Lin
,
Q.
Chen
, and
S.
Yan
, “
Network in network
,” arXiv:1312.4400 (
2013
).
35.
R.
Jonker
and
A.
Volgenant
, “
A shortest augmenting path algorithm for dense and sparse linear assignment problems
,”
Computing
38
,
325
340
(
1987
).
36.
L. V. D.
Maaten
, “
Barnes-Hut-SNE
,” arXiv:1301.3342 (
2013
).
37.
G. E.
Hinton
,
N.
Srivastava
,
A.
Krizhevsky
,
I.
Sutskever
, and
R. R.
Salakhutdinov
, “
Improving neural networks by preventing co-adaptation of feature detectors
,” arXiv:1207.0580 (
2012
).
38.
N.
Srivastava
,
G.
Hinton
,
A.
Krizhevsky
,
I.
Sutskever
, and
R.
Salakhutdinov
, “
Dropout: A simple way to prevent neural networks from overfitting
,”
J. Mach. Learn. Res.
15
,
1929
1958
(
2014
).
39.
L1 regularization promotes sparse weights, offering a combination of built-in feature selection and reduced computational cost, vs L2 regularization.
40.
I.
Goodfellow
,
Y.
Bengio
, and
A.
Courville
,
Deep Learning
(
MIT Press
,
2016
).
41.
Accuracy during training is defined as the percentage of validation images for which the highest classification probabilities are assigned to the manually labeled class.
42.
W.
Henschel
,
Y. M.
Georgiev
, and
H.
Kurz
, “
Study of a high contrast process for hydrogen silsesquioxane as a negative tone electron beam resist
,”
J. Vac. Sci. Technol. B
21
,
2018
(
2003
).
43.
A. E.
Grigorescu
,
M. C. V. D.
Krogt
, and
C. W.
Hagen
, “
Sub-10-nm structures written in ultra-thin HSQ resist layers using electron-beam lithography
,”
Proc. SPIE
6519
,
65194A
(
2007
).
44.
J. K. W.
Yang
,
B.
Cord
,
H.
Duan
,
K. K.
Berggren
,
J.
Klingfus
,
S.-W.
Nam
,
K.-B.
Kim
, and
M. J.
Rooks
, “
Understanding of hydrogen silsesquioxane electron resist for sub-5-nm-half-pitch lithography
,”
J. Vac. Sci. Technol. B
27
,
2622
(
2009
).
45.
A. T. K.
G
,
S. N.
Piramanayagam
,
M.
Ranjbar
,
R.
Sbiaa
, and
T. C.
Chong
, “
Path to achieve sub-10-nm half-pitch using electron beam lithography
,”
J. Vac. Sci. Technol. B
29
,
011035
(
2011
).
46.
F. C. M. J. M.
van Delft
, “
Delay-time and aging effects on contrast and sensitivity of hydrogen silsesquioxane
,”
J. Vac. Sci. Technol. B
20
,
2932
(
2002
).
47.
N.
Clark
,
A.
Vanderslice
,
R.
Grove
, and
R. R.
Krchnavek
, “
Time-dependent exposure dose of hydrogen silsesquioxane when used as a negative electron-beam resist
,”
J. Vac. Sci. Technol. B
24
,
3073
(
2006
).
48.
Y.
Chen
,
H.
Yang
, and
Z.
Cui
, “
Effects of developing conditions on the contrast and sensitivity of hydrogen silsesquioxane
,”
Microelectron. Eng.
83
,
1119
1123
(
2006
).
49.
Dose D is sampled within wafers at a resolution of 0.1 mC/cm2. The remaining experimental variables are sampled across wafers.
50.
Curves are omitted from panels for which interactions between variables were not investigated.
51.
D. A.
Westly
,
D. M.
Tennant
,
Y.
Aida
,
H.
Ohki
, and
T.
Ohkubo
, “
Improved time dependent performance of hydrogen silsesquioxane resist using a spin on top coat
,”
J. Vac. Sci. Technol. B
29
,
06FJ02
(
2011
).
52.
H.-S.
Lee
,
J.-S.
Wi
,
S.-W.
Nam
,
H.-M.
Kim
, and
K.-B.
Kim
, “
Two-step resist-development process of hydrogen silsesquioxane for high-density electron-beam nanopatterning
,”
J. Vac. Sci. Technol. B
27
,
188
(
2009
).
53.
Z.
Yu
,
J.
Hwu
,
Y.
Liu
,
G.
Gauzner
,
K.
Lee
, and
D.
Kuo
, “
Study of spin-coated resist coverage on nanoscale topography using spectroscopic ellipsometry
,”
J. Appl. Phys.
110
,
014303
(
2011
).
54.
R.
Grove
, “
A patterning process utilizing a nanoimprint lithography for fabrication of planar perpendicular patterned magnetic media
,” Ph.D. thesis (
Rowan University
,
2005
).
55.
M. J.
Loboda
and
G. A.
Toskey
, “
Understanding hydrogen silsesquioxane-based dielectric film processing
,”
Solid State Technol.
41
,
99
103
(
1998
).
56.
D. L.
Olynick
,
J. A.
Liddle
,
A. V.
Tivanski
,
M. K.
Gilles
,
T.
Tyliszczak
,
F.
Salmassi
,
K.
Liang
, and
S. R.
Leone
, “
Scanning x-ray microscopy investigations into the electron-beam exposure mechanism of hydrogen silsesquioxane resists
,”
J. Vac. Sci. Technol. B
24
,
3048
(
2006
).
57.
V. A.
Sidorkin
,
P. F. A.
Alkemade
,
H. W. M.
Salemink
,
R.
Schmits
, and
E. V. D.
Drift
, “
Method for improving the aspect ratio of ultrahigh-resolution structures in negative electron-beam resist
,”
J. Vac. Sci. Technol. B
27
,
2503
(
2009
).
58.
D. L.
Olynick
,
B.
Cord
,
A.
Schipotinin
,
D. F.
Ogletree
, and
P. J.
Schuck
, “
Electron-beam exposure mechanisms in hydrogen silsesquioxane investigated by vibrational spectroscopy and in situ electron-beam-induced desorption
,”
J. Vac. Sci. Technol. B
28
,
581
587
(
2010
).
59.
Y. K.
Siew
,
G.
Sarkar
,
X.
Hu
,
J.
Hui
,
A.
See
, and
C. T.
Chua
, “
Thermal curing of hydrogen silsesquioxane
,”
J. Electrochem. Soc.
147
,
335
(
2000
).
60.
Y.
Zeng
,
S. W.
Russell
,
A. J.
McKerrow
,
L.
Chen
, and
T. L.
Alford
, “
Effectiveness of Ti, TiN, Ta, TaN, and W2N as barriers for the integration of low-k dielectric hydrogen silsesquioxane
,”
J. Vac. Sci. Technol. B
18
,
221
(
2000
).
61.
T. H. P.
Chang
, “
Proximity effect in electron–beam lithography
,”
J. Vac. Sci. Technol.
12
,
1271
1275
(
1975
).
62.
F.
Murai
, “
Fast proximity effect correction method using a pattern area density map
,”
J. Vac. Sci. Technol. B
10
,
3072
(
1992
).
63.
G. G.
Lopez
,
G. d
Villafranca
,
M.
Azadi
,
M. G.
Metzler
,
K.
Lister
,
M.
Labella
,
C.
Eichfeld
,
N.
Belic
, and
U.
Hofmann
, “
On the trends and application of pattern density dependent isofocal dose of positive resists for 100 keV electron beam lithography
,”
J. Vac. Sci. Technol. B
36
,
06JA05
(
2018
).
64.
Pattern densities in the lead section of our devices spans 19%–55% as a result of the leads being spaced at a pitch of ∼70 nm and having widths which vary between ∼10 and 40 nm.
65.
J. R.
Bickford
,
G.
Lopez
,
N.
Belic
, and
U.
Hofmann
, “
Hydrogen silsesquioxane on SOI proximity and microloading effects correction from a single 1D characterization sample
,”
J. Vac. Sci. Technol. B
32
,
06F511
(
2014
).
66.
GenISys
,
Tracer
(
GenISys
,
2020
).
67.
ZEP is a common positive-tone electron-beam lithography resist based on methyl styrene and chloromethyl acrylate copolymer.
68.
D.
Brown
, “Dose determination using ZEP520A resist as a model” (unpublished).

Supplementary Material

You do not currently have access to this content.