Machine learning optimization of Surface-Normal optical modulators for SWIR Time-of-Flight 3-D camera

Simone Bianconi; Skyler Wheaton; Min Su Park; Iman Hassani Nia; Hooman Mohseni

doi:10.1109/JSTQE.2018.2854566

Machine learning optimization of Surface-Normal optical modulators for SWIR Time-of-Flight 3-D camera

Simone Bianconi, Skyler Wheaton, Min Su Park, Iman Hassani Nia, Hooman Mohseni^*

^*Corresponding author for this work

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Surface-normal optical modulators based on multiple quantum wells are attractive for an increasing number of applications, including photonic links such as on-chip optical interconnects. The design of such structures however is still based on intuition and experience rather than on a quantitative assessment of the device and system performance, due to the extreme complexity of the device behavior and the large number of design parameters involved. We developed a method for the systematic optimization of the modulator design, using a combination of analytical modeling and supervised machine learning. The global optimization is driven by an evolutionary algorithm, and the robustness of the final results is evaluated using variance-based sensitivity analysis. The optimization algorithm was tested on the case of time-of-flight three-dimensional camera (ranging) application, yielding two novel optimized designs which allow for a considerable improvement of the depth resolution of the system. Finally, we propose a figure of merit for comparing the modulation efficiency of surface-normal modulators.

Original language	English (US)
Article number	8201108
Journal	IEEE Journal of Selected Topics in Quantum Electronics
Volume	24
Issue number	6
DOIs	https://doi.org/10.1109/JSTQE.2018.2854566
State	Published - Nov 1 2018

Funding

Manuscript received February 8, 2018; revised June 5, 2018; accepted July 4, 2018. Date of publication July 13, 2018; date of current version July 19, 2018. This work was supported in part by Army Research Office Award #W911NF-16-1-0458 and #W911NF-11-1-0390, and in part by a W. M. Keck Foundation Science and Engineering Grant. (Corresponding author: Hooman Mohseni.) The authors are with the Department of Electrical Engineering and Computer Science, Northwestern University, Evanston, IL 60208 USA (e-mail:, [email protected]; [email protected]. edu; [email protected]; [email protected]; [email protected]). The authors acknowledge the computational resources and staff contributions provided by the Quest high performance computing facility at Northwestern University, which is jointly supported by the Office of the Provost, the Office for Research, and Northwestern University Information Technology.

Keywords

3D imaging
Electrooptic modulation
Infrared imaging
integrated optoelectronics
quantum well devices

ASJC Scopus subject areas

Atomic and Molecular Physics, and Optics
Electrical and Electronic Engineering

Access to Document

10.1109/JSTQE.2018.2854566

Cite this

@article{02d5431bf5234d318fb098c775cd920d,

title = "Machine learning optimization of Surface-Normal optical modulators for SWIR Time-of-Flight 3-D camera",

abstract = "Surface-normal optical modulators based on multiple quantum wells are attractive for an increasing number of applications, including photonic links such as on-chip optical interconnects. The design of such structures however is still based on intuition and experience rather than on a quantitative assessment of the device and system performance, due to the extreme complexity of the device behavior and the large number of design parameters involved. We developed a method for the systematic optimization of the modulator design, using a combination of analytical modeling and supervised machine learning. The global optimization is driven by an evolutionary algorithm, and the robustness of the final results is evaluated using variance-based sensitivity analysis. The optimization algorithm was tested on the case of time-of-flight three-dimensional camera (ranging) application, yielding two novel optimized designs which allow for a considerable improvement of the depth resolution of the system. Finally, we propose a figure of merit for comparing the modulation efficiency of surface-normal modulators.",

keywords = "3D imaging, Electrooptic modulation, Infrared imaging, integrated optoelectronics, quantum well devices",

author = "Simone Bianconi and Skyler Wheaton and Park, {Min Su} and {Hassani Nia}, Iman and Hooman Mohseni",

note = "Publisher Copyright: {\textcopyright} 1995-2012 IEEE.",

year = "2018",

month = nov,

day = "1",

doi = "10.1109/JSTQE.2018.2854566",

language = "English (US)",

volume = "24",

journal = "IEEE Journal of Selected Topics in Quantum Electronics",

issn = "0792-1233",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "6",

}

TY - JOUR

T1 - Machine learning optimization of Surface-Normal optical modulators for SWIR Time-of-Flight 3-D camera

AU - Bianconi, Simone

AU - Wheaton, Skyler

AU - Park, Min Su

AU - Hassani Nia, Iman

AU - Mohseni, Hooman

PY - 2018/11/1

Y1 - 2018/11/1

N2 - Surface-normal optical modulators based on multiple quantum wells are attractive for an increasing number of applications, including photonic links such as on-chip optical interconnects. The design of such structures however is still based on intuition and experience rather than on a quantitative assessment of the device and system performance, due to the extreme complexity of the device behavior and the large number of design parameters involved. We developed a method for the systematic optimization of the modulator design, using a combination of analytical modeling and supervised machine learning. The global optimization is driven by an evolutionary algorithm, and the robustness of the final results is evaluated using variance-based sensitivity analysis. The optimization algorithm was tested on the case of time-of-flight three-dimensional camera (ranging) application, yielding two novel optimized designs which allow for a considerable improvement of the depth resolution of the system. Finally, we propose a figure of merit for comparing the modulation efficiency of surface-normal modulators.

AB - Surface-normal optical modulators based on multiple quantum wells are attractive for an increasing number of applications, including photonic links such as on-chip optical interconnects. The design of such structures however is still based on intuition and experience rather than on a quantitative assessment of the device and system performance, due to the extreme complexity of the device behavior and the large number of design parameters involved. We developed a method for the systematic optimization of the modulator design, using a combination of analytical modeling and supervised machine learning. The global optimization is driven by an evolutionary algorithm, and the robustness of the final results is evaluated using variance-based sensitivity analysis. The optimization algorithm was tested on the case of time-of-flight three-dimensional camera (ranging) application, yielding two novel optimized designs which allow for a considerable improvement of the depth resolution of the system. Finally, we propose a figure of merit for comparing the modulation efficiency of surface-normal modulators.

KW - 3D imaging

KW - Electrooptic modulation

KW - Infrared imaging

KW - integrated optoelectronics

KW - quantum well devices

UR - http://www.scopus.com/inward/record.url?scp=85049926608&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049926608&partnerID=8YFLogxK

U2 - 10.1109/JSTQE.2018.2854566

DO - 10.1109/JSTQE.2018.2854566

M3 - Article

AN - SCOPUS:85049926608

SN - 0792-1233

VL - 24

JO - IEEE Journal of Selected Topics in Quantum Electronics

JF - IEEE Journal of Selected Topics in Quantum Electronics

IS - 6

M1 - 8201108

ER -

Machine learning optimization of Surface-Normal optical modulators for SWIR Time-of-Flight 3-D camera

Abstract

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this