Referenceless Characterisation of Complex Media Using Physics-Informed Neural Networks

Suraj Goel; Claudio Conti; Saroch Leedumrongwatthanakun; Mehul Malik

doi:10.1364/FIO.2023.JM4A.43

Referenceless Characterisation of Complex Media Using Physics-Informed Neural Networks

Suraj Goel^*
, Claudio Conti
, Saroch Leedumrongwatthanakun
, Mehul Malik

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

We accurately characterize the transmission matrices of complex scattering media using a physics-informed, multi-plane neural network (MPNN) without a known reference field. Our method is extremely noise-robust and can characterize a cascade of transmission matrices.

Original language	English
Title of host publication	Frontiers in Optics 2023
Publisher	Optica Publishing Group
ISBN (Print)	9781957171296
DOIs	https://doi.org/10.1364/FIO.2023.JM4A.43
Publication status	Published - 2023
Event	Frontiers in Optics + Laser Science 2023 - Tacoma, United States Duration: 9 Oct 2023 → 12 Oct 2023

Conference

Conference	Frontiers in Optics + Laser Science 2023
Country/Territory	United States
City	Tacoma
Period	9/10/23 → 12/10/23

ASJC Scopus subject areas

Nuclear Energy and Engineering
Electronic, Optical and Magnetic Materials
Nuclear and High Energy Physics
Atomic and Molecular Physics, and Optics

Access to Document

10.1364/FIO.2023.JM4A.43

Cite this

@inproceedings{9e6d50d10d444837a051a77a195c79e1,

title = "Referenceless Characterisation of Complex Media Using Physics-Informed Neural Networks",

abstract = "We accurately characterize the transmission matrices of complex scattering media using a physics-informed, multi-plane neural network (MPNN) without a known reference field. Our method is extremely noise-robust and can characterize a cascade of transmission matrices.",

author = "Suraj Goel and Claudio Conti and Saroch Leedumrongwatthanakun and Mehul Malik",

note = "Publisher Copyright: {\textcopyright} Optica Publishing Group 2023, {\textcopyright} 2023 The Author(s); Frontiers in Optics + Laser Science 2023 ; Conference date: 09-10-2023 Through 12-10-2023",

year = "2023",

doi = "10.1364/FIO.2023.JM4A.43",

language = "English",

isbn = "9781957171296",

booktitle = "Frontiers in Optics 2023",

publisher = "Optica Publishing Group",

address = "United States",

}

TY - GEN

T1 - Referenceless Characterisation of Complex Media Using Physics-Informed Neural Networks

AU - Goel, Suraj

AU - Conti, Claudio

AU - Leedumrongwatthanakun, Saroch

AU - Malik, Mehul

PY - 2023

Y1 - 2023

N2 - We accurately characterize the transmission matrices of complex scattering media using a physics-informed, multi-plane neural network (MPNN) without a known reference field. Our method is extremely noise-robust and can characterize a cascade of transmission matrices.

AB - We accurately characterize the transmission matrices of complex scattering media using a physics-informed, multi-plane neural network (MPNN) without a known reference field. Our method is extremely noise-robust and can characterize a cascade of transmission matrices.

UR - https://www.scopus.com/pages/publications/85215529228

U2 - 10.1364/FIO.2023.JM4A.43

DO - 10.1364/FIO.2023.JM4A.43

M3 - Conference contribution

AN - SCOPUS:85215529228

SN - 9781957171296

BT - Frontiers in Optics 2023

PB - Optica Publishing Group

T2 - Frontiers in Optics + Laser Science 2023

Y2 - 9 October 2023 through 12 October 2023

ER -

Referenceless Characterisation of Complex Media Using Physics-Informed Neural Networks

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this