Modelling the Refractive Index Structure Parameter: A ResNet Approach

Christopher Lamprecht; Pasha Bekhrad; Hristo Danchov Ivanov; Erich Leitgeb

doi:10.1109/CoBCom49975.2020.9174186

Modelling the Refractive Index Structure Parameter: A ResNet Approach

Christopher Lamprecht, Pasha Bekhrad, Hristo Danchov Ivanov, Erich Leitgeb

Institute of Microwave and Photonic Engineering (4510)

Research output: Contribution to conference › Paper › peer-review

Abstract

Various atmospheric effects have a negative influence on optical signals, especially in the troposphere, which must be taken into account in free space optical (FSO) communication systems. To obtain a quantitative estimate of these effects, different mathematical models are used, often based on empirical data from around the world. The main problem with existing models is the limited accuracy, due to the different meteorological conditions at different locations on earth. We propose a new approach of modelling the refractive index structure parameter using residual neural networks (ResNets). New models, tailored to the meteorological conditions at any place on earth, can be easily created, which yields in a more accurate estimation of the refractive index profile.

Original language	English
DOIs	https://doi.org/10.1109/CoBCom49975.2020.9174186
Publication status	Published - Jul 2020
Event	3rd International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications: CoBCom 2020 - TU Graz, Virtuell, Graz, Austria Duration: 7 Jul 2020 → 10 Jul 2020 https://www.cobcom.tugraz.at/

Conference

Conference	3rd International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications
Abbreviated title	CoBCom 2020
Country/Territory	Austria
City	Virtuell, Graz
Period	7/07/20 → 10/07/20
Internet address	https://www.cobcom.tugraz.at/

Keywords

Artificial neural networks
atmospheric turbulence
Hufnagel-Valley model
machine learning
refractive index structure parameter
ResNet

ASJC Scopus subject areas

Instrumentation
Hardware and Architecture
Computer Networks and Communications
Media Technology

Access to Document

10.1109/CoBCom49975.2020.9174186

Cite this

Modelling the Refractive Index Structure Parameter: A ResNet Approach. / Lamprecht, Christopher; Bekhrad, Pasha ; Ivanov, Hristo Danchov et al.
2020. Paper presented at 3rd International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications, Virtuell, Graz, Austria.

Research output: Contribution to conference › Paper › peer-review

@conference{1fe9329801a34d0cbc8058a65b2361c9,

title = "Modelling the Refractive Index Structure Parameter: A ResNet Approach",

abstract = "Various atmospheric effects have a negative influence on optical signals, especially in the troposphere, which must be taken into account in free space optical (FSO) communication systems. To obtain a quantitative estimate of these effects, different mathematical models are used, often based on empirical data from around the world. The main problem with existing models is the limited accuracy, due to the different meteorological conditions at different locations on earth. We propose a new approach of modelling the refractive index structure parameter using residual neural networks (ResNets). New models, tailored to the meteorological conditions at any place on earth, can be easily created, which yields in a more accurate estimation of the refractive index profile.",

keywords = "Artificial neural networks, Atmospheric turbulence, Refractive index structure parameter, ResNet, Machine learning, Hufnagel-Valley model, Artificial neural networks, atmospheric turbulence, Hufnagel-Valley model, machine learning, refractive index structure parameter, ResNet",

author = "Christopher Lamprecht and Pasha Bekhrad and Ivanov, {Hristo Danchov} and Erich Leitgeb",

year = "2020",

month = jul,

doi = "10.1109/CoBCom49975.2020.9174186",

language = "English",

note = "3rd International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications : CoBCom 2020, CoBCom 2020 ; Conference date: 07-07-2020 Through 10-07-2020",

url = "https://www.cobcom.tugraz.at/",

}

TY - CONF

T1 - Modelling the Refractive Index Structure Parameter: A ResNet Approach

AU - Lamprecht, Christopher

AU - Bekhrad, Pasha

AU - Ivanov, Hristo Danchov

AU - Leitgeb, Erich

PY - 2020/7

Y1 - 2020/7

N2 - Various atmospheric effects have a negative influence on optical signals, especially in the troposphere, which must be taken into account in free space optical (FSO) communication systems. To obtain a quantitative estimate of these effects, different mathematical models are used, often based on empirical data from around the world. The main problem with existing models is the limited accuracy, due to the different meteorological conditions at different locations on earth. We propose a new approach of modelling the refractive index structure parameter using residual neural networks (ResNets). New models, tailored to the meteorological conditions at any place on earth, can be easily created, which yields in a more accurate estimation of the refractive index profile.

AB - Various atmospheric effects have a negative influence on optical signals, especially in the troposphere, which must be taken into account in free space optical (FSO) communication systems. To obtain a quantitative estimate of these effects, different mathematical models are used, often based on empirical data from around the world. The main problem with existing models is the limited accuracy, due to the different meteorological conditions at different locations on earth. We propose a new approach of modelling the refractive index structure parameter using residual neural networks (ResNets). New models, tailored to the meteorological conditions at any place on earth, can be easily created, which yields in a more accurate estimation of the refractive index profile.

KW - Artificial neural networks

KW - Atmospheric turbulence

KW - Refractive index structure parameter

KW - ResNet

KW - Machine learning

KW - Hufnagel-Valley model

KW - Artificial neural networks

KW - atmospheric turbulence

KW - Hufnagel-Valley model

KW - machine learning

KW - refractive index structure parameter

KW - ResNet

UR - http://www.scopus.com/inward/record.url?scp=85092288313&partnerID=8YFLogxK

U2 - 10.1109/CoBCom49975.2020.9174186

DO - 10.1109/CoBCom49975.2020.9174186

M3 - Paper

T2 - 3rd International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications

Y2 - 7 July 2020 through 10 July 2020

ER -

Modelling the Refractive Index Structure Parameter: A ResNet Approach

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Forschungspreis 2020 der Bundeskammer der ZiviltechnikerInnen

Cite this

Modelling the Refractive Index Structure Parameter: A ResNet Approach

Abstract

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Prizes

Forschungspreis 2020 der Bundeskammer der ZiviltechnikerInnen

Cite this