Fuzzy inference systems for the prediction of Earth rotation parameters

Orhan Akyilmaz; Hansjörg Kutterer

doi:10.1007/3-540-27432-4_99

Fuzzy inference systems for the prediction of Earth rotation parameters

Orhan Akyilmaz, Hansjörg Kutterer

Department of Geomatics Engineering

Deutsches Geodätisches Forschungsinstitut

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

2 Citations (Scopus)

Abstract

The paper presents short-term and longterm predictions of Earth rotation parameters (ERP) (Length-of-Day and polar motion) up to one year by means of ANFIS (Adaptive Network based Fuzzy Inference System). The ERP C04 time series of the International Earth Rotation and Reference Systems Service (IERS) with daily values are used as data basis. The impact of the tides of the solid Earth and the oceans and seasonal variations of the atmosphere are removed from the C04 series. The residual series are used both for training and validation of the ANFIS. For network optimization purposes, different architectures are considered. The results of the prediction are compared with those from other methods. The ERP values predicted by ANFIS have RMS errors, which are equal or even less than those from other methods. The most striking advantage of using ANFIS instead of other approaches is its significantly reduced complexity.

Original language	English
Title of host publication	A Window on the Future of Geodesy - Proceedings of the International Association of Geodesy
Editors	Fernando Sansò
Publisher	Springer Verlag
Pages	582-587
Number of pages	6
ISBN (Print)	9783540240556
DOIs	https://doi.org/10.1007/3-540-27432-4_99
Publication status	Published - 2005
Event	Proceedings of the International Association of Geodesy, IAG 2003 - Sapporo, Japan Duration: 30 Jun 2003 → 11 Jul 2003

Publication series

Name	International Association of Geodesy Symposia
Volume	128
ISSN (Print)	0939-9585
ISSN (Electronic)	2197-9359

Conference

Conference	Proceedings of the International Association of Geodesy, IAG 2003
Country/Territory	Japan
City	Sapporo
Period	30/06/03 → 11/07/03

Bibliographical note

Publisher Copyright:
© Springer-Verlag Berlin Heidelberg 2005.

Funding

The authors would like to thank DAAD for supporting this project. Special thanks to DGFI (Deutsches Geodatisches Forschungsinstitut) for providing scientific and logistic assistance. The advice of Dr. Katja Heine from Cottbus University of Technology is gratefully acknowledged.

Funders	Funder number
Cottbus University of Technology
DGFI
Deutscher Akademischer Austauschdienst

Keywords

ANFIS
Earth rotation
Fuzzy inference systems
Prediction
Soft computing

Access to Document

10.1007/3-540-27432-4_99

Cite this

@inproceedings{e7fac814429a4f50911dae0dd464f7ed,

title = "Fuzzy inference systems for the prediction of Earth rotation parameters",

abstract = "The paper presents short-term and longterm predictions of Earth rotation parameters (ERP) (Length-of-Day and polar motion) up to one year by means of ANFIS (Adaptive Network based Fuzzy Inference System). The ERP C04 time series of the International Earth Rotation and Reference Systems Service (IERS) with daily values are used as data basis. The impact of the tides of the solid Earth and the oceans and seasonal variations of the atmosphere are removed from the C04 series. The residual series are used both for training and validation of the ANFIS. For network optimization purposes, different architectures are considered. The results of the prediction are compared with those from other methods. The ERP values predicted by ANFIS have RMS errors, which are equal or even less than those from other methods. The most striking advantage of using ANFIS instead of other approaches is its significantly reduced complexity.",

keywords = "ANFIS, Earth rotation, Fuzzy inference systems, Prediction, Soft computing",

author = "Orhan Akyilmaz and Hansj{\"o}rg Kutterer",

note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2005.; Proceedings of the International Association of Geodesy, IAG 2003 ; Conference date: 30-06-2003 Through 11-07-2003",

year = "2005",

doi = "10.1007/3-540-27432-4_99",

language = "English",

isbn = "9783540240556",

series = "International Association of Geodesy Symposia",

publisher = "Springer Verlag",

pages = "582--587",

editor = "Fernando Sans{\`o}",

booktitle = "A Window on the Future of Geodesy - Proceedings of the International Association of Geodesy",

address = "Germany",

}

Akyilmaz, O & Kutterer, H 2005, Fuzzy inference systems for the prediction of Earth rotation parameters. in F Sansò (ed.), A Window on the Future of Geodesy - Proceedings of the International Association of Geodesy. International Association of Geodesy Symposia, vol. 128, Springer Verlag, pp. 582-587, Proceedings of the International Association of Geodesy, IAG 2003, Sapporo, Japan, 30/06/03. https://doi.org/10.1007/3-540-27432-4_99

Fuzzy inference systems for the prediction of Earth rotation parameters. / Akyilmaz, Orhan; Kutterer, Hansjörg.
A Window on the Future of Geodesy - Proceedings of the International Association of Geodesy. ed. / Fernando Sansò. Springer Verlag, 2005. p. 582-587 (International Association of Geodesy Symposia; Vol. 128).

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

TY - GEN

T1 - Fuzzy inference systems for the prediction of Earth rotation parameters

AU - Akyilmaz, Orhan

AU - Kutterer, Hansjörg

N1 - Publisher Copyright: © Springer-Verlag Berlin Heidelberg 2005.

PY - 2005

Y1 - 2005

N2 - The paper presents short-term and longterm predictions of Earth rotation parameters (ERP) (Length-of-Day and polar motion) up to one year by means of ANFIS (Adaptive Network based Fuzzy Inference System). The ERP C04 time series of the International Earth Rotation and Reference Systems Service (IERS) with daily values are used as data basis. The impact of the tides of the solid Earth and the oceans and seasonal variations of the atmosphere are removed from the C04 series. The residual series are used both for training and validation of the ANFIS. For network optimization purposes, different architectures are considered. The results of the prediction are compared with those from other methods. The ERP values predicted by ANFIS have RMS errors, which are equal or even less than those from other methods. The most striking advantage of using ANFIS instead of other approaches is its significantly reduced complexity.

AB - The paper presents short-term and longterm predictions of Earth rotation parameters (ERP) (Length-of-Day and polar motion) up to one year by means of ANFIS (Adaptive Network based Fuzzy Inference System). The ERP C04 time series of the International Earth Rotation and Reference Systems Service (IERS) with daily values are used as data basis. The impact of the tides of the solid Earth and the oceans and seasonal variations of the atmosphere are removed from the C04 series. The residual series are used both for training and validation of the ANFIS. For network optimization purposes, different architectures are considered. The results of the prediction are compared with those from other methods. The ERP values predicted by ANFIS have RMS errors, which are equal or even less than those from other methods. The most striking advantage of using ANFIS instead of other approaches is its significantly reduced complexity.

KW - ANFIS

KW - Earth rotation

KW - Fuzzy inference systems

KW - Prediction

KW - Soft computing

UR - http://www.scopus.com/inward/record.url?scp=84964012099&partnerID=8YFLogxK

U2 - 10.1007/3-540-27432-4_99

DO - 10.1007/3-540-27432-4_99

M3 - Conference contribution

AN - SCOPUS:84964012099

SN - 9783540240556

T3 - International Association of Geodesy Symposia

SP - 582

EP - 587

BT - A Window on the Future of Geodesy - Proceedings of the International Association of Geodesy

A2 - Sansò, Fernando

PB - Springer Verlag

T2 - Proceedings of the International Association of Geodesy, IAG 2003

Y2 - 30 June 2003 through 11 July 2003

ER -

Fuzzy inference systems for the prediction of Earth rotation parameters

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this