Total electron content forecasting using artificial neural network

Space weather forecasting and its importance for the power and communication industry have inspired research related to TEC forecasting lately. Research has attempted to establish an empirical model approach for TEC prediction. In this paper, artificial neural networks (ANNs) have been applied in to...

Full description

Bibliographic Details
Main Authors: Mat Akir, Rohaida, Chellappan, Kalaivani, Abdullah, Mardina
Format: Article
Language:English
Published: Universiti Putra Malaysia 2017
Subjects:
Online Access:http://eprints.uthm.edu.my/2906/
http://eprints.uthm.edu.my/2906/1/AJ%202019%20%2869%29.pdf
_version_ 1848887874146009088
author Mat Akir, Rohaida
Chellappan, Kalaivani
Abdullah, Mardina
author_facet Mat Akir, Rohaida
Chellappan, Kalaivani
Abdullah, Mardina
author_sort Mat Akir, Rohaida
building UTHM Institutional Repository
collection Online Access
description Space weather forecasting and its importance for the power and communication industry have inspired research related to TEC forecasting lately. Research has attempted to establish an empirical model approach for TEC prediction. In this paper, artificial neural networks (ANNs) have been applied in total electron content using GPS Ionospheric Scintillation and TEC Monitor (GISTM) data from UKM Station. The TEC prediction will be useful in improving the quality of current GNSS applications, such as in automobiles, road mapping, location-based advertising, personal navigation or logistics. Hence, a neural network model was designed with relevant features and customised parameters. Various types of input data and data representations from the ionospheric activity were used for the chosen network structure, which was a three-layer perceptron trained by feed forward back propagation method and tested on the chosen test data. We found that the optimum RMSE occurred with 10 nodes as the best NN for GISTM UKM station for the studied period with RMSE 1.3457 TECU. An analysis was made to compare the TEC from the measured TEC with neural network prediction and from IRI-corr model. The results showed that the NN model forecast the TEC values close to the measured TEC values with 9.96% of relative error. Thus, the forecasting of total electron content has the potential to be implemented successfully with larger data set from multi-centred environment.
first_indexed 2025-11-15T20:01:19Z
format Article
id uthm-2906
institution Universiti Tun Hussein Onn Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T20:01:19Z
publishDate 2017
publisher Universiti Putra Malaysia
recordtype eprints
repository_type Digital Repository
spelling uthm-29062021-11-16T04:12:31Z http://eprints.uthm.edu.my/2906/ Total electron content forecasting using artificial neural network Mat Akir, Rohaida Chellappan, Kalaivani Abdullah, Mardina G100.5 -108.5 Toponymy Including gazetteers, geographic names and terms TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television Space weather forecasting and its importance for the power and communication industry have inspired research related to TEC forecasting lately. Research has attempted to establish an empirical model approach for TEC prediction. In this paper, artificial neural networks (ANNs) have been applied in total electron content using GPS Ionospheric Scintillation and TEC Monitor (GISTM) data from UKM Station. The TEC prediction will be useful in improving the quality of current GNSS applications, such as in automobiles, road mapping, location-based advertising, personal navigation or logistics. Hence, a neural network model was designed with relevant features and customised parameters. Various types of input data and data representations from the ionospheric activity were used for the chosen network structure, which was a three-layer perceptron trained by feed forward back propagation method and tested on the chosen test data. We found that the optimum RMSE occurred with 10 nodes as the best NN for GISTM UKM station for the studied period with RMSE 1.3457 TECU. An analysis was made to compare the TEC from the measured TEC with neural network prediction and from IRI-corr model. The results showed that the NN model forecast the TEC values close to the measured TEC values with 9.96% of relative error. Thus, the forecasting of total electron content has the potential to be implemented successfully with larger data set from multi-centred environment. Universiti Putra Malaysia 2017 Article PeerReviewed text en http://eprints.uthm.edu.my/2906/1/AJ%202019%20%2869%29.pdf Mat Akir, Rohaida and Chellappan, Kalaivani and Abdullah, Mardina (2017) Total electron content forecasting using artificial neural network. Pertanika Journal of Social Science and Technology, 25 (S). pp. 19-28. ISSN 0128-7680 http://www.pertanika.upm.edu.my/pjst/browse/special-issue?article=JST-S0371-2017
spellingShingle G100.5 -108.5 Toponymy Including gazetteers, geographic names and terms
TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Mat Akir, Rohaida
Chellappan, Kalaivani
Abdullah, Mardina
Total electron content forecasting using artificial neural network
title Total electron content forecasting using artificial neural network
title_full Total electron content forecasting using artificial neural network
title_fullStr Total electron content forecasting using artificial neural network
title_full_unstemmed Total electron content forecasting using artificial neural network
title_short Total electron content forecasting using artificial neural network
title_sort total electron content forecasting using artificial neural network
topic G100.5 -108.5 Toponymy Including gazetteers, geographic names and terms
TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
url http://eprints.uthm.edu.my/2906/
http://eprints.uthm.edu.my/2906/
http://eprints.uthm.edu.my/2906/1/AJ%202019%20%2869%29.pdf