Total Electron Content PCA-NN Prediction Model for South-European Middle Latitudes
A regression-based model was previously developed to forecast total electron content (TEC) at middle latitudes. We present a more sophisticated model using neural networks (NN) instead of linear regression. This regional model prototype simulates and forecasts TEC variations in relation to space wea...
Published in: | Atmosphere |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/atmos14071058 |
id |
ftmdpi:oai:mdpi.com:/2073-4433/14/7/1058/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2073-4433/14/7/1058/ 2023-08-20T04:08:22+02:00 Total Electron Content PCA-NN Prediction Model for South-European Middle Latitudes Anna Morozova Teresa Barata Tatiana Barlyaeva Ricardo Gafeira agris 2023-06-21 application/pdf https://doi.org/10.3390/atmos14071058 EN eng Multidisciplinary Digital Publishing Institute Upper Atmosphere https://dx.doi.org/10.3390/atmos14071058 https://creativecommons.org/licenses/by/4.0/ Atmosphere; Volume 14; Issue 7; Pages: 1058 ionosphere total electron content prediction middle latitudes neural networks space weather Text 2023 ftmdpi https://doi.org/10.3390/atmos14071058 2023-08-01T10:34:11Z A regression-based model was previously developed to forecast total electron content (TEC) at middle latitudes. We present a more sophisticated model using neural networks (NN) instead of linear regression. This regional model prototype simulates and forecasts TEC variations in relation to space weather conditions. The development of a prototype consisted of the selection of the best set of predictors, NN architecture, and the length of the input series. Tests made using the data from December 2014 to June 2018 show that the PCA-NN model based on a simple feed-forward NN with a very limited number (up to six) of space weather predictors performs better than the PCA-MRM model that uses up to 27 space weather predictors. The prototype is developed on a TEC series obtained from a GNSS receiver at Lisbon airport and tested on TEC series from three other locations at middle latitudes of the Eastern North Atlantic. Conclusions on the dependence of the forecast quality on longitude and latitude are made. Text North Atlantic MDPI Open Access Publishing Atmosphere 14 7 1058 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
ionosphere total electron content prediction middle latitudes neural networks space weather |
spellingShingle |
ionosphere total electron content prediction middle latitudes neural networks space weather Anna Morozova Teresa Barata Tatiana Barlyaeva Ricardo Gafeira Total Electron Content PCA-NN Prediction Model for South-European Middle Latitudes |
topic_facet |
ionosphere total electron content prediction middle latitudes neural networks space weather |
description |
A regression-based model was previously developed to forecast total electron content (TEC) at middle latitudes. We present a more sophisticated model using neural networks (NN) instead of linear regression. This regional model prototype simulates and forecasts TEC variations in relation to space weather conditions. The development of a prototype consisted of the selection of the best set of predictors, NN architecture, and the length of the input series. Tests made using the data from December 2014 to June 2018 show that the PCA-NN model based on a simple feed-forward NN with a very limited number (up to six) of space weather predictors performs better than the PCA-MRM model that uses up to 27 space weather predictors. The prototype is developed on a TEC series obtained from a GNSS receiver at Lisbon airport and tested on TEC series from three other locations at middle latitudes of the Eastern North Atlantic. Conclusions on the dependence of the forecast quality on longitude and latitude are made. |
format |
Text |
author |
Anna Morozova Teresa Barata Tatiana Barlyaeva Ricardo Gafeira |
author_facet |
Anna Morozova Teresa Barata Tatiana Barlyaeva Ricardo Gafeira |
author_sort |
Anna Morozova |
title |
Total Electron Content PCA-NN Prediction Model for South-European Middle Latitudes |
title_short |
Total Electron Content PCA-NN Prediction Model for South-European Middle Latitudes |
title_full |
Total Electron Content PCA-NN Prediction Model for South-European Middle Latitudes |
title_fullStr |
Total Electron Content PCA-NN Prediction Model for South-European Middle Latitudes |
title_full_unstemmed |
Total Electron Content PCA-NN Prediction Model for South-European Middle Latitudes |
title_sort |
total electron content pca-nn prediction model for south-european middle latitudes |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2023 |
url |
https://doi.org/10.3390/atmos14071058 |
op_coverage |
agris |
genre |
North Atlantic |
genre_facet |
North Atlantic |
op_source |
Atmosphere; Volume 14; Issue 7; Pages: 1058 |
op_relation |
Upper Atmosphere https://dx.doi.org/10.3390/atmos14071058 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/atmos14071058 |
container_title |
Atmosphere |
container_volume |
14 |
container_issue |
7 |
container_start_page |
1058 |
_version_ |
1774720593524948992 |