NOIRE-Net–a convolutional neural network for automatic classification and scaling of high-latitude ionograms
Millions of ionograms are acquired annually to monitor the ionosphere. The accumulated data contain untapped information from a range of locations, multiple solar cycles, and various geomagnetic conditions. In this study, we propose the application of deep convolutional neural networks to automatica...
Published in: | Frontiers in Astronomy and Space Sciences |
---|---|
Main Authors: | , , , , , , |
Other Authors: | |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
Frontiers Media SA
2024
|
Subjects: | |
Online Access: | http://dx.doi.org/10.3389/fspas.2024.1289840 https://www.frontiersin.org/articles/10.3389/fspas.2024.1289840/full |
id |
crfrontiers:10.3389/fspas.2024.1289840 |
---|---|
record_format |
openpolar |
spelling |
crfrontiers:10.3389/fspas.2024.1289840 2024-09-15T18:04:30+00:00 NOIRE-Net–a convolutional neural network for automatic classification and scaling of high-latitude ionograms Kvammen, Andreas Vierinen, Juha Huyghebaert, Devin Rexer, Theresa Spicher, Andres Gustavsson, Björn Floberg, Jens Universitetet i Tromsø 2024 http://dx.doi.org/10.3389/fspas.2024.1289840 https://www.frontiersin.org/articles/10.3389/fspas.2024.1289840/full unknown Frontiers Media SA https://creativecommons.org/licenses/by/4.0/ Frontiers in Astronomy and Space Sciences volume 11 ISSN 2296-987X journal-article 2024 crfrontiers https://doi.org/10.3389/fspas.2024.1289840 2024-07-23T04:03:28Z Millions of ionograms are acquired annually to monitor the ionosphere. The accumulated data contain untapped information from a range of locations, multiple solar cycles, and various geomagnetic conditions. In this study, we propose the application of deep convolutional neural networks to automatically classify and scale high-latitude ionograms. A supervised approach is implemented and the networks are trained and tested using manually analyzed oblique ionograms acquired at a receiver station located in Skibotn, Norway. The classification routine categorizes the observations based on the presence or absence of E− and F-region traces, while the scaling procedure automatically defines the E− and F-region virtual distances and maximum plasma frequencies. Overall, we conclude that deep convolutional neural networks are suitable for automatic processing of ionograms, even under auroral conditions. The networks achieve an average classification accuracy of 93% ± 4% for the E-region and 86% ± 7% for the F-region. In addition, the networks obtain scientifically useful scaling parameters with median absolute deviation values of 118 kHz ±27 kHz for the E-region maximum frequency and 105 kHz ±37 kHz for the F-region maximum O-mode frequency. Predictions of the virtual distance for the E− and F-region yield median distance deviation values of 6.1 km ± 1.7 km and 8.3 km ± 2.3 km, respectively. The developed networks may facilitate EISCAT 3D and other instruments in Fennoscandia by automatic cataloging and scaling of salient ionospheric features. This data can be used to study both long-term ionospheric trends and more transient ionospheric features, such as traveling ionospheric disturbances. Article in Journal/Newspaper EISCAT Fennoscandia Skibotn Frontiers (Publisher) Frontiers in Astronomy and Space Sciences 11 |
institution |
Open Polar |
collection |
Frontiers (Publisher) |
op_collection_id |
crfrontiers |
language |
unknown |
description |
Millions of ionograms are acquired annually to monitor the ionosphere. The accumulated data contain untapped information from a range of locations, multiple solar cycles, and various geomagnetic conditions. In this study, we propose the application of deep convolutional neural networks to automatically classify and scale high-latitude ionograms. A supervised approach is implemented and the networks are trained and tested using manually analyzed oblique ionograms acquired at a receiver station located in Skibotn, Norway. The classification routine categorizes the observations based on the presence or absence of E− and F-region traces, while the scaling procedure automatically defines the E− and F-region virtual distances and maximum plasma frequencies. Overall, we conclude that deep convolutional neural networks are suitable for automatic processing of ionograms, even under auroral conditions. The networks achieve an average classification accuracy of 93% ± 4% for the E-region and 86% ± 7% for the F-region. In addition, the networks obtain scientifically useful scaling parameters with median absolute deviation values of 118 kHz ±27 kHz for the E-region maximum frequency and 105 kHz ±37 kHz for the F-region maximum O-mode frequency. Predictions of the virtual distance for the E− and F-region yield median distance deviation values of 6.1 km ± 1.7 km and 8.3 km ± 2.3 km, respectively. The developed networks may facilitate EISCAT 3D and other instruments in Fennoscandia by automatic cataloging and scaling of salient ionospheric features. This data can be used to study both long-term ionospheric trends and more transient ionospheric features, such as traveling ionospheric disturbances. |
author2 |
Universitetet i Tromsø |
format |
Article in Journal/Newspaper |
author |
Kvammen, Andreas Vierinen, Juha Huyghebaert, Devin Rexer, Theresa Spicher, Andres Gustavsson, Björn Floberg, Jens |
spellingShingle |
Kvammen, Andreas Vierinen, Juha Huyghebaert, Devin Rexer, Theresa Spicher, Andres Gustavsson, Björn Floberg, Jens NOIRE-Net–a convolutional neural network for automatic classification and scaling of high-latitude ionograms |
author_facet |
Kvammen, Andreas Vierinen, Juha Huyghebaert, Devin Rexer, Theresa Spicher, Andres Gustavsson, Björn Floberg, Jens |
author_sort |
Kvammen, Andreas |
title |
NOIRE-Net–a convolutional neural network for automatic classification and scaling of high-latitude ionograms |
title_short |
NOIRE-Net–a convolutional neural network for automatic classification and scaling of high-latitude ionograms |
title_full |
NOIRE-Net–a convolutional neural network for automatic classification and scaling of high-latitude ionograms |
title_fullStr |
NOIRE-Net–a convolutional neural network for automatic classification and scaling of high-latitude ionograms |
title_full_unstemmed |
NOIRE-Net–a convolutional neural network for automatic classification and scaling of high-latitude ionograms |
title_sort |
noire-net–a convolutional neural network for automatic classification and scaling of high-latitude ionograms |
publisher |
Frontiers Media SA |
publishDate |
2024 |
url |
http://dx.doi.org/10.3389/fspas.2024.1289840 https://www.frontiersin.org/articles/10.3389/fspas.2024.1289840/full |
genre |
EISCAT Fennoscandia Skibotn |
genre_facet |
EISCAT Fennoscandia Skibotn |
op_source |
Frontiers in Astronomy and Space Sciences volume 11 ISSN 2296-987X |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3389/fspas.2024.1289840 |
container_title |
Frontiers in Astronomy and Space Sciences |
container_volume |
11 |
_version_ |
1810441990528040960 |