Monitoring Space Weather: Using Automated, Accurate Neural Network Based Whistler Segmentation for Whistler Inversion
Abstract It is challenging, yet important, to measure the—ever‐changing—cold electron density in the plasmasphere. The cold electron density inside and outside of the plasmapause is a key parameter for radiation belt dynamics. One indirect measurement is through finding the velocity dispersion relat...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-02-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2021SW002981 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536374357884928 |
|---|---|
| author | Bálint Ármin Pataki János Lichtenberger Mark Clilverd Gergely Máthé Péter Steinbach Szilárd Pásztor Lilla Murár‐Juhász Dávid Koronczay Orsolya Ferencz István Csabai |
| author_facet | Bálint Ármin Pataki János Lichtenberger Mark Clilverd Gergely Máthé Péter Steinbach Szilárd Pásztor Lilla Murár‐Juhász Dávid Koronczay Orsolya Ferencz István Csabai |
| author_sort | Bálint Ármin Pataki |
| collection | DOAJ |
| description | Abstract It is challenging, yet important, to measure the—ever‐changing—cold electron density in the plasmasphere. The cold electron density inside and outside of the plasmapause is a key parameter for radiation belt dynamics. One indirect measurement is through finding the velocity dispersion relation exhibited by lightning induced whistlers. The main difficulty of the method comes from low signal‐to‐noise ratios for most of the ground‐based whistler components. To provide accurate electron density and L‐shell measurements, whistler components need to be detectable in the noisy background, and their characteristics need to be reliably determined. For this reason, precise segmentation is needed on a spectrogram image. Here, we present a fully automated way to perform such an image segmentation by leveraging the power of convolutional neural networks, a state‐of‐the‐art method for computer vision tasks. Testing the proposed method against a manually, and semi‐manually segmented whistler data set achieved <10% relative electron density prediction error for 80% of the segmented whistler traces, while for the L shell, the relative error is <5% for 90% of the cases. By segmenting more than 1 million additional real whistler traces from Rothera station Antarctica, logged over 9 years, seasonal changes in the average electron density were found. The variations match previously published findings, and confirm the capabilities of the image segmentation technique. |
| format | Article |
| id | doaj-art-eda0965c6ea3475f8ec4a5d62ee4fc7a |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2022-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-eda0965c6ea3475f8ec4a5d62ee4fc7a2025-01-14T16:30:59ZengWileySpace Weather1542-73902022-02-01202n/an/a10.1029/2021SW002981Monitoring Space Weather: Using Automated, Accurate Neural Network Based Whistler Segmentation for Whistler InversionBálint Ármin Pataki0János Lichtenberger1Mark Clilverd2Gergely Máthé3Péter Steinbach4Szilárd Pásztor5Lilla Murár‐Juhász6Dávid Koronczay7Orsolya Ferencz8István Csabai9Department of Physics of Complex Systems ELTE Eötvös Loránd University Budapest HungarySpace Research Group Department of Geophysics and Space Sciences ELTE Eötvös Loránd University Budapest HungaryBritish Antarctic Survey (UKRI‐NERC) Cambridge UKDepartment of Physics of Complex Systems ELTE Eötvös Loránd University Budapest HungaryELKH‐ELTE Research Group for Geology, Geophysics and Space Sciences Budapest HungarySpace Research Group Department of Geophysics and Space Sciences ELTE Eötvös Loránd University Budapest HungarySpace Research Group Department of Geophysics and Space Sciences ELTE Eötvös Loránd University Budapest HungarySpace Research Group Department of Geophysics and Space Sciences ELTE Eötvös Loránd University Budapest HungarySpace Research Group Department of Geophysics and Space Sciences ELTE Eötvös Loránd University Budapest HungaryDepartment of Physics of Complex Systems ELTE Eötvös Loránd University Budapest HungaryAbstract It is challenging, yet important, to measure the—ever‐changing—cold electron density in the plasmasphere. The cold electron density inside and outside of the plasmapause is a key parameter for radiation belt dynamics. One indirect measurement is through finding the velocity dispersion relation exhibited by lightning induced whistlers. The main difficulty of the method comes from low signal‐to‐noise ratios for most of the ground‐based whistler components. To provide accurate electron density and L‐shell measurements, whistler components need to be detectable in the noisy background, and their characteristics need to be reliably determined. For this reason, precise segmentation is needed on a spectrogram image. Here, we present a fully automated way to perform such an image segmentation by leveraging the power of convolutional neural networks, a state‐of‐the‐art method for computer vision tasks. Testing the proposed method against a manually, and semi‐manually segmented whistler data set achieved <10% relative electron density prediction error for 80% of the segmented whistler traces, while for the L shell, the relative error is <5% for 90% of the cases. By segmenting more than 1 million additional real whistler traces from Rothera station Antarctica, logged over 9 years, seasonal changes in the average electron density were found. The variations match previously published findings, and confirm the capabilities of the image segmentation technique.https://doi.org/10.1029/2021SW002981whistlerplasmasphereneural network |
| spellingShingle | Bálint Ármin Pataki János Lichtenberger Mark Clilverd Gergely Máthé Péter Steinbach Szilárd Pásztor Lilla Murár‐Juhász Dávid Koronczay Orsolya Ferencz István Csabai Monitoring Space Weather: Using Automated, Accurate Neural Network Based Whistler Segmentation for Whistler Inversion Space Weather whistler plasmasphere neural network |
| title | Monitoring Space Weather: Using Automated, Accurate Neural Network Based Whistler Segmentation for Whistler Inversion |
| title_full | Monitoring Space Weather: Using Automated, Accurate Neural Network Based Whistler Segmentation for Whistler Inversion |
| title_fullStr | Monitoring Space Weather: Using Automated, Accurate Neural Network Based Whistler Segmentation for Whistler Inversion |
| title_full_unstemmed | Monitoring Space Weather: Using Automated, Accurate Neural Network Based Whistler Segmentation for Whistler Inversion |
| title_short | Monitoring Space Weather: Using Automated, Accurate Neural Network Based Whistler Segmentation for Whistler Inversion |
| title_sort | monitoring space weather using automated accurate neural network based whistler segmentation for whistler inversion |
| topic | whistler plasmasphere neural network |
| url | https://doi.org/10.1029/2021SW002981 |
| work_keys_str_mv | AT balintarminpataki monitoringspaceweatherusingautomatedaccurateneuralnetworkbasedwhistlersegmentationforwhistlerinversion AT janoslichtenberger monitoringspaceweatherusingautomatedaccurateneuralnetworkbasedwhistlersegmentationforwhistlerinversion AT markclilverd monitoringspaceweatherusingautomatedaccurateneuralnetworkbasedwhistlersegmentationforwhistlerinversion AT gergelymathe monitoringspaceweatherusingautomatedaccurateneuralnetworkbasedwhistlersegmentationforwhistlerinversion AT petersteinbach monitoringspaceweatherusingautomatedaccurateneuralnetworkbasedwhistlersegmentationforwhistlerinversion AT szilardpasztor monitoringspaceweatherusingautomatedaccurateneuralnetworkbasedwhistlersegmentationforwhistlerinversion AT lillamurarjuhasz monitoringspaceweatherusingautomatedaccurateneuralnetworkbasedwhistlersegmentationforwhistlerinversion AT davidkoronczay monitoringspaceweatherusingautomatedaccurateneuralnetworkbasedwhistlersegmentationforwhistlerinversion AT orsolyaferencz monitoringspaceweatherusingautomatedaccurateneuralnetworkbasedwhistlersegmentationforwhistlerinversion AT istvancsabai monitoringspaceweatherusingautomatedaccurateneuralnetworkbasedwhistlersegmentationforwhistlerinversion |