Substorm Onset Prediction Using Machine Learning Classified Auroral Images
Abstract We classify all sky images from four seasons, transform the classification results into time‐series data to include information about the evolution of images and combine these with information on the onset of geomagnetic substorms. We train a lightweight classifier on this data set to predi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-02-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2022SW003300 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536373878685696 |
|---|---|
| author | P. Sado L. B. N. Clausen W. J. Miloch H. Nickisch |
| author_facet | P. Sado L. B. N. Clausen W. J. Miloch H. Nickisch |
| author_sort | P. Sado |
| collection | DOAJ |
| description | Abstract We classify all sky images from four seasons, transform the classification results into time‐series data to include information about the evolution of images and combine these with information on the onset of geomagnetic substorms. We train a lightweight classifier on this data set to predict the onset of substorms within a 15 min interval after being shown information of 30 min of aurora. The best classifier achieves a balanced accuracy of 59% with a recall rate of 39% and false positive rate of 20%. We show that the classifier is limited by the strong imbalance in the data set of approximately 50:1 between negative and positive events. All software and results are open source and freely available. |
| format | Article |
| id | doaj-art-ecf89412c51d4eea87a9e57becd113fd |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2023-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-ecf89412c51d4eea87a9e57becd113fd2025-01-14T16:31:24ZengWileySpace Weather1542-73902023-02-01212n/an/a10.1029/2022SW003300Substorm Onset Prediction Using Machine Learning Classified Auroral ImagesP. Sado0L. B. N. Clausen1W. J. Miloch2H. Nickisch3Department of Physics University of Oslo Oslo NorwayDepartment of Physics University of Oslo Oslo NorwayDepartment of Physics University of Oslo Oslo NorwayPhilips Research Hamburg GermanyAbstract We classify all sky images from four seasons, transform the classification results into time‐series data to include information about the evolution of images and combine these with information on the onset of geomagnetic substorms. We train a lightweight classifier on this data set to predict the onset of substorms within a 15 min interval after being shown information of 30 min of aurora. The best classifier achieves a balanced accuracy of 59% with a recall rate of 39% and false positive rate of 20%. We show that the classifier is limited by the strong imbalance in the data set of approximately 50:1 between negative and positive events. All software and results are open source and freely available.https://doi.org/10.1029/2022SW003300auroraall sky imagermachine learningspace weathersubstormsspace weather prediction |
| spellingShingle | P. Sado L. B. N. Clausen W. J. Miloch H. Nickisch Substorm Onset Prediction Using Machine Learning Classified Auroral Images Space Weather aurora all sky imager machine learning space weather substorms space weather prediction |
| title | Substorm Onset Prediction Using Machine Learning Classified Auroral Images |
| title_full | Substorm Onset Prediction Using Machine Learning Classified Auroral Images |
| title_fullStr | Substorm Onset Prediction Using Machine Learning Classified Auroral Images |
| title_full_unstemmed | Substorm Onset Prediction Using Machine Learning Classified Auroral Images |
| title_short | Substorm Onset Prediction Using Machine Learning Classified Auroral Images |
| title_sort | substorm onset prediction using machine learning classified auroral images |
| topic | aurora all sky imager machine learning space weather substorms space weather prediction |
| url | https://doi.org/10.1029/2022SW003300 |
| work_keys_str_mv | AT psado substormonsetpredictionusingmachinelearningclassifiedauroralimages AT lbnclausen substormonsetpredictionusingmachinelearningclassifiedauroralimages AT wjmiloch substormonsetpredictionusingmachinelearningclassifiedauroralimages AT hnickisch substormonsetpredictionusingmachinelearningclassifiedauroralimages |