|
Persistent Identifier
|
doi:10.18710/SSA38J |
|
Publication Date
|
2020-01-15 |
|
Title
| Replication Data for: Auroral Image Classification with Deep Neural Networks |
|
Author
| Kvammen, AndreasUiT The Arctic University of NorwayORCID0000-0002-5511-4473
Wickstrøm, KristofferUiT The Arctic University of NorwayORCID0000-0003-1395-7154
McKay, DerekNORCE Norwegian Research CentreORCID0000-0003-1052-1929
Partamies, NooraUniversity Centre in SvalbardORCID0000-0003-2536-9341 |
|
Point of Contact
|
Use email button above to contact.
Kvammen, Andreas (UiT The Arctic University of Norway)
Wickstrøm, Kristoffer (UiT The Arctic University of Norway) |
|
Description
| Results from a study of automatic aurora classification using machine learning techniques are presented. The aurora is the manifestation of physical phenomena in the ionosphere magnetosphere environment. Automatic classification of millions of auroral images from the Arctic and Antarctic is therefore an attractive tool for developing auroral statistics and for supporting scientists to study auroral images in an objective, organized and repeatable manner. Although previous studies have presented tools for detecting aurora, there has been a lack of tools for classifying aurora into subclasses with a high precision (>90%). This work considers seven auroral subclasses; breakup, colored, arcs-bands, discrete, patchy, edge and clear-faint. Five different deep neural network architectures have been tested along with the well known classification methods; k nearest neighbor (KNN) and support vector machine (SVM). A set of clean nighttime color auroral images, without ambiguous auroral forms, moonlight, twilight, clouds etc., were used for training and testing. The deep neural networks generally outperformed the KNN and SVM methods, and the ResNet-50 architecture achieved the highest performance with an average classification precision of 92%. Although the results indicate that high precision aurora classification is an attainable objective using deep neural networks, it is stressed that a common consensus of the auroral morphology and the criteria for each class needs.
The authors would like to thank Urban Brändström and the Swedish Institute of Space Physics for providing the original auroral image data. The image data archive is freely accessible at http://www2.irf.se/allsky/data.html, however, the users are obliged to contact the Kiruna Atmospheric and Geophysical Observatory before usage (2020-01-03) |
|
Subject
| Computer and Information Science; Mathematical Sciences; Physics |
|
Keyword
| auroral images
auroral classification
convolutional neural networks
aurora dataset
deep learning |
|
Related Publication
| Kvammen, A., Wickstrøm, K., McKay, D., & Partamies, N. (2020). Auroral image classification with deep neural networks. Journal of Geophysical Research: Space Physics, 125, e2020JA027808. https://doi.org/10.1029/2020JA027808 doi 10.1029/2020JA027808 https://doi.org/10.1029/2020JA027808
McKay, D. and Kvammen, A.: Auroral classification ergonomics and the implications for machine learning, Geoscientific Instrumentation, Methods and Data Systems, 9, 267–273, https://doi.org/10.5194/gi-9-267-2020, 2020. doi 10.5194/gi-9-267-2020 https://doi.org/10.5194/gi-9-267-2020 |
|
Language
| English |
|
Producer
| UiT The Arctic University of Norway (UiT) https://en.uit.no/ |
|
Production Location
| Kiruna, Sweden |
|
Contributor
| Data Collector: Swedish Institute of Space Physics |
|
Distributor
| UiT The Arctic University of Norway (UiT The Arctic University of Norway) https://dataverse.no/dataverse/uit |
|
Depositor
| Wickstrøm, Kristoffer Knutsen |
|
Deposit Date
| 2020-01-03 |
|
Time Period
| Start Date: 2009-01-01; End Date: 2020-01-01 |
|
Date of Collection
| Start Date: 2010-01-01; End Date: 2019-01-01 |
|
Data Type
| Images |
|
Related Dataset
| The dataset contained in this repository was extracted from the All-Sky camera in Kiruna, Sweden, available at http://www2.irf.se/allsky/data.html. |
