skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Automatic Classification of Auroral Images From the Oslo Auroral THEMIS (OATH) Data Set Using Machine Learning

Journal of geophysical research. Space physics, 2018-07, Vol.123 (7), p.5640-5647 [Peer Reviewed Journal]

2018. The Authors. ;2018. American Geophysical Union. All Rights Reserved. ;info:eu-repo/semantics/openAccess ;ISSN: 2169-9380 ;EISSN: 2169-9402 ;DOI: 10.1029/2018JA025274

Digital Resources/Online E-Resources

Citations Cited by
  • Title:
    Automatic Classification of Auroral Images From the Oslo Auroral THEMIS (OATH) Data Set Using Machine Learning
  • Author: Clausen, Lasse B. N. ; Nickisch, Hannes
  • Subjects: Artificial neural networks ; aurora ; auroral imaging ; Automatic classification ; Classification ; Classifiers ; Computer codes ; Feature extraction ; Image classification ; Labels ; Machine learning ; Moon ; Neural networks
  • Is Part Of: Journal of geophysical research. Space physics, 2018-07, Vol.123 (7), p.5640-5647
  • Description: Based on their salient features we manually label 5,824 images from various Time History of Events and Macroscale Interactions during Substorms (THEMIS) all‐sky imagers; the labels we use are clear/no aurora, cloudy, moon, arc, diffuse, and discrete. We then use a pretrained deep neural network to automatically extract a 1,001‐dimensional feature vector from these images. Together, the labels and feature vectors are used to train a ridge classifier that is then able to correctly predict the category of unseen auroral images based on extracted features with 82% accuracy. If we only distinguish between a binary classification aurora and no aurora, the true positive rate increases to 96%. While this study paves the way for easy automatic classification of all auroral images from the THEMIS all‐sky imager chain, we believe that the methodology shown here is readily applied to all images from any other auroral imager as long as the data are available in digital form. Both the neural network and the ridge classifier are free, off‐the‐shelf computer codes; the simplicity of our approach is demonstrated by the fact that our entire analysis comprises about 50 lines of Python code. Automatically attaching labels to all available all‐sky imager data would enable statistical studies of unprecedented scope. Key Points We use a deep neural network to automatically extract features from auroral images With these features we train a machine to predict the detailed auroral image category We achieve an auroral classification accuracy of 82% and an auroral detection rate of 96%
  • Publisher: Washington: Blackwell Publishing Ltd
  • Language: English;Norwegian
  • Identifier: ISSN: 2169-9380
    EISSN: 2169-9402
    DOI: 10.1029/2018JA025274
  • Source: NORA Norwegian Open Research Archives
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait