A Contrastive Learning Approach to Auroral Identification and Classification

  title={A Contrastive Learning Approach to Auroral Identification and Classification},
  author={Jeremiah W. Johnson and Swathi Hari and Donald L. Hampton and Hyunju K. Connor and Amy M Keesee},
  journal={2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)},
Unsupervised learning algorithms are beginning to achieve accuracies comparable to their supervised counterparts on benchmark computer vision tasks, but their utility for practical applications has not yet been demonstrated. In this work, we present a novel application of unsupervised learning to the task of auroral image classification. Specifically, we modify and adapt the Simple framework for Contrastive Learning of Representations (SimCLR) algorithm to learn representations of auroral… 

Figures and Tables from this paper



Auroral Image Classification With Deep Neural Networks

Results from a study of automatic aurora classification using machine learning techniques are presented, which considers seven auroral subclasses: breakup, colored, arcs, discrete, patchy, edge, and faint.

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

This study paves the way for easy automatic classification of all auroral images from the THEMIS all‐sky imager chain, and believes 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.

A Simple Framework for Contrastive Learning of Visual Representations

It is shown that composition of data augmentations plays a critical role in defining effective predictive tasks, and introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning.

Automatic classification of auroral images in substorm studies

Millions of auroral images are captured every year by ground-based imagers. Even though the auroral appearance or "type" yields relevant information about the physical processes in the ionosphere and

Automatic Auroral Detection in Color All-Sky Camera Images

A method for performing automated classification of ASC images into three mutually exclusive classes: aurora, no Aurora, and cloudy is described, which reduces the amount of data to be processed, but also facilitates in building statistical models linking the magnetic fluctuations and auroral activity helping to get a step closer to forecasting Auroral activity.

Diurnal auroral occurrence statistics obtained via machine vision

This paper describes machine vision techniques that have been developed for use on large auroral image data sets and presents the results of application to a 350000 image subset of the CANOPUS Gillam ASI in the years 1993–1998.

Unsupervised Feature Learning via Non-parametric Instance Discrimination

This work forms this intuition as a non-parametric classification problem at the instance-level, and uses noise-contrastive estimation to tackle the computational challenges imposed by the large number of instance classes.

CNN Features Off-the-Shelf: An Astounding Baseline for Recognition

A series of experiments conducted for different recognition tasks using the publicly available code and model of the OverFeat network which was trained to perform object classification on ILSVRC13 suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.

Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

This paper proposes an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons, and uses a swapped prediction mechanism where it predicts the cluster assignment of a view from the representation of another view.

Analysis of Auroral Images: Detection and Tracking

The aurora provides us with a powerful tool for studying the near-Earth space. Processes in the magnetosphere and the ionosphere shape the visual appearance of the aurora, which itself is caused by