Date of Award
Master of Science (MS)
Machine learning., Neural networks (Computer science), Auroras., Image analysis.
Auroras are a dynamically evolving phenomenon. Different auroral forms are correlated with various physical processes in the magnetosphere and ionosphere system. Millions of auroral images are captured every year by the modern ground-based All-Sky Imager(ASI). In dealing with data from ASI, machine learning techniques play a critical scientific role, facilitating both efficient searches and statistical studies. In this work, we manually label night-side auroral images from various Time History of Events and Macroscale Interactions during Substorms (THEMIS) all-sky imager based on the sky conditions; the labels are clear sky with auroras, cloudy with the moon, cloudy, clear-sky with the moon, and clear-sky. This is an interdisciplinary work between space science and computer science disciplines. A deep convolutional neural network is developed with auroral images as input for training. The deep learning model is trained to classify the images into five classes based on the extracted features. The central aspect we are concerned with is what the network learns about auroral features and how it learns as it convolves into deeper iterations. In comparison with conventional techniques, the proposed model achieves a high classification accuracy.
Herga, Shwetha, "Feature extraction for classification of auroral images" (2020). Theses. 324.