Artificial Intelligence Approach for Classifying Images of Upper-Atmospheric Transient Luminous Events

TL;DR

This paper introduces an AI method to automatically classify images of rare upper-atmospheric lightning events, using deep learning models like ResNet and Vision Transformers.

Contribution

The novel contribution is applying transfer learning and pre-trained CNNs to classify TLE images, comparing performance across architectures.

Findings

ResNet50 achieved the highest classification accuracy for TLE images.

A trade-off exists between model accuracy and execution time.

Image augmentation and preprocessing improved model performance.

Abstract

Transient Luminous Events (TLEs) are short-lived, upper-atmospheric optical phenomena associated with thunderstorms. Their rapid and random occurrence makes manual classification laborious and time-consuming. This study presents an effective approach to automating the classification of TLEs using state-of-the-art Convolutional Neural Networks (CNNs) and a Vision Transformer (ViT). The ViT architecture and four different CNN architectures, namely, ResNet50, ResNet18, GoogLeNet, and SqueezeNet, are employed and their performance is evaluated based on their accuracy and execution time. The models are trained on a dataset that was augmented using rotation, translation, and flipping techniques to increase its size and diversity. Additionally, the images are preprocessed using bilateral filtering to enhance their quality. The results show high classification accuracy across all models, with ResNet50 achieving the highest accuracy. However, a trade-off is observed between accuracy and execution time, which should be considered based on the specific requirements of the task. This study demonstrates the feasibility and effectiveness of using transfer learning and pre-trained CNNs for the automated classification of TLEs.

Figures