Aurora Classification in All-Sky Images via CNN–Transformer

Abstract

An aurora is a unique geophysical phenomenon with polar characteristics that can be directly observed with the naked eye. It is the most concentrated manifestation of solar–terrestrial physical processes (especially magnetospheric–ionospheric interactions) in polar regions and is also the best window for studying solar storms. Due to the rich morphological information in aurora images, people are paying more and more attention to studying aurora phenomena from the perspective of images. Recently, some machine learning and deep learning methods have been applied to this field and have achieved preliminary results. However, due to the limitations of these learning models, they still need to meet the requirements for the classification and prediction of auroral images regarding recognition accuracy. In order to solve this problem, this study introduces a convolutional neural network transformer solution based on vision transformers. Comparative experiments show that the proposed method can effectively improve the accuracy of aurora image classification, and its performance has exceeded that of state-of-the-art deep learning methods. The experimental results show that the algorithm presented in this study is an effective instrument for classifying auroral images and can provide practical assistance for related research.

Sky Image Classification Based Solar Power Prediction Using CNN

“…AlexNet gets a 256-by-256 RGB (3-channel) image. 60 million parameters, 650,000 neurons [19]. Dropout layers reduce overtraining.…”

Aurora retrieval in all-sky images based on hash vision transformer

“…However, manual operations introduce artificial errors and labor noise, affecting image quality and research accuracy. Moreover, conventional approaches rely on the human visual system [4] , which increases human consumption and is time-consuming. Therefore, it is necessary to design an automatic retrieval algorithm without any human intervention, which provides convenience to physicists in selecting their interested auroras from all-sky images.…”

Random Forest Classification and Ionospheric Response to Solar Flares: Analysis and Validation

“…The current research in the fields of SFs, CMEs, and the ionosphere is focused on the application of machine learning (ML) techniques. Classification methods have been employed in the classification of lighting waveforms [8], as well as in the classification of radar returns [9][10][11][12][13] and auroral image classification [14,15]. Similar to the pre-processing phase of VLF data analysis, manual radar return classification entails human intervention and is a labor-intensive procedure [9].…”