Analysing AIA Flare Observations using Convolutional Neural Networks

Abstract

In order to efficiently analyse the vast amount of data generated by solar space missions and ground-base instruments, modern machine learning techniques such as decision trees, support vector machines (SVMs) and neural networks can be very useful. In this paper we present initial results from using a convolutional neural network (CNN) to analyse observations from the Atmospheric Imaging Assembly (AIA) in the 1600A wavelength. The data is pre-processed to locate flaring regions where flare ribbons are visible in the observations. The CNN is created and trained to automatically analyse the shape and position of the flare ribbons, by identifying whether each image belongs into one of four classes: two-ribbon flare, compact/circular ribbon flare, limb flare or quiet Sun, with the final class acting as a control for any data included in the training or test sets where flaring regions are not present. The network created can classify flare ribbon observations into any of the four classes with a final accuracy of 94%. Initial results show that most of the images are correctly classified with the compact flare class being the only class where accuracy drops below 90% ad some observations are wrongly classified as belonging to the limb class.

9 pages, 4 figures. To be published in Frontiers in Astronomy and Space Science as part of the Machine Learning in Heliophysics research topic

References in corpus (8)

• An Observational Overview of Solar Flares
• Solar Flare Prediction Using SDO/HMI Vector Magnetic Field Data with a Machine-Learning Algorithm
• Heliophysics Event Knowledgebase for the Solar Dynamics Observatory and Beyond
• A Database of Flare Ribbon Properties From Solar Dynamics Observatory I: Reconnection Flux
• The Relation between Solar Eruption Topologies and Observed Flare Features I: Flare Ribbons
• Evolution of Flare Ribbons, Electric Currents and Quasi-separatrix Layers During an X-class Flare
• Fast Solar Image Classification Using Deep Learning and its Importance for Automation in Solar Physics
• A secondary fan-spine magnetic structure in active region 11897

Cited by in corpus (2)

• Unsupervised classification of simulated magnetospheric regions
• The Development of Spatial Attention U-Net for The Recovery of Ionospheric Measurements and The Extraction of Ionospheric Parameters