A Neural-Network Technique for Recognition of Filaments in Solar Images

TL;DR

This paper presents a neural-network-based method for automated recognition of solar filaments in hydrogen H-alpha images, capable of learning from limited data and recognizing multiple filaments despite background variations.

Contribution

The paper introduces a neural-network technique that learns from few labeled image fragments to recognize multiple solar filaments in variable backgrounds.

Findings

Neural network successfully recognizes filaments with minimal training data.

The method handles background brightness variations caused by atmospheric distortions.

It extends to recognizing multiple filaments in a single image fragment.

Abstract

We describe a new neural-network technique developed for an automated recognition of solar filaments visible in the hydrogen H-alpha line full disk spectroheliograms. This technique allows neural networks learn from a few image fragments labelled manually to recognize the single filaments depicted on a local background. The trained network is able to recognize filaments depicted on the backgrounds with variations in brightness caused by atmospherics distortions. Despite the difference in backgrounds in our experiments the neural network has properly recognized filaments in the testing image fragments. Using a parabolic activation function we extend this technique to recognize multiple solar filaments which may appear in one fragment.