Automatic analysis of magnetograms for identification and classification of active regions using Deep Learning

Abstract

Some phenomena that occur in the Sun have consequences on Earth. Among these phenomena, solar flares release large amounts of radiation and energy that impact on Earth's life and technological systems. These flares usually come from sunspots, which derive from solar magnetic activities. One strategy to predict solar flares is to identify active regions, i. e., a group of sunspots with a high potential to cause solar flares. This paper reports the use of the deep learning technique to identify and classify active regions from magnetogram analysis. To achieve these tasks, we created a dataset with magnetograms and performed tests to choose the best deep learning models for the identification and classification of active regions. The results of the best models reached accuracies higher than 80% for both the identification and classification tasks. Based on these results, we implemented a system in Python to automate the complete identification and classification process, also reported in this paper.

Sunspot Detection Using YOLOv5 in Spectroheliograph H-Alpha Images

“…Oliveira et al [28] proposed a deep learning technique in Python for the detection and classification of active regions. Several deep learning models were taken into account in order to compare the results between them and find the one(s) with the best accuracy.…”

“…Table 1. Classification of the solar flares according to their peak flux, in W/m 2 (Oliveira et al [28]). The dataset was obtained from The Helioviewer Project (2019) (https://helioviewer.…”

Automatic fabric defect detection employing deep learning

“…Deep learning is a leading machine learning technique which use artificial neural networks; it tends to be able to handle higher levels of abstracting data by using horizontal hierarchical architectures [8]. This approach is recent and has been largely used in many areas of artificial intelligence, such as health care, automotive industry, natural language processing, document analysis and recognition [9]- [12]. Deep neuron networks (DNNs) for image classification generally combine layers of convolutional neural networks (CNNs) and fully connected artificial neurons stacked to satisfy overlaying vision areas.…”