Identifying and Tracking Solar Magnetic Flux Elements with Deep Learning

TL;DR

This paper introduces SolarUnet, a deep learning-based method for identifying and tracking solar magnetic flux elements in magnetogram data, offering faster performance and comparable accuracy to existing tools.

Contribution

The paper presents SolarUnet, a novel deep learning approach using a U-shaped CNN for solar magnetic feature identification and tracking, improving speed and complementing existing methods.

Findings

SolarUnet is faster than SWAMIS while maintaining similar accuracy.

SolarUnet effectively tracks long-lifetime magnetic features.

The method is applicable to observational data from the Goode Solar Telescope.

Abstract

Deep learning has drawn a lot of interest in recent years due to its effectiveness in processing big and complex observational data gathered from diverse instruments. Here we propose a new deep learning method, called SolarUnet, to identify and track solar magnetic flux elements or features in observed vector magnetograms based on the Southwest Automatic Magnetic Identification Suite (SWAMIS). Our method consists of a data pre-processing component that prepares training data from the SWAMIS tool, a deep learning model implemented as a U-shaped convolutional neural network for fast and accurate image segmentation, and a post-processing component that prepares tracking results. SolarUnet is applied to data from the 1.6 meter Goode Solar Telescope at the Big Bear Solar Observatory. When compared to the widely used SWAMIS tool, SolarUnet is faster while agreeing mostly with SWAMIS on feature size and flux distributions, and complementing SWAMIS in tracking long-lifetime features. Thus, the proposed physics-guided deep learning-based tool can be considered as an alternative method for solar magnetic tracking.