Identifying and Tracking Solar Magnetic Flux Elements with Deep Learning

Haodi Jiang1,2, Jiasheng Wang1,3,4, Chang Liu1,3,4, Ju Jing1,3,4, Hao Liu1,2, Jason T. L. Wang1,2, and Haimin Wang1,3,4

1. Institute for Space Weather Sciences, New Jersey Institute of Technology
2. Department of Computer Science, New Jersey Institute of Technology
3. Big Bear Solar Observatory, New Jersey Institute of Technology
4. Center for Solar-Terrestrial Research, New Jersey Institute of Technology

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.

Source Code and Data

ยป Click here to download the SolarUnet tool and data in the Jupyter Notebook. Data can also be downloaded from here.

Reference

Identifying and Tracking Solar Magnetic Flux Elements with Deep Learning. Jiang, H., Wang, J., Liu, C., Jing, J., Liu, H., Wang, J. T. L., Wang, H., ApJS., 250:5, 2020   [GitHub]