This repository contains the dataset of sunspot groups, sunspot parametrization model and latent vectors. With these data one can reproduce the results presented in the paper Parametrization of sunspot groups based on machine learning approach.
Online demo with the sunspot parametrization model is available at https://sun.njit.edu/sunspots
Clone the repository with its submodules
git clone --recursive https://github.com/observethesun/sunspot_groups.git
Folder dataset contains
- sunspot_dataset - a dataset of sunspot groups observed at the Kislovodsk Mountain Astronomical Station for the period 2010--2020;
- sunspot_group_properties.csv - a table with position, area and other properties of sunspot groups.
Read more about the dataset here.
Folder notebooks contains
- Model_training.ipynb - description of the sunspot parametrization model and model training process;
- Latent_space_exploration.ipynb - demonstration of latent features and its relation to physical properties of sunspot groups.
Finally, the folder latent_vectors contains latent vectors obtained with the sunspot parametrization model for all sunspot groups in the dataset.
To save disk space, some files are archived in zip format.
Illarionov, E., Tlatov, A. Parametrization of Sunspot Groups Based on Machine-Learning Approach. Sol Phys 297, 19 (2022). https://doi.org/10.1007/s11207-022-01955-0