Deep Active Learning–Based Classification of Solar Radio Spectrogram Data

The study of solar burst activity can provide early warnings for the environmental protection of the solar–terrestrial space environment. With the improvement of solar radio observation techniques, observation devices have generated enormous amounts of observation data. To solve the shortcomings of...

Full description

Saved in:
Bibliographic Details
Main Authors: Yan Liu, HongQiang Song, FaBao Yan, YanRui Su
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:The Astrophysical Journal Supplement Series
Subjects:
Online Access:https://doi.org/10.3847/1538-4365/adda30
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850087247281389568
author Yan Liu
HongQiang Song
FaBao Yan
YanRui Su
author_facet Yan Liu
HongQiang Song
FaBao Yan
YanRui Su
author_sort Yan Liu
collection DOAJ
description The study of solar burst activity can provide early warnings for the environmental protection of the solar–terrestrial space environment. With the improvement of solar radio observation techniques, observation devices have generated enormous amounts of observation data. To solve the shortcomings of time-consuming and error-prone manual recognition, researchers have begun to use deep learning to recognize and automatically classify solar radio outbursts. Deep learning will depend on a large number of labeled samples; however, the labeling of samples requires a lot of time and manual labor. This leads to low efficiency. In addition, the labeled samples are not all valuable samples, so it is necessary to improve the effectiveness of the labeled samples and select the high-value samples. The occurrence of active-learning techniques provides an opportunity to solve this problem. In this study, we developed a progressive deep convolutional generative adversarial network model. Then, we combined it with deep active learning to complete the automatic classification of solar radio spectrum data. We used solar radio spectrum data from the Chashan Observatory (CSO) of Shandong University and Learmonth Observatory in Australia. The results show that the method proposed in this paper can achieve high accuracy in the automatic recognition of solar radio spectrum data and solve the time-consuming problem of labeling a huge number of data samples. Finally, we applied the results to the CSO and realized the automatic recognition of solar radio spectral data.
format Article
id doaj-art-a9ae32ca33e5453f84c826571532bb6c
institution DOAJ
issn 0067-0049
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series The Astrophysical Journal Supplement Series
spelling doaj-art-a9ae32ca33e5453f84c826571532bb6c2025-08-20T02:43:15ZengIOP PublishingThe Astrophysical Journal Supplement Series0067-00492025-01-0127912510.3847/1538-4365/adda30Deep Active Learning–Based Classification of Solar Radio Spectrogram DataYan Liu0HongQiang Song1https://orcid.org/0000-0001-5705-661XFaBao Yan2https://orcid.org/0000-0002-4451-7293YanRui Su3Laboratory for ElectromAgnetic Detection (LEAD), Institute of Space Sciences, Shandong University , Weihai 264209, People’s Republic of China ; suyanrui@sdu.edu.cnLaboratory for ElectromAgnetic Detection (LEAD), Institute of Space Sciences, Shandong University , Weihai 264209, People’s Republic of China ; suyanrui@sdu.edu.cnLaboratory for ElectromAgnetic Detection (LEAD), Institute of Space Sciences, Shandong University , Weihai 264209, People’s Republic of China ; suyanrui@sdu.edu.cn; School of Mechanical, Electrical & Information Engineering, Shandong University , Weihai 264209, People’s Republic of China; Shandong Key Laboratory of Intelligent Electronic Packaging, Testing and Application, Shandong University , Weihai 264209, People’s Republic of ChinaLaboratory for ElectromAgnetic Detection (LEAD), Institute of Space Sciences, Shandong University , Weihai 264209, People’s Republic of China ; suyanrui@sdu.edu.cn; School of Mechanical, Electrical & Information Engineering, Shandong University , Weihai 264209, People’s Republic of China; Shandong Key Laboratory of Intelligent Electronic Packaging, Testing and Application, Shandong University , Weihai 264209, People’s Republic of ChinaThe study of solar burst activity can provide early warnings for the environmental protection of the solar–terrestrial space environment. With the improvement of solar radio observation techniques, observation devices have generated enormous amounts of observation data. To solve the shortcomings of time-consuming and error-prone manual recognition, researchers have begun to use deep learning to recognize and automatically classify solar radio outbursts. Deep learning will depend on a large number of labeled samples; however, the labeling of samples requires a lot of time and manual labor. This leads to low efficiency. In addition, the labeled samples are not all valuable samples, so it is necessary to improve the effectiveness of the labeled samples and select the high-value samples. The occurrence of active-learning techniques provides an opportunity to solve this problem. In this study, we developed a progressive deep convolutional generative adversarial network model. Then, we combined it with deep active learning to complete the automatic classification of solar radio spectrum data. We used solar radio spectrum data from the Chashan Observatory (CSO) of Shandong University and Learmonth Observatory in Australia. The results show that the method proposed in this paper can achieve high accuracy in the automatic recognition of solar radio spectrum data and solve the time-consuming problem of labeling a huge number of data samples. Finally, we applied the results to the CSO and realized the automatic recognition of solar radio spectral data.https://doi.org/10.3847/1538-4365/adda30Solar radio telescopes
spellingShingle Yan Liu
HongQiang Song
FaBao Yan
YanRui Su
Deep Active Learning–Based Classification of Solar Radio Spectrogram Data
The Astrophysical Journal Supplement Series
Solar radio telescopes
title Deep Active Learning–Based Classification of Solar Radio Spectrogram Data
title_full Deep Active Learning–Based Classification of Solar Radio Spectrogram Data
title_fullStr Deep Active Learning–Based Classification of Solar Radio Spectrogram Data
title_full_unstemmed Deep Active Learning–Based Classification of Solar Radio Spectrogram Data
title_short Deep Active Learning–Based Classification of Solar Radio Spectrogram Data
title_sort deep active learning based classification of solar radio spectrogram data
topic Solar radio telescopes
url https://doi.org/10.3847/1538-4365/adda30
work_keys_str_mv AT yanliu deepactivelearningbasedclassificationofsolarradiospectrogramdata
AT hongqiangsong deepactivelearningbasedclassificationofsolarradiospectrogramdata
AT fabaoyan deepactivelearningbasedclassificationofsolarradiospectrogramdata
AT yanruisu deepactivelearningbasedclassificationofsolarradiospectrogramdata