| A novel solar flare forecast model with deep convolution neural network and one-against-rest approach | |
Zhang, Shunhuang1; Zheng, Yanfang1; Li, Xuebao1; Ye, Hongwei1; Dong L(董亮)2,3 ; Huang, Xusheng1; Yan, Pengchao1; Li, Xuefeng1; Wei, Jinfang1; Xiang, Changtian1; Wang, Xiaotian1; Pan, Yexin4
| |
| 发表期刊 | ADVANCES IN SPACE RESEARCH
 |
| 2024-10-01 | |
| 卷号 | 74期号:7页码:3467-3480 |
| DOI | 10.1016/j.asr.2024.06.035 |
| 产权排序 | 第2完成单位 |
| 收录类别 | SCI |
| 关键词 | Active regions Magnetic fields Solar flare prediction Deep learning |
| 摘要 | We present a novel deep Convolutional Neural Network model with one-against-rest approach (OAR-CNN) and modify the hybrid Convolutional Neural Network (H-CNN) model of Zheng et al. (2019) for multiclass flare prediction to forecast whether an active region generates multiclass flare within 24 h. Additionally, in the OAR-CNN and H-CNN models, we employ the decision strategies of majority voting and probability threshold, respectively, comparing the prediction outcomes of these two strategies. Our models undergo training and testing on the same 10 cross-validation datasets as employed by Zheng et al. (2019), and then compare the results with previous studies using forecast verification metrics, with a focus on the true skill statistic (TSS). The major results are summarized as follows. (1) This is the first attempt to utilize the decision strategies of majority voting and probability threshold in the OAR-CNN model for multiclass solar flare prediction. (2) In both the OAR-CNN and H-CNN models, the predictive results with the probability threshold decision strategy are higher than those with majority voting across all six classes (i.e., No-flare, C, M, X, C, and M class), except for a slight decrease in the C class in the OAR-CNN model. (3) The OAR-CNN and modified H-CNN models with the probability threshold decision strategy demonstrate comparable statistical scores across all categories and outperform previous studies. (4) In the prediction of four-class flare, our proposed OAR-CNN model with the probability threshold decision strategy achieves relatively high mean TSS scores of 0.744, 0.429, 0.567, and 0.630 for No-flare, C, M, and X class, respectively, surpassing or comparable to results from prior studies. Furthermore, our model achieves high TSS scores of 0.744 +/- 0.042 for C-class and 0.764 +/- 0.089 for M-class predictions. (c) 2024 COSPAR. Published by Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies. |
| 资助项目 | National Natural Science Foundation of China[11703009]; National Natural Science Foundation of China[11803010]; Natural Science Foundation of Jiangsu Province, China[BK20170566]; Natural Science Foundation of Jiangsu Province, China[BK20201199]; Qing Lan Project; National Natural Science Astronomy Joint Fund[U2031133]; Kunming Foreign (International) Cooperation Base Project[GHJD-2021022] |
| 项目资助者 | National Natural Science Foundation of China[11703009, 11803010] ; Natural Science Foundation of Jiangsu Province, China[BK20170566, BK20201199] ; Qing Lan Project ; National Natural Science Astronomy Joint Fund[U2031133] ; Kunming Foreign (International) Cooperation Base Project[GHJD-2021022] |
| 语种 | 英语 |
| 学科领域 | 天文学 ; 太阳与太阳系 |
| 文章类型 | Article |
| 出版者 | ELSEVIER SCI LTD |
| 出版地 | 125 London Wall, London, ENGLAND |
| ISSN | 0273-1177 |
| URL | 查看原文 |
| WOS记录号 | WOS:001298102000001 |
| WOS研究方向 | Engineering ; Astronomy & Astrophysics ; Geology ; Meteorology & Atmospheric Sciences |
| WOS类目 | Engineering, Aerospace ; Astronomy & Astrophysics ; Geosciences, Multidisciplinary ; Meteorology & Atmospheric Sciences |
| 关键词[WOS] | SPACE-WEATHER |
| 引用统计 | |
| 文献类型 | 期刊论文 |
| 版本 | 出版稿 |
| 条目标识符 | http://ir.ynao.ac.cn/handle/114a53/27579 |
| 专题 | 射电天文研究组 |
| 作者单位 | 1.School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212100, China; 2.Yunnan Astronomical Observatory, Chinese Academy of Sciences, Kunming 650216, China; 3.Yunnan Sino-Malaysian International Joint Laboratory of HF-VHF Advanced Radio Astronomy Technology, Kunming 650216, China; 4.MailBox 5111, Beijing 100094, China; 5.Jiangsu Univ Sci & Technol, Sch Comp Sci, Zhenjiang 212100, Peoples R China; 6.Chinese Acad Sci, Yunnan Astron Observ, Kunming 650216, Peoples R China; 7.Yunnan Sino Malaysian Int Joint Lab HF VHF Adv Rad, Kunming 650216, Peoples R China; 8.MailBox 5111, Beijing 100094, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Shunhuang,Zheng, Yanfang,Li, Xuebao,et al. A novel solar flare forecast model with deep convolution neural network and one-against-rest approach[J]. ADVANCES IN SPACE RESEARCH,2024,74(7):3467-3480. |
| APA | Zhang, Shunhuang.,Zheng, Yanfang.,Li, Xuebao.,Ye, Hongwei.,董亮.,...&Pan, Yexin.(2024).A novel solar flare forecast model with deep convolution neural network and one-against-rest approach.ADVANCES IN SPACE RESEARCH,74(7),3467-3480. |
| MLA | Zhang, Shunhuang,et al."A novel solar flare forecast model with deep convolution neural network and one-against-rest approach".ADVANCES IN SPACE RESEARCH 74.7(2024):3467-3480. |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
| A novel solar flare （2495KB） | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 请求全文 | |
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
修改评论