Yanfang Zheng

Prof. Dr. Yanfang Zheng


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 February 2020 in The Astrophysical Journal
Verified
Journal Article
Open access
PDF file
XLXuebao Li
Xuebao Li
YZYanfang Zheng
Yanfang Zheng
XWXinshuo Wang
Xinshuo Wang
LWLulu Wang
Lulu Wang
Space weather forecasting is very important, and the prediction of space weather, especially for solar flares, has increasingly attracted research interests with the numerous recent breakthroughs in machine learning. In this study, we propose a novel convolutional neural network (CNN) model to make binary class prediction for both ≥C-class and ≥M-class flares within 24 hr. We collect magnetogram samples of solar active regions (ARs) provided by the Space-weather Helioseismic and Magnetic Imager Active Region Patches (SHARP) data from 2010 May to 2018 September. These samples are used to construct 10 separate data sets. Then, after training, validating, and testing our model, we compare the results of our model with previous studies in several metrics, with a focus on the true skill statistic (TSS). The major results are summarized as follows. (1) We propose a method of shuffle and split cross-validation (CV) based on AR segregation, which is the first attempt to verify the validity and stability of the model in flare prediction. (2) The proposed CNN model achieves a relatively high score of TSS = 0.749 ± 0.079 for ≥M-class prediction, and TSS = 0.679 ± 0.045 for ≥C-class prediction, which is greatly improved compared with previous studies. (3) The model trained on 10 CV data sets is considerably robust and stable in making flare prediction for both ≥C class and ≥M class. Our experimental results indicate that our proposed CNN model is a highly effective method for flare forecasting, with quite excellent prediction performance.

1 November 2019 in The Astrophysical Journal
Verified
Journal Article
Open access
YZYanfang Zheng
Yanfang Zheng
XLXuebao Li
Xuebao Li
XWXinshuo Wang
Xinshuo Wang
We propose a hybrid Convolutional Neural Network (CNN) model (Model 2) and modify a popular CNN model (Model 1) to predict multiclass solar flare occurrence within 24 hr. We collect samples of solar active regions provided by the Space-weather Helioseismic and Magnetic Imager Active Region Patches data from 2010 May to 2018 September. These samples are categorized into four classes (No-flare, C, M, and X), containing 10 separate data sets. Then after training, validating, and testing our models, we compare the results with previous studies in forecast verification metrics with an emphasis on the true skill statistic (TSS). The main results are summarized as follows. (1) This is the first time that the CNN models are used to make multiclass predictions of solar flare. (2) Model 2 has better values of all statistical scores than Model 1 in every class. (3) Model 2 achieves relatively high average scores of TSS = 0.768 for No-flare class, 0.538 for C class, 0.534 for M class, and 0.552 for X class, which are the best results from the existing literatures. (4) Model 2 also can be used to make binary class flare predictions for ≥M-class major flares, and the performance yields a TSS with 0.749 ± 0.079. (5) Model 2 obtains fairly good scores in other metrics for both multiclass flare predictions and ≥M-class major flare predictions. We surmise that some crucial features extracted automatically by our models may have not been excavated before and could provide important clues for studying the mechanism of flare.

22 March 2023 in Monthly Notices of the Royal Astronomical Society
Verified
Journal Article
Open access
PDF file
YZYanfang Zheng
Yanfang Zheng
XLXuebao Li
Xuebao Li
SYShuainan Yan
Shuainan Yan
XHXusheng Huang
Xusheng Huang
HLHengrui Lou
Hengrui Lou
ZLZhe Li
Zhe Li
We develop a Hybrid Bidirectional Long and Short-Term Memory based on attention mechanism (HBiLSTM-Attention) model and a BiLSTM-Attention model for multiclass flare forecasting within 24 h. We construct a new data base containing 10 separate data sets with magnetogram images and magnetic field parameters. Based on the same data base, for the first time we compare the multiclass forecasting performance of our proposed HBiLSTM-Attention model, BiLSTM-Attention model, and three other deep-learning models based on Convolutional Neural Network (CNN-based) from two aspects of categorical performance with the true skill statistic (TSS) and probabilistic performance with the Brier skill score (BSS). The major results are as follows. (1) The TSS values of our proposed model are 0.692 ± 0.042, 0.475 ± 0.038, 0.642 ± 0.043, 0.754 ± 0.062, 0.692 ± 0.042, and 0.708 ± 0.052 for No-flare, C, M, X, ≥C, and ≥M class, respectively, which are better than those of the BiLSTM-Attention model, and much better than those of the three other CNN-based models. (2) Our proposed model achieves the scores of BSS = 0.498 ± 0.061, 0.202 ± 0.037, 0.209 ± 0.050, −0.271 ± 0.180, 0.498 ± 0.061, 0.268 ± 0.056 for No-flare, C, M, X, ≥C, and ≥M class, respectively, outperforming the other four models in every class except for X class. (3) To our knowledge, HBiLSTM-Attention is the first multiclass flare forecasting model based on magnetic field parameters and deep learning, and achieves promising prediction performance. Moreover, this is the first attempt to investigate the reliability of probabilistic prediction for multiclass flares.

12 December 2024 in The Astrophysical Journal Supplement Series
Verified
Journal Article
Open access
XLXuebao Li
Xuebao Li
XLXuefeng Li
Xuefeng Li
YZYanfang Zheng
Yanfang Zheng
TLTing Li
Ting Li
PYPengchao Yan
Pengchao Yan
XHXusheng Huang
Xusheng Huang
The existing flare prediction primarily relies on photospheric magnetic field parameters from the entire active region (AR), such as Space-Weather HMI Activity Region Patches (SHARP) parameters. However, these parameters may not capture the details of the AR evolution preceding flares. The magnetic structure within the core area of an AR is essential for predicting large solar flares. This paper utilizes the area of high photospheric free energy density (high-energy-density, hereafter HED, region) as a proxy for the AR core region. We construct two data sets: SHARP and HED data sets. The ARs contained in both data sets are identical. Furthermore, the start and end times for the same AR in both data sets are identical. We develop six models for 24 hr solar flare forecasting, utilizing SHARP and HED data sets. We then compare their categorical and probabilistic forecasting performance. Additionally, we conduct an analysis of parameter importance. The main results are as follows: (1) Among the six solar flare prediction models, the models using HED parameters outperform those using SHARP parameters in both categorical and probabilistic prediction, indicating the important role of the HED region in the flare initiation process. (2) The transformer flare prediction model stands out significantly in true skill statistic and Brier skill score, surpassing the other models. (3) In parameter importance analysis, the total photospheric free magnetic energy density (E free) within the HED parameters excels in both categorical and probabilistic forecasting. Similarly, among the SHARP parameters, the R_VALUE stands out as the most effective parameter for both categorical and probabilistic forecasting.

28 March 2024 in The Astrophysical Journal
Verified
Journal Article
Open access
TLTing Li
Ting Li
YZYanfang Zheng
Yanfang Zheng
XLXuefeng Li
Xuefeng Li
YHYijun Hou
Yijun Hou
XLXuebao Li
Xuebao Li
ACAnqin Chen
Anqin Chen
Until now, how the magnetic fields in M/X-class flaring active regions (ARs) differ from C-class flaring ARs remains unclear. Here, we calculate the key magnetic field parameters within the area of high photospheric free energy density (HED region) for 323 ARs (217 C- and 106 M/X-flaring ARs), including total photospheric free magnetic energy density E free, total unsigned magnetic flux ΦHED, mean unsigned current helicity h c , length of the polarity inversion lines L PIL with a steep horizontal magnetic gradient, etc., and compare these with flare/coronal mass ejection (CME) properties. We first show the quantitative relations among the flare intensity, the eruptive character, and ΦHED. We reveal that ΦHED is a measure for the GOES flux upper limit of the flares in a given region. For a given ΦHED, there exists the lower limit of F SXR for eruptive flares. This means that only the relatively strong flares with the large fraction of energy release compared to the total free energy are likely to generate a CME. We also find that the combinations of E free–L PIL and E free–h c present a good ability to distinguish between C-class and M/X-class flaring ARs. Using determined critical values of E free and L PIL, one predicts correctly 93 out of 106 M/X-class flaring ARs and 159 out of 217 C-class flaring ARs. The large L PIL or h c for M/X-class flaring ARs probably implies the presence of a compact current with twisted magnetic fields winding about it.

28 October 2024 in Astrophysics and Space Science
Verified
Journal Article
Closed access
PDF file
PYPengchao Yan
Pengchao Yan
XLXuebao Li
Xuebao Li
YZYanfang Zheng
Yanfang Zheng
LDLiang Dong
Liang Dong
SYShuainan Yan
Shuainan Yan
YPYexin Pan
Yexin Pan