SHORT-TERM SOLAR FLARE PREDICTION USING MULTIRESOLUTION PREDICTORS

被引：36

作者：

Yu, Daren ^{[1
]}

Huang, Xin ^{[1
]}

Hu, Qinghua ^{[1
]}

Zhou, Rui ^{[1
]}

Wang, Huaning ^{[2
]}

Cui, Yanmei ^{[3
]}

机构：

[1] Harbin Inst Technol, Harbin, Heilongjiang Pr, Peoples R China

[2] Natl Astron Observ, Beijing, Peoples R China

[3] Ctr Space Sci & Appl Res, Beijing, Peoples R China

来源：

ASTROPHYSICAL JOURNAL | 2010年 / 709卷 / 01期

基金：

中国国家自然科学基金;

关键词：

methods: statistical; Sun: activity; Sun: flares; Sun: magnetic fields; Sun: photosphere; MAGNETIC-FIELD PROPERTIES; QUIET ACTIVE REGIONS; PRODUCTIVITY; MODEL; CLASSIFICATION; SPECTRUM; GRADIENT; ENERGY; LENGTH;

D O I：

10.1088/0004-637X/709/1/321

中图分类号：

P1 [天文学];

学科分类号：

0704 ;

摘要：

Multiresolution predictors of solar flares are constructed by a wavelet transform and sequential feature extraction method. Three predictors-the maximum horizontal gradient, the length of neutral line, and the number of singular points-are extracted from Solar and Heliospheric Observatory/Michelson Doppler Imager longitudinal magnetograms. A maximal overlap discrete wavelet transform is used to decompose the sequence of predictors into four frequency bands. In each band, four sequential features-the maximum, the mean, the standard deviation, and the root mean square-are extracted. The multiresolution predictors in the low-frequency band reflect trends in the evolution of newly emerging fluxes. The multiresolution predictors in the high-frequency band reflect the changing rates in emerging flux regions. The variation of emerging fluxes is decoupled by wavelet transform in different frequency bands. The information amount of these multiresolution predictors is evaluated by the information gain ratio. It is found that the multiresolution predictors in the lowest and highest frequency bands contain the most information. Based on these predictors, a C4.5 decision tree algorithm is used to build the short-term solar flare prediction model. It is found that the performance of the short-term solar flare prediction model based on the multiresolution predictors is greatly improved.

引用

页码：321 / 326

页数：6

共 50 条

[21] Short-Term Traffic Prediction Using Long Short-Term Memory Neural Networks
Abbas, Zainab
Al-Shishtawy, Ahmad
Girdzijauskas, Sarunas
Vlassov, Vladimir
[J]. 2018 IEEE INTERNATIONAL CONGRESS ON BIG DATA (IEEE BIGDATA CONGRESS), 2018, : 57 - 65
[22] Solar cycle prediction using a long short-term memory deep learning model
Qi-Jie Wang
Jia-Chen Li
Liang-Qi Guo
[J]. Research in Astronomy and Astrophysics, 2021, 21 (01) : 121 - 128
[23] Solar cycle prediction using a long short-term memory deep learning model
Wang, Qi-Jie
Li, Jia-Chen
Guo, Liang-Qi
[J]. RESEARCH IN ASTRONOMY AND ASTROPHYSICS, 2021, 21 (01)
[24] Dictionary Learning for Short-term Prediction of Solar PV Production
Shamsi, Pourya
Marsousi, Mahdi
Xie, Huaiqi
Fries, William
Shaffer, Chelsea
[J]. 2015 IEEE POWER & ENERGY SOCIETY GENERAL MEETING, 2015,
[25] Structure of the Program of Short-term Prediction of Powerful Solar Flares
V.Maksimov
D.Prosovetsky
[J]. 空间科学学报, 2005, (05) : 329 - 332
[26] Short-Term Solar Power Forecasting and Uncertainty Analysis Using Long and Short-Term Memory
Zhang, Wei
[J]. JOURNAL OF NANOELECTRONICS AND OPTOELECTRONICS, 2021, 16 (12) : 1948 - 1955
[27] Intermittence of the short-term periodicities of the flare index
Rybák, J
Özgüç, A
Ataç, T
Sözen, E
[J]. INFLUENCE OF THE SUN'S RADIATION AND PARTICLES ON THE EARTH'S ATMOSPHERE AND CLIMATE, 2005, 35 (03): : 406 - 409
[28] Bi-model short-term solar irradiance prediction using support vector regressors
Cheng, Hsu-Yung
Yu, Chih-Chang
Lin, Sian-Jing
[J]. ENERGY, 2014, 70 : 121 - 127
[29] Short-Term Solar Irradiance Prediction with a Hybrid Ensemble Model Using EUMETSAT Satellite Images
Thaker, Jayesh
Hoeller, Robert
Kapasi, Mufaddal
[J]. ENERGIES, 2024, 17 (02)
[30] Enhanced Short-Term Prediction of Solar Radiation Using HRNet Model With Geostationary Satellite Data
Ahn, Hyojung
Yu, Jeongmin
Ko, Jonghan
Yeom, Jong-Min
[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2024, 21

← 1 2 3 4 5 →