NSSC OpenIR
LSTM神经网络在太阳F_(10.7)射电流量中期预报中的应用
Alternative TitleApplication of LSTM Neural Network in F_(10.7) Solar Radio Flux Mid-term Forecast
杨旭; 朱亚光; 杨升高; 王西京; 钟秋珍
Source Publication空间科学学报
2020
Volume40Issue:2Pages:176-185; AR:0254-6124(2020)40:2<176:LSJWLZ>2.0.TX;2-6
ISSN0254-6124
Language中文
KeywordLSTM神经网络 中期预报 F_(10.7) F_(10.7) LSTM neural network Medium-term forecast
AbstractF_(10.7)指数作为大气密度经验模型的重要输入参量,其预报精度直接影响航天器轨道预报精度.研究发现,太阳活动表现出长时间尺度上平均11年和中短时间尺度平均27天的周期性变化特征.依据这一观测事实,基于长短期记忆单元(Long Short-term Memory, LSTM)递归神经网络方法进行F_(10.7)指数未来27天的中期预报.利用一个连续长时段F_(10.7)数据作为训练数据,构建LSTM神经网络训练和预测模型,分别预测太阳活动高低年未来27天的F_(10.7)指数.结果表明,太阳活动高年的第27天F_(10.7)指数预报平均相对误差最优可达10%以内,低年最优可达2%以内.
Other AbstractThe F_(10.7) index is an important input parameter for the empirical models of atmospheric density, and its prediction accuracy directly affects the accuracy of spacecraft orbit prediction. The solar activity exhibited an average of 11 years on a long-term scale and a 27-day periodic variation on a short-term scale. Based on this observational fact, a 1 Long and Short Term Memory (LSTM) recurrent neural network method is proposed to conduct the mid-term forecast of F_(10.7) index for the next 27 days. Using a continuous long period of F_(10.7) data as training data, the LSTM neural network training is constructed, and the upper and lower bounds of model parameters based on empirical formula are determined. The method of trial and error is used to select the optimal model parameters, and the prediction models to predict solar activity of high and low years F_(10.7) index in the next 27 days are constructed. The results show that the average relative error of the 27th day F_(10.7) index forecast for solar activity in the high year can reach about 10%,and can reach 2% or less in the low year. In 1998, the correlation coefficient between the predicted value of the F_(10.7) index on the 27th day and the measured value was 0.60.
Indexed ByCSCD
Citation statistics
Document Type期刊论文
Identifierhttp://ir.nssc.ac.cn/handle/122/7406
Collection中国科学院国家空间科学中心
Affiliation1.杨旭, 西安卫星测控中心, 宇航动力学国家重点实验室, 西安, 陕西 710043, 中国.
2.朱亚光, 西安卫星测控中心, 宇航动力学国家重点实验室, 西安, 陕西 710043, 中国.
3.杨升高, 西安卫星测控中心, 宇航动力学国家重点实验室, 西安, 陕西 710043, 中国.
4.王西京, 西安卫星测控中心, 宇航动力学国家重点实验室, 西安, 陕西 710043, 中国.
5.钟秋珍, 中国科学院国家空间科学中心, 北京 100190, 中国.
6.Yang Xu, Xi'an Satellite Control Center, State Key Laboratory of Astronautic Dynamics, Xi'an, Shaanxi 710043, China.
7.Zhu Yaguang, Xi'an Satellite Control Center, State Key Laboratory of Astronautic Dynamics, Xi'an, Shaanxi 710043, China.
8.Yang Shenggao, Xi'an Satellite Control Center, State Key Laboratory of Astronautic Dynamics, Xi'an, Shaanxi 710043, China.
9.Wang Xijing, Xi'an Satellite Control Center, State Key Laboratory of Astronautic Dynamics, Xi'an, Shaanxi 710043, China.
10.Zhong Qiuzhen, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China.
11.yang_xu126@126.com
Recommended Citation
GB/T 7714
杨旭,朱亚光,杨升高,等. LSTM神经网络在太阳F_(10.7)射电流量中期预报中的应用[J]. 空间科学学报,2020,40(2):176-185; AR:0254-6124(2020)40:2<176:LSJWLZ>2.0.TX;2-6.
APA 杨旭,朱亚光,杨升高,王西京,&钟秋珍.(2020).LSTM神经网络在太阳F_(10.7)射电流量中期预报中的应用.空间科学学报,40(2),176-185; AR:0254-6124(2020)40:2<176:LSJWLZ>2.0.TX;2-6.
MLA 杨旭,et al."LSTM神经网络在太阳F_(10.7)射电流量中期预报中的应用".空间科学学报 40.2(2020):176-185; AR:0254-6124(2020)40:2<176:LSJWLZ>2.0.TX;2-6.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[杨旭]'s Articles
[朱亚光]'s Articles
[杨升高]'s Articles
Baidu academic
Similar articles in Baidu academic
[杨旭]'s Articles
[朱亚光]'s Articles
[杨升高]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[杨旭]'s Articles
[朱亚光]'s Articles
[杨升高]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.