Multi-dimensional Time Series Modeling of Ionospheric foF2

被引：0

作者：

Li, Zhangyi ^{[1
,2
]}

Guo, Lixin ^{[2
]}

Li, Jingchun ^{[3
]}

Wang, Benchao ^{[1
]}

Zhao, Yanan ^{[1
]}

机构：

[1] State Radio Monitoring Ctr, Shaanxi Monitoring Stn, Xian, Shaanxi, Peoples R China

[2] Xidian Univ, Sch Phys & Optoelect Engn, Xian, Shaanxi, Peoples R China

[3] State Radio Monitoring Ctr, Beijing, Peoples R China

来源：

2020 CROSS STRAIT RADIO SCIENCE & WIRELESS TECHNOLOGY CONFERENCE, CSRSWTC | 2020年

基金：

中国国家自然科学基金;

关键词：

ionosphere; F2; layer; critical frequency; time series; scikit-learn;

D O I：

10.1109/CSRSWTC50769.2020.9372525

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

A multi-dimensional time series method for modeling ionospheric foF2 is developed using the scikit-learn technique. Knowledge about the character of the foF2 is used to reduce the complexity of machine learning methods. Then, Linear regression, Bayesian ridge regression, Elastic net and SVM are chosen to predict foF2. Compared with measurements data and the conventional models, the proposed approach shows its ability to model foF2 and can greatly improve the prediction accuracy.

引用

页数：3

共 8 条

[1] Forecasting of low-latitude storm-time ionospheric foF2 using support vector machine [J].

Ban, Pan-Pan ;

Sun, Shu-Ji ;

Chen, Chun ;

Zhao, Zhen-Wei .

RADIO SCIENCE, 2011, 46

[2]

Boris S., 2019, CEUR WORKSHOP PROC

[3] Effect of solar cycle 23 in foF2 trend estimation [J].

Elias, Ana G. ;

de Haro Barbas, Blas F. ;

Shibasaki, Kiyoto ;

Souza, Jonas R. .

EARTH PLANETS AND SPACE, 2014, 66

[4]

Haralambous H, 2011, IFIP ADV INF COMM TE, V363, P306

[5] foF2 long-term trend linked to Earth's magnetic field secular variation at a station under the northern crest of the equatorial ionization anomaly [J].

Hong Pham Thi Thu ;

Amory-Mazaudier, Christine ;

Minh Le Huy ;

Elias, Ana G. .

JOURNAL OF GEOPHYSICAL RESEARCH-SPACE PHYSICS, 2016, 121 (01) :719-726

[6]

Pedregosa F, 2011, J MACH LEARN RES, V12, P2825

[7] Modeling ionospheric foF2 response during geomagnetic storms using neural network and linear regression techniques [J].

Tshisaphungo, Mpho ;

Habarulema, John Bosco ;

McKinnell, Lee-Anne .

ADVANCES IN SPACE RESEARCH, 2018, 61 (12) :2891-2903

[8] Twenty-four hour predictions of foF2 using time delay neural networks [J].

Wintoft, P ;

Cander, LR .

RADIO SCIENCE, 2000, 35 (02) :395-408

← 1 →