On the Prediction of foF2 Using Artificial Neural Networks
Lists
Only you see this
Abstract
Abstract A method to predict f o F 2 one hour ahead using neural network is developed. Based on the time variation characteristics of f o F 2 , six parameters are determined as inputs by time series analysis, which are the present observation of f o F 2 , f o F 2 one‐day before at the same time as the predicted one, the seven‐day average f o F 2 before the predicted hour and the current hour, the first difference of f o F 2 and time of day. The output is the f o F 2 one hour ahead. During high solar activity period, the average relative error is less than 6 percent and RMS less than 0.6 MHz, while during solar minimum, the average relative error is less than 10 percent and RMS less than 0.5 MHz.
BibTeX
@inproceedings{kong2009prediction,
author = {Qing‐Yan Kong and Wenyu Liu and J. Z. Fan and Peinan Jiao and Jing Feng and Junjiang Wang},
title = {{On the Prediction of <i>f</i><sub>o</sub>F<sub>2</sub> Using Artificial Neural Networks}},
booktitle = {Chinese},
year = {2009},
doi = {10.1002/cjg2.1375},
}Loading related content...