基于神经网络技术的f0F2短期预报方法

A short-term f_0F_2 forecasting method based on neural network techniques

利用神经网络技术并考虑太阳和地磁活动对电离层的影响,提出一种提前1h预报电离层临界频率f0F2的方法。网络的输入包括时间、季节、地磁指数、太阳黑子数。太阳射电流量F10.7以及f0F2偏离月中值的一阶和二阶有限差和相对偏差。分别用广州和兰州站的历史数据进行检验,预报结果与观测数据符合得较好,比国际参考电离层更具有实用性。

By using artificial neural network and considering the effects of the solar and geomagnetic activities on the ionosphere, this paper brought out a method of forecasting the ionospheric critical frequency, f0F2 for an hour in advance. The inputs of the network include time, season, geomagnetic indices such as Kp, ap, Dst, sunspot number, solar radio flux F10.7, and the first and the second differences and the relative discrepancy of the deviation of f0F2 from its monthly-median value. An example was presented by using the ionospheric sounding data at Guangzhou and Lanzhou between 1981 and 1991, respectively. The results indicate that the predicted f0F2 has good agreement with observed data and is superior to that of IRI（International Reference Ionosphere）model.