摘要
对于电离层参数预测,通过长短期记忆(LSTM)的预测神经网络建模实现电离层参数的短期和日均值预测。使用逐点预测和序列预测2种方法,并采用多维预测和经验模态分解(EMD)算法优化,预测电离层参数的每小时和每天的变化规律。实验结果验证了所提优化算法在提高预测电离层参数预测精度上的可行性。
For ionospheric parameter prediction,the short-term and daily mean value prediction of ionospheric parameters was established by long short-term memory(LSTM)predictive neural network modeling.Two methods of point-by-point prediction and sequence prediction were utilized.Furthermore,in order to predict the hourly and daily changes of ionospheric parameters,the proposed scheme was optimized by multidimensional prediction and empirical mode decomposition(EMD)algorithm.Finally,the feasibility of the proposed optimization algorithm in improving the prediction accuracy of ionospheric parameters is verified.
作者
冯蕴天
吴霞
许雄
张荣庆
FENG Yuntian;WU Xia;XU Xiong;ZHANG Rongqing(State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System,Luoyang 471003,China;School of Electronics and Information Engineering,Tongji University,Shanghai 201804,China;School of Software Engineering,Tongji University,Shanghai 201804,China)
出处
《通信学报》
EI
CSCD
北大核心
2021年第4期202-206,共5页
Journal on Communications
基金
电子信息系统复杂电磁环境效应国家重点实验室课题基金资助项目(No.CEMEE2020K0104B)
国家重点研发计划基金资助项目(No.2017YFE0119300)。
