A Short-Term Forecast Model of foF2 Based on Elman Neural Network

The critical frequency foF2 of the ionosphere F2 layer is one of the most important parameters of the ionosphere. Based on the Elman neural network (ENN), this paper constructs a single station forecasting model to predict foF2 one hour ahead. In order to avoid the network falling into local minimum, the model is optimized by the improved particle swarm optimization (IPSO). The input parameters used in the model include local time, seasonal information, solar cycle information and magnetic activity information. Data of the Wuhan Station from 2008 to 2016 were used to train and test the model. The prediction results of foF2 show that the root mean square error (RMSE) of the Elman neural network model is 4.30% lower than that of the back-propagation neural network (BPNN) model. The RMSE is further reduced by 8.92% after using the IPSO to optimize the model. This indicates that the Elman neural network model optimized by the improved particle swarm optimization is superior to the BP neural network and Elman neural network in the forecast of foF2 one hour ahead at Wuhan station.

[1]  Lee-Anne Williscroft,et al.  Neural networks, foF2, sunspot number and magnetic activity , 1996 .

[2]  Lee-Anne McKinnell,et al.  Neural network-based ionospheric modelling over the South African region , 2004 .

[3]  L. McKinnell,et al.  On the global model for foF2 using neural networks , 2005 .

[4]  Shen Zu-yi.  OPTIMAL HYDRAULIC TURBOGENERATORS PID GOVERNOR TUNING WITH AN IMPROVED PARTICLE SWARM OPTIMIZATION ALGORITHM , 2005 .

[5]  Biqiang Zhao,et al.  Applying artificial neural network to derive long‐term foF2 trends in the Asia/Pacific sector from ionosonde observations , 2006 .

[6]  Y. Shidama,et al.  Using a neural network to make operational forecasts of ionospheric variations and storms at Kokubunji, Japan , 2007 .

[7]  Rajat Acharya,et al.  Prediction of ionospheric total electron content using adaptive neural network with in-situ learning algorithm , 2011 .

[8]  Chen Zhou,et al.  Predicting foF2 in the China region using the neural networks improved by the genetic algorithm , 2013 .

[9]  Gangbing Song,et al.  A prediction model of short-term ionospheric foF2 based on AdaBoost , 2014 .

[10]  A. Dmitriev,et al.  Methods of analysis of geophysical data during increased solar activity , 2016, Pattern Recognition and Image Analysis.

[11]  Pornchai Supnithi,et al.  A comparison of neural network-based predictions of foF2 with the IRI-2012 model at conjugate points in Southeast Asia , 2017 .

[12]  Dean Zhao,et al.  A novel optimized GA–Elman neural network algorithm , 2017, Neural Computing and Applications.

[13]  Huchuan Lu,et al.  Deep visual tracking: Review and experimental comparison , 2018, Pattern Recognit..

[14]  Yu Xue,et al.  Energy-Storage Optimization Strategy for Reducing Wind Power Fluctuation via Markov Prediction and PSO Method , 2018 .

[15]  Shanlin Yang,et al.  Optimal load dispatch of community microgrid with deep learning based solar power and load forecasting , 2019, Energy.