A Short-Term Forecast Model of foF2 Based on Elman Neural Network
Source abstract
Abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Ionosphere and magnetosphere dynamics · Earthquake Detection and Analysis · Atmospheric Ozone and Climate
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electrical and Electronic Engineering, North China Electric Power University, Beijing 102206, China
China Research Institute of Radiowave Propagation, Qingdao 266107, China
References (15)
Show source-provided references
1. Neural Networks, foF2, sunspot number and magnetic activity10.1029/96GL03472 ↗
2. Applying artificial neural network to derive long-term foF2 trends in the Asia/Pacific sector from ionosonde observations10.1029/2005JA011577 ↗
3. A comparison of neural network-based predictions of foF2 with the IRI-2012 model at conjugate points in Southeast Asia10.1016/j.asr.2017.03.023 ↗
4. On the global model for foF2 using neural networks10.1029/2004RS003223 ↗
5. Neural network-based ionospheric modelling over the South African region
6. Predicting foF2 in the China region using neural networks improved by the genetic algorithm10.1016/j.jastp.2012.09.010 ↗
7. A prediction model of short-term ionospheric foF2 based on AdaBoost10.1016/j.asr.2013.12.001 ↗
8. Deep visual tracking: Review and experimental comparison10.1016/j.patcog.2017.11.007 ↗
9. Optimal load dispatch of community microgrid with deep learning based solar power and load forecasting10.1016/j.energy.2019.01.075 ↗
10. Prediction of ionospheric total electron content using adaptive neural network with in-situ learning algorithm10.1016/j.asr.2010.08.016 ↗
11. A novel optimized GA-Elman neural network algorithm
12. Yun, P.P., Ren, Y.F., and Xun, Y. (2018). Energy-Storage optimization strategy for reducing wind power fluctuation via Markov prediction and PSO method. Energies, 11.10.3390/en11123393 ↗
13. Optimal hydraulic turbogenerators pid governor tuning with an improved particle swarm optimization algorithm
14. Using a neural network to make operational forecasts of ionospheric variations and storms at Kokubunji
15. Method of analysis of geophysical data during increased solar activity10.1134/S1054661816020103 ↗