Forecasting the Ionospheric f0F2 Parameter One Hour in Advance Using Recurrent Neural Network
- DOI
- 10.2991/cnci-19.2019.37How to use a DOI?
- Keywords
- Ionospheric critical frequency, modeling and forecasting, recurrent neural networks
- Abstract
It is difficult to forecast the state of ionosphere because the time-varying characteristics. Using recurrent neural network(RNN) one hour ahead prediction of the critical parameter of ionospheric F2 layer(f0F2) is realized. The prediction model is developed based on 11 years (from 2005 to 2016) of data measured from ionospheric vertical stations in China. By analyzing time series correlation of f0F2 and solar-terrestrial and geomagnetic activities, several parameters are selected as inputs. Though training the RNN model, the forecasting values one hour ahead can be obtained. For this time-series problem, the predicted ability of RNN is better than Artificial Neural Network(ANN) and the autocorrelation method by comparing the results of three different algorithms.
- Copyright
- © 2019, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Zhe Lv AU - Changjun Yu AU - Aijun Liu PY - 2019/05 DA - 2019/05 TI - Forecasting the Ionospheric f0F2 Parameter One Hour in Advance Using Recurrent Neural Network BT - Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019) PB - Atlantis Press SP - 249 EP - 258 SN - 2352-538X UR - https://doi.org/10.2991/cnci-19.2019.37 DO - 10.2991/cnci-19.2019.37 ID - Lv2019/05 ER -