Details

Autor(en) / Beteiligte

• Risal, N. N.
• Homam, M. J.
• Akir, R. Mat
• Sudin, Nor’aisah
• Jamil, Muhammad Mahadi Abd
• Wahab, Mohd Helmy Abd
• Ambar, Radzi

Titel

Prediction of the critical frequency of the ionospheric F2 layer using backpropagation neural network during various solar epoch and storm condition

Ist Teil von

• AIP Conference Proceedings, 2023, Vol.2564 (1)

Ort / Verlag

Melville: American Institute of Physics

Erscheinungsjahr

2023

Beschreibungen/Notizen

• This paper presents the prediction of ionospheric F2 layer critical frequencies, foF2, using a backpropagation neural network (BPNN) model during various solar activities. The Canadian Advanced Digital Ionosonde (CADI) data were collected from Universiti Tun Hussein Onn Malaysia, Johor (1.86° N, 103.80° E). This study explores the efficiency of the model in predicting foF2 under various conditions of solar activity. The model’s performance was evaluated using root mean square error (RMSE) and mean average percentage error (MAPE). The backpropagation neural network model has the best efficiency during low solar activity, with the lowest RMSE and MAPE. Overall, the BPNN model can reliably predict foF2’s actual value in a quiet condition. However, this model requires some enhancements to its prediction during storm conditions in order to yield precise foF2, which can be tremendously valuable to radio operators, navigation systems, and space control systems in both quiet and storm conditions.