Prediction of the maximum observed frequency of the ionospheric HF radio channel using the method of artificial neural networks

Бархатов, Н. А.; Ревунов, С. Е.; Vertogradov, G. G.; Vertogradov, V. G.; Valov, V. A.; Uryadov, V. P.

doi:10.1134/s0016793206010099

Cited by 7 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the first derivative of the critical frequency, we can allow for its irregular variations and, hence, improve the prediction quality. The numerical results show the prediction efficiency PE (defined in [3]) up to 92%. This indicates the acceptable quality of prediction, but its efficiency significantly decreases with increasing prediction time.…”

Section: Prediction Of the Critical Frequency Of The Ionospheric F 2 mentioning

confidence: 98%

“…This is stipulated by the structural features of the high-latitude ionosphere and a set of processes ensuring its ionization in which we should distinguish between the daytime and night-time features. This requires significant changes in the architecture of the artificial neural network, in particular in the formation of the input-data vector compared with the network which predicts the parameters of the midlatitude ionosphere [3,4,15]. In addition, for the numerical experiments in this work, we developed a two-layer recurrence Elman network [5] with increased number of connections due to supplying the input data array to the second hidden layer (Fig.…”

Section: Search For An Optimal Architecture Of the Artificial Neural mentioning

confidence: 99%

“…Therefore, to ensure the HF communication reliability, we should perform the prompt and short-term prediction of the ionospheric parameters for intervals from several minutes to several hours. At present, developing the neural-network techniques [1][2][3][4], which perform the nonlinear correlation processing of the studied data series [5], is one of the most successful approaches to the short-term prediction for time intervals of 30 min and longer.…”

Section: Introduction and Statement Of The Problemmentioning

confidence: 99%

See 2 more Smart Citations

Allowance for the solar-magnetospheric connections in a problem of predicting the critical frequency of the subauroral ionosphere

Бархатова

Smirnova

Ulybina

2009

Radiophys Quantum El

View full text Add to dashboard Cite

The cause-and-effect relation between variations in the critical frequency of the F 2 subauroral ionospheric layer and the key solar-magnetospheric parameters is studied. The features of the dependence of the critical frequency of the subauroral ionosphere on the value and components of the interplanetary magnetic field, the solar-wind parameters, the X-ray and ultraviolet radiation intensities, the solar zenith angle, and the intensity of precipitation of low-energy particles are established. Within the framework of this study, codes allowing one to solve the problems of predicting the critical frequency of the ionosphere by the method of artificial neural networks has been developed. The neural-network forecasting experiments reveal the characteristic times of the ionospheric response to magnetospheric disturbancs. The found optimal architecture of the neural network allows us to predict the time series of the critical frequency of the high-latitude ionosphere for the interval 0.5-3 h with an accuracy of up to 93%. The obtained linear and nonlinear dependences of the critical frequency of the ionospheric F 2 layer on the geophysical parameters can be used for developing ionospheric models required for determining the maximum usable frequency of HF radio communication.

show abstract

Section: Prediction Of the Critical Frequency Of The Ionospheric F 2 mentioning

confidence: 98%

Section: Search For An Optimal Architecture Of the Artificial Neural mentioning

confidence: 99%

Section: Introduction and Statement Of The Problemmentioning

confidence: 99%

See 1 more Smart Citation

Allowance for the solar-magnetospheric connections in a problem of predicting the critical frequency of the subauroral ionosphere

Бархатова

Smirnova

Ulybina

2009

Radiophys Quantum El

View full text Add to dashboard Cite

show abstract

“…A deep learning algorithm, such as a neural network (NN), is a very important ionospheric parameter prediction method and has been widely used in recent years [17,[20][21][22]. It often requires a large amount of data for training, so it has a good effect when dealing with large samples of data for a long time.…”

Section: Introductionmentioning

confidence: 99%

A Model-Assisted Combined Machine Learning Method for Ionospheric TEC Prediction

2023

View full text Add to dashboard Cite

In order to improve the prediction accuracy of ionospheric total electron content (TEC), a combined intelligent prediction model (MMAdapGA-BP-NN) based on a multi-mutation, multi-cross adaptive genetic algorithm (MMAdapGA) and a back propagation neural network (BP-NN) was proposed. The model combines the international reference ionosphere (IRI), statistical machine learning (SML), BP-NN, and MMAdapGA. Compared with the IRI, SML-based, and other neural network models, MMAdapGA-BP-NN has higher accuracy and a more stable prediction effect. Taking the Athens station in Greece as an example, the root mean square errors (RMSEs) of MMAdapGA-BP-NN in 2015 and 2020 are 2.84TECU and 0.85TECU, respectively, 52.27% and 72.13% lower than the IRI model. Compared with the single neural network model, the MMAdapGA-BP-NN model reduced RMSE by 28.82% and 24.11% in 2015 and 2020, respectively. Furthermore, compared with the neural network optimized by a single mutation genetic algorithm, MMAdapGA-BP-NN has fewer iterations ranging from 10 to 30. The results show that the prediction effect and stability of the proposed model have obvious advantages. As a result, the model could be extended to an alternative prediction scheme for more ionospheric parameters.

show abstract

IRI-2001 model efficiency in ionospheric radiowave propagation forecasting

Krasheninnikov

Egorov

2010

Advances in Space Research

View full text Add to dashboard Cite

Prediction of the maximum observed frequency of the ionospheric HF radio channel using the method of artificial neural networks

Cited by 7 publications

References 9 publications

Allowance for the solar-magnetospheric connections in a problem of predicting the critical frequency of the subauroral ionosphere

Allowance for the solar-magnetospheric connections in a problem of predicting the critical frequency of the subauroral ionosphere

A Model-Assisted Combined Machine Learning Method for Ionospheric TEC Prediction

IRI-2001 model efficiency in ionospheric radiowave propagation forecasting

Contact Info

Product

Resources

About