Forecasting of low‐latitude storm‐time ionospheric foF2 using support vector machine

Ban, Panpan; Sun, Shuo; Chen, Chun; Zhao, Zhenwei

doi:10.1029/2010rs004633

Cited by 26 publications

(14 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, one can employ a time history of a given quantity, recorded with a certain time frequency. Examples of supervised regression in Space Weather are the forecast of a geomagnetic index, as function of solar wind parameters observed at L1 (Gleisner et al, ; Lundstedt & Wintoft, ; Macpherson et al, ; Uwamahoro & Habarulema, ; Valach et al, ; Weigel et al, ), the prediction of solar energetic particles (SEPs) (Fernandes, ; Gong et al, ; Li et al, ), of the F10.7 index for radio emissions (Ban et al, ; Huang et al, ), of ionospheric parameters (Chen et al, ), of sunspot numbers or, more in general, of the solar cycle (Ashmall & Moore, ; Calvo et al, ; Conway et al, ; Fessant et al, ; Lantos & Richard, ; Pesnell, ; Uwamahoro et al, ), of the arrival time of interplanetary shocks (Vandegriff et al, ), and of CMEs (Choi et al, ; Sudar et al, ).…”

Section: Machine Learning In Space Weathermentioning

confidence: 99%

The Challenge of Machine Learning in Space Weather: Nowcasting and Forecasting

2019

View full text Add to dashboard Cite

The numerous recent breakthroughs in machine learning make imperative to carefully ponder how the scientific community can benefit from a technology that, although not necessarily new, is today living its golden age. This Grand Challenge review paper is focused on the present and future role of machine learning in Space Weather. The purpose is twofold. On one hand, we will discuss previous works that use machine learning for Space Weather forecasting, focusing in particular on the few areas that have seen most activity: the forecasting of geomagnetic indices, of relativistic electrons at geosynchronous orbits, of solar flares occurrence, of coronal mass ejection propagation time, and of solar wind speed. On the other hand, this paper serves as a gentle introduction to the field of machine learning tailored to the Space Weather community and as a pointer to a number of open challenges that we believe the community should undertake in the next decade. The recurring themes throughout the review are the need to shift our forecasting paradigm to a probabilistic approach focused on the reliable assessment of uncertainties, and the combination of physics-based and machine learning approaches, known as gray box. Plain Language SummaryIn the last decade, machine learning has achieved unforeseen results in industrial applications. In particular, the combination of massive data sets and computing with specialized processors (graphics processing units, or GPUs) can perform as well or better than humans in tasks like image classification and game playing. Space weather is a discipline that lives between academia and industry, given the relevant physical effects on satellites and power grids in a variety of applications, and the field therefore stands to benefit from the advances made in industrial applications. Today, machine learning poses both a challenge and an opportunity for the space weather community. The challenge is that the current data science revolution has not been fully embraced, possibly because space physicists remain skeptical of the gains achievable with machine learning. If the community can master the relevant technical skills, they should be able to appreciate what is possible within a few years time and what is possible within a decade. The clearest opportunity lies in creating space weather forecasting models that can respond in real time and that are built on both physics predictions and on observed data.

show abstract

Section: Machine Learning In Space Weathermentioning

confidence: 99%

The Challenge of Machine Learning in Space Weather: Nowcasting and Forecasting

2019

View full text Add to dashboard Cite

show abstract

“…These very short-term predictions are generally referred to as nowcasts [34]. The most common ionospheric short-term fore-casting methods at present mainly include auto-correlation function method, multiple linear regression method, artificial neural network method, equivalent sunspot number method, Kalman filtering method, similar day method, storm time ionospheric forecasting method and so on [35][36][37]. Figure 3 shows a typical variation of LUF, MUF and FOT over a day.…”

Section: Hf Radio Propagation Prediction: Purposes and Approachesmentioning

confidence: 99%

Radio Propagation Prediction for HF Communications

Mudzingwa¹,

Chawanda²

2018

COM

View full text Add to dashboard Cite

The refraction and apparent reflection of HF radio waves by the ionosphere enables long range HF radio communications. The ionosphere is a distinctly irregular medium that is mostly driven by solar activity. Ionospheric models are useful in the prediction of ionospheric behaviour and in the provision of data required for the analysis and forecasting of ionospheric propagation. This paper provides a compact review of HF radio propagation prediction techniques and approaches for HF communications. The paper also highlights the numerous approaches have been used to date in an attempt to estimate F2 usable frequencies. The review presented in this paper is inspired by the most recent advances in the field of ionospheric prediction and modelling.

show abstract

“…Some literatures utilized the autoregression method, Muhtarov proposed a correlated autoregression ionospheric model driven by a synthetic geomagnetical index [16], Tsagouri presented an autoregression model for ionospheric short-term forecast based on the solar wind [17] [18], Tsagouri and Belehaki combined an autoregression forecasting algorithm with the empirical storm-time model [19]. In order to study the effects of the storm on the ionosphere, an empirical storm-time ionospheric correction model has been developed by Araujo Pradere [20] [21], and Ban introduced a forecasting model of low-latitude storm-time ionospheric f0F2 [22].…”

Section: Introductionmentioning

confidence: 99%

Forecasting the Ionospheric f0F2 Parameter One Hour in Advance Using Recurrent Neural Network

Lv¹,

Yu²,

Liu³

2019

Proceedings of the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019)

View full text Add to dashboard Cite

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.

show abstract

Forecasting of low‐latitude storm‐time ionospheric foF2 using support vector machine

Cited by 26 publications

References 39 publications

The Challenge of Machine Learning in Space Weather: Nowcasting and Forecasting

The Challenge of Machine Learning in Space Weather: Nowcasting and Forecasting

Radio Propagation Prediction for HF Communications

Forecasting the Ionospheric f0F2 Parameter One Hour in Advance Using Recurrent Neural Network

Contact Info

Product

Resources

About