Short-term estimation of GNSS TEC using a neural network model in Brazil

Ferreira, Arthur Amaral; Borges, Renato Alves; Paparini, Claudia; Ciraolo, L.; Radicella, S. M.

doi:10.1016/j.asr.2017.06.001

Cited by 17 publications

(14 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the accuracy, BPANN is a very powerful network that can be used to estimate various parameters. These networks will be able to provide logical answers to new input data if they are properly trained [2,5,14].…”

Section: The Study Area and Resultsmentioning

confidence: 99%

“…TEC has very high variations due to changes in time and space. Another important point is that the TEC is strongly dependent on the satellite's elevation angle (the geometric position of the satellite) because the signal path length in the ionosphere varies with the satellite position in the sky [14].…”

Section: Vtec (Tec)mentioning

confidence: 99%

“…The Kp-index is obtained by averaging the observations of the horizontal field H intensity from a network [3]. This index is calculated at 3-h intervals, which is a kind of global measurement of the magnetic deviation from regular daily changes in one-hour period [14].…”

Section: Kp-indexmentioning

confidence: 99%

See 2 more Smart Citations

Deep learning of total electron content

Sorkhabi

2021

SN Appl. Sci.

View full text Add to dashboard Cite

One of the most notable errors in the global navigation satellite system (GNSS) is the ionospheric delay due to the total electron content (TEC). TEC is the number of electrons in the ionosphere in the signal path from the satellite to the receiver, which fluctuates with time and location. This error is one of the major problems in single-frequency (SF) GPS receivers. One way to eliminate this error is to use dual-frequency. Users of SF receivers should either use estimation models or local models to reduce this error. In this study, deep learning of artificial neural networks (ANN) was used to estimate TEC for SF users. For this purpose, the ionosphere as a single-layer model (assuming that all free electrons in the ionosphere are in this thin layer) is locally modeled by the code observation method. Linear combination has been used by selecting 24 permanent GNSS stations in the northwest of Iran. TEC was modeled independently of the geometry between the satellite and the receiver, called L4. This modeling was used to train the error ANN with two 5-day periods of high and low solar and geomagnetic activity range with a hyperbolic tangential sigmoid activation function. The results show that the proposed method is capable of eliminating ionosphere error with an average accuracy of 90%. The international reference ionosphere 2016 (IRI2016) is used for the verification, which has a 96% significance correlation with estimated TEC.

show abstract

Section: The Study Area and Resultsmentioning

confidence: 99%

Section: Vtec (Tec)mentioning

confidence: 99%

See 1 more Smart Citation

Deep learning of total electron content

Sorkhabi

2021

SN Appl. Sci.

View full text Add to dashboard Cite

show abstract

“…TEC is obtained by the integration of Ne along the signal path S, as shown in Equation 5. TEC can be expressed in TECU (1 TECU is equivalent to 1x10 16 electrons/ m2) [38], [39]. (5) Where, electron density (Ne) is the amount of electron in a column of the cross-sectional area of 1 m 2 along the path of the signal through the ionosphere.…”

Section: Datasetsmentioning

confidence: 99%

“…The relationship between time delay, a frequency of the signal and TEC is represented in the following equation. (6) Where dt is the ionosphere time delay, c is the velocity of light and f is the wave propagation frequency [38], [39]. The sample of data to be collected and analyzed for this study is shown in Figure 4.…”

Section: Datasetsmentioning

confidence: 99%

Enhancing Prediction Method of Ionosphere for Space Weather Monitoring Using Machine Learning Approaches: A Review

Salleh

Yuhaniz

Sabri

et al. 2020

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

This paper studies the machine learning techniques that can be used to enhance the prediction method of the ionosphere for space weather monitoring. Previously, the empirical model is used. However, there is a large deviation of the total electron content of ionosphere data for the areas located in the equatorial and low-latitude regions due to the lack of observation data contributed by these areas during the development of the empirical model. The machine learning technique is an alternative method used to develop the predictive model. Thus, in this study, the machine learning techniques that can be applied are investigated. The aim is to improve the predictive model in terms of reducing the total electron content deviation, increasing the accuracy and minimizing the error. In this review, the techniques used in previous works will be compared. The artificial neural network is found to be a suitable technique and the most favorable from the review conducted. Also, this technique can provide an accurate model for time series data and fewer errors compared to other techniques. However, due to the size and complexity of the data, the deep neural network technique that is an improved artificial neural network technique is suggested. By using this technique, an accurate ionosphere predictive model in equatorial and low region area is expected. In the future, this study will analyze further by using computing tools and real-time data.

show abstract