Showing papers on "Total electron content published in 2021"

Implementation of Hybrid Deep Learning Model (LSTM-CNN) for Ionospheric TEC Forecasting Using GPS Data

Abstract: Prominent advances in the field of artificial intelligence during the past decade and the breakthrough of deep learning would be useful for investigating ionospheric weather using ground and space-based ionospheric sensors data. The significance of deep learning algorithms needs to be assessed in forecasting the low latitude ionospheric disturbances (delays) for the global positioning system (GPS) signals. Total electron content (TEC) data sets prepared by taking advantage of GPS satellite radio frequency (RF) signals. This letter provides the application of deep learning models, long short-term memory (LSTM), gated recurrent unit (GRU), and a hybrid model that consists of LSTM combined with convolution neural network (CNN) to forecast the ionospheric delays for GPS signals. The deep learning models implemented using the vertical TEC (VTEC) time-series data estimated from GPS measurements over Bengaluru, Guntur, and Lucknow GPS stations. The LSTM-CNN model performs well when compared to other ionospheric deep learning forecasting algorithms with minimum root-mean-square error (RMSE) of 1.5 TEC units (TECUs) and a high degree of $R^{2} = 0.99$ .

Concentric Secondary Gravity Waves in the Thermosphere and Ionosphere Over the Continental United States on March 25–26, 2015 From Deep Convection

Abstract: Atmospheric gravity waves (GWs) are excited when deep convective plumes push up into the lower stratosphere. Most of these GWs have relatively small phase speeds and large amplitudes, which causes them to break and dissipate in the stratosphere and mesosphere (Alexander et al., 1995; Choi et al., 2007; Chun & Kim, 2008; Holton & Alexander, 1999; Lane et al., 2003). However, a small fraction of the GWs have small amplitudes and large horizontal phase speeds and vertical wavelengths, which allows them to propagate into the thermosphere (Heale et al., 2014; Hickey et al., 2009; Vadas & Fritts, 2004, 2005, 2006; Vadas & Liu, 2009). Here, kinematic viscosity is quite important, because it increases approximately exponentially with altitude (Pitteway & Hines, 1963). This increase creates a situation where GWs with different parameters are eliminated by viscosity at different altitudes (Vadas, 2007, 2013). This so-called “dissipative filtering” acts alongside wind filtering to transform and filter spectra of GWs from below (Fritts & Vadas, 2008). Modeling (Vadas, 2007) and observational (Djuth et al., 1997, 2004; Oliver et al., 1997) studies have shown that the vertical wavelength λz of the surviving GWs increases approximately exponentially with altitude up to z ∼ 220 km. Above that altitude, λz is approximately constant or has a weak dependence with altitude (Nicolls et al., 2014). This may occur because the molecular viscosity μ decreases with altitude when the mean free path becomes a substantial fraction of the density scale height  (Vadas & Crowley, 2017).

GIMLi: Global Ionospheric total electron content model based on machine learning

Abstract: EXtreme Gradient Boosting over Decision Trees (XGBoost or XGBDT) is a powerful tool to model a wide range of processes. We propose a new approach to create a global total electron content model, using machine-learning-based techniques, in particular, gradient boosting. The model is based on the Global Ionospheric Maps computed by Universitat Politecnica de Catalunya with a tomographic-kriging combined technique (UQRG). To reduce the problem complexity, we used empirical orthogonal functions (EOFs). The created model involves the first 16 spatial EOFs. For training and validation we used the 1998–2016 data sets, and the 2017 data as a test data set. To drive the model, we used the following features: (1) geomagnetic activity indexes (Kp, Ap, AE, AU, AL) and solar activity indexes (R, F10.7); (2) derivative values from these indexes such as the mean value and standard deviations within the last 12 h, last 11 days, and last 40 days; (3) day of the year (DOY); (4) averaged EOFs for given Kp and UT, and those for a given DOY and UT. The validation data set revealed the following hyperparameters for XGBoost learning: number of trees is 100, tree depth is 6, and learning rate is 0.1. Comparisons with the NeQuick2, Klobuchar, and GEMTEC models show that machine learning achieves higher accuracy for the 2017 test data set. The global averaged root-mean-square errors and mean absolute percentage errors were about 2.5 TECU and 19% for the nonlinear GIMLi-XGBDT model, about 4 TECU and 30–40% for NeQuick2, GEMTEC, and the linear model GIMLi-LM, and about 5.2 TECU and 73% for the Klobuchar model. A 4-fully-connected-layer artificial neural network provided a higher error (3.28 TECU and 27.7%) as compared to GIMLi-XGBDT. For all models mentioned, the error peaked in the equatorial anomaly region. The solar activity increase does not affect the error of the nonlinear GIMLi-XGBDT model. However, an increase in geomagnetic activity strongly affects that model.

The cooperative IGS RT-GIMs: a reliable estimation of the global ionospheric electron content distribution in real time

Abstract: . The Real-Time Working Group (RTWG) of the International GNSS Service (IGS) is dedicated to providing high-quality data and high-accuracy products for Global Navigation Satellite System (GNSS) positioning, navigation, timing and Earth observations. As one part of real-time products, the IGS combined Real-Time Global Ionosphere Map (RT-GIM) has been generated by the real-time weighting of the RT-GIMs from IGS real-time ionosphere centers including the Chinese Academy of Sciences (CAS), Centre National d'Etudes Spatiales (CNES), Universitat Politecnica de Catalunya (UPC) and Wuhan University (WHU). The performance of global vertical total electron content (VTEC) representation in all of the RT-GIMs has been assessed by VTEC from Jason-3 altimeter for 3 months over oceans and dSTEC-GPS technique with 2 d observations over continental regions. According to the Jason-3 VTEC and dSTEC-GPS assessment, the real-time weighting technique is sensitive to the accuracy of RT-GIMs. Compared with the performance of post-processed rapid global ionosphere maps (GIMs) and IGS combined final GIM (igsg) during the testing period, the accuracy of UPC RT-GIM (after the improvement of the interpolation technique) and IGS combined RT-GIM (IRTG) is equivalent to the rapid GIMs and reaches around 2.7 and 3.0 TECU (TEC unit, 10 16 el m−2 ) over oceans and continental regions, respectively. The accuracy of CAS RT-GIM and CNES RT-GIM is slightly worse than the rapid GIMs, while WHU RT-GIM requires a further upgrade to obtain similar performance. In addition, a strong response to the recent geomagnetic storms has been found in the global electron content (GEC) of IGS RT-GIMs (especially UPC RT-GIM and IGS combined RT-GIM). The IGS RT-GIMs turn out to be reliable sources of real-time global VTEC information and have great potential for real-time applications including range error correction for transionospheric radio signals, the monitoring of space weather, and detection of natural hazards on a global scale. All the IGS combined RT-GIMs generated and analyzed during the testing period are available at https://doi.org/10.5281/zenodo.5042622 ( Liu et al. , 2021 b ) .

Pre-Seismic Irregularities during the 2020 Samos (Greece) Earthquake (M = 6.9) as Investigated from Multi-Parameter Approach by Ground and Space-Based Techniques

Abstract: We present a comprehensive analysis of pre-seismic anomalies as computed from the ground and space-based techniques during the recent Samos earthquake in Greece on 30 October 2020, with a magnitude M = 6.9. We proceed with a multi-parametric approach where pre-seismic irregularities are investigated in the stratosphere, ionosphere, and magnetosphere. We use the convenient methods of acoustics and electromagnetic channels of the Lithosphere–Atmosphere–Ionosphere-Coupling (LAIC) mechanism by investigating the Atmospheric Gravity Wave (AGW), magnetic field, electron density, Total Electron Content (TEC), and the energetic particle precipitation in the inner radiation belt. We incorporate two ground-based IGS GPS stations DYNG (Greece) and IZMI (Turkey) for computing the TEC and observed a significant enhancement in daily TEC variation around one week before the earthquake. For the space-based observation, we use multiple parameters as recorded from Low Earth Orbit (LEO) satellites. For the AGW, we use the SABER/TIMED satellite data and compute the potential energy of stratospheric AGW by using the atmospheric temperature profile. It is found that the maximum potential energy of such AGW is observed around six days before the earthquake. Similar AGW is also observed by the method of wavelet analysis in the fluctuation in TEC values. We observe significant energetic particle precipitation in the inner radiation belt over the earthquake epicenter due to the conventional concept of an ionospheric-magnetospheric coupling mechanism by using an NOAA satellite. We first eliminate the particle count rate (CR) due to possible geomagnetic storms and South Atlantic Anomaly (SAA) by the proper choice of magnetic field B values. After the removal of the statistical background CRs, we observe a significant enhancement of CR four and ten days before the mainshock. We use Swarm satellite outcomes to check the magnetic field and electron density profile over a region of earthquake preparation. We observe a significant enhancement in electron density one day before the earthquake. The parameters studied here show an overall pre-seismic anomaly from a duration of ten days to one day before the earthquake.

Validation of GNSS-derived global ionosphere maps for different solar activity levels: case studies for years 2014 and 2018

Abstract: Ionosphere Associate Analysis Centers (IAACs) of the International GNSS Service (IGS) independently produce global ionosphere maps (GIMs) of the total electron content (TEC). The GIMs are based on different modeling techniques, resulting in different TEC levels and accuracies. In this study, we evaluated the accuracy and consistency of the IAAC GIMs during high (2014) and low (2018) solar activity periods of the 24th solar cycle. In our study, we applied two different evaluation methods. First, we carried out a comparison of the GIM-derived slant TEC (STEC) with carrier phase geometry-free combination of GNSS signals obtained from 25 globally distributed stations. Second, vertical TEC (VTEC) from GIMs was compared to altimetry-derived VTEC obtained from the Jason-2 and Jason-3 satellites and complemented for plasmaspheric TEC. The analyzed GIMs obtained STEC RMS values reaching from 1.98 to 3.00 TECU and from 0.96 to 1.29 TECU during 2014 and 2018, respectively. The comparison to altimetry data resulted in VTEC STD values that varied from 3.61 to 5.97 TECU and from 1.92 to 2.78 TECU during 2014 and 2018, respectively. The results show that among the IAACs, the Center for Orbit Determination in Europe global maps performed best in low and high solar activity periods. However, the highest accuracy was obtained by a non-IGS product—UQRG GIMs provided by Universitat Politecnica de Catalunya. It was also shown that the best results were obtained using a modified single layer model mapping function and that the map time interval has a relatively small influence on the resulting map accuracy.

Global equivalent slab thickness model of the Earth’s ionosphere

Abstract: The shape of the vertical electron density profile is a result of production, loss and transportation of plasma in the Earth’s ionosphere. Therefore, the equivalent slab thickness of the ionosphere that characterizes the width of vertical electron density profiles is an important parameter for a better understanding of ionospheric processes under regular as well as under perturbed conditions. The equivalent slab thickness is defined by the ratio of the vertical total electron content over the peak electron density and is therefore easy to compute by utilizing powerful data sources nowadays available thanks to ground and space based GNSS techniques. Here we use peak electron density data from three low earth orbiting (LEO) satellite missions, namely CHAMP, GRACE and FORMOSAT-3/COSMIC, as well as total electron content data obtained from numerous GNSS ground stations. For the first time, we present a global model of the equivalent slab thickness (Neustrelitz equivalent Slab Thickness Model – NSTM). The model approach is similar to a family of former model approaches successfully applied for total electron content (TEC), peak electron density NmF2 and corresponding height hmF2 at DLR. The model description focuses on an overall view of the behaviour of the equivalent slab thickness as a function of local time, season, geographic/geomagnetic location and solar activity on a global scale. In conclusion, the model agrees quite well with the overall observation data within a RMS range of 70 km. There is generally a good correlation with solar heat input that varies with local time, season and level of solar activity. However, under non-equilibrium conditions, plasma transport processes dominate the behaviour of the equivalent slab thickness. It is assumed that night-time plasmasphere–ionosphere coupling causes enhanced equivalent slab thickness values like the pre-sunrise enhancement. The overall fit provides consistent results with the mid-latitude bulge (MLB) of the equivalent slab thickness, described for the first time in this paper. Furthermore, the model recreates quite well ionospheric anomalies such as the Night-time Winter Anomaly (NWA) which is closely related to the Mid-latitude Summer Night-time Anomaly (MSNA) like the Weddell Sea Anomaly (WSA) and Okhotsk Sea Anomaly (OSA). Further model improvements can be achieved by using an extended model approach and considering the particular geomagnetic field structure.

BeiDou Global Ionospheric delay correction Model (BDGIM): performance analysis during different levels of solar conditions

Abstract: The BeiDou-3 system uses the BeiDou Global broadcast Ionospheric delay correction Model (BDGIM) to describe global vertical total electron content (VTEC) distributions and provide ionospheric delay mitigations in single-frequency positioning. The transmission of BDGIM correction parameters in the navigation message of BeiDou-3 started in mid-2015. The limited coverage of BeiDou-3 transmitted BDGIM parameters inhibits the evaluation of model performance during different levels of solar conditions. As such, we present a method to re-estimate BDGIM correction parameters and generate model parameters during the period 2010–2017 using a small global network of 20 global navigation satellite system (GNSS) stations. Tests covering the eight years demonstrate that BDGIM can reduce the ionospheric error to less than 25% for 98% of the examined samples when compared to global ionospheric maps (GIMs) provided by the International GNSS Service (IGS), and for 90% when compared to the observed VTECs from Jason-2/3 altimetry missions. Overall, BDGIM reduces residual ionospheric delays by 10–20% compared to the ionospheric correction algorithm (ICA) of the global positioning system (GPS), the empirical International Reference Ionosphere (IRI) 2016, and our fitted NeQuick-C model. The root-mean-square (RMS) error of BDGIM increases by 32 and 21% in comparison with GIM-derived and Jason-2 observed VTECs during the geomagnetic storm in March 2015, indicating the significant degradation of model performance during the disturbed geomagnetic period.

Solar activity dependence of medium-scale traveling ionospheric disturbances using GPS receivers in Japan

Abstract: In order to reveal solar activity dependence of the medium-scale traveling ionospheric disturbances (MSTIDs) at midlatitudes, total electron content (TEC) data obtained from a Global Positioning System (GPS) receiver network in Japan during 22 years from 1998 to 2019 were analyzed. We have calculated the detrended TEC by subtracting the 1-h running average from the original TEC data for each satellite and receiver pair, and made two-dimensional TEC maps of the detrended TEC with a spatial resolution of 0.15° × 0.15° in longitude and latitude. We have investigated MSTID activity, defined as $$\delta I/\overline{I}$$ , where $$\delta I$$ and $$\overline{I}$$ are standard deviation of the detrended TEC and the average vertical TEC within the area of 133.0°–137.0° E and 33.0°–37.0° N for 1 h, respectively. From each 2-h time series of the detrended TEC data within the same area as the MSTID activity, auto-correlation functions (ACFs) of the detrended TEC were calculated to estimate the horizontal propagation velocity and direction of the MSTIDs. Statistical results of the MSTID activity and propagation direction of MSTIDs were consistent with previous studies and support the idea that daytime MSTIDs could be caused by atmospheric gravity waves, and that nighttime MSTIDs were caused by electro-dynamical forces, such as the Perkins instability. From the current long-term observations, we have found that the nighttime MSTID activity and occurrence rate increased with decreasing solar activity. For the daytime MSTID, the occurrence rate increased with decreasing solar activity, whereas the MSTID activity did not show distinct solar activity dependence. These results suggest that the secondary gravity waves generated by dissipation of the primary gravity waves propagating from below increase under low solar activity conditions. The mean horizontal phase velocity of the MSTIDs during nighttime did not show a distinct solar activity dependence, whereas that during daytime showed an anticorrelation with solar activity. The horizontal phase velocity of the daytime MSTIDs was widely distributed from 40 to 180 m/s under high solar activity conditions, whereas it ranged between 80 and 200 m/s, with a maximum occurrence at 130 m/s under low solar activity conditions, suggesting that gravity waves with low phase velocity could be dissipated by high viscosity in the thermosphere under low solar activity conditions.

Using Support Vector Machine (SVM) and Ionospheric Total Electron Content (TEC) Data for Solar Flare Predictions

Abstract: Predicting where and when space weather events such as solar flares and X-rays bursts are likely to occur in a specific area of interest constitutes a significant challenge in space weather research. Space weather scientists are, therefore, gradually exploring multivariate data analysis techniques from the fields of data mining or machine learning in order to approximate future occurrences of space weather events from past distribution patterns. As solar flares emit extreme ultraviolet and X-ray radiation, which leads to ionization effect in different layers of the ionosphere, most recent works related to solar flare predictions using machine learning (ML) techniques, focused on X-ray time series predictions. Here, we suggest using support vector machine for classifying subdaily and diurnal total electron content (TEC) spatial changes prior to solar flare events, in order to assess the possibility of predicting B, C, M, and X-class solar flare events. This is done as opposed to predicting TEC time series using ML techniques. The predictions are estimated up to three days before each tested class events, along with different skill scores such as precision, recall, Heidke skill score (HSS), accuracy, and true skill statistics. The results indicate that the suggested approach has the ability to predict solar flare events of X and M-class 24 h prior to their occurrence with 91% and 76% HSS skill scores, respectively, which improves over most recent related works. However, for the small-size C and B-class flares, the suggested approach does not succeed in producing similar promising results.

Processing and Validation of FORMOSAT-7/COSMIC-2 GPS Total Electron Content Observations

Abstract: Slant absolute total electron content (TEC) is observed by the Formosa Satellite-7/Constellation Observing System for Meteorology, Ionosphere, and Climate-2 (FORMOSAT-7/COSMIC-2, F7/C2) Tri-GNSS Radio Occultation System (TGRS) instrument. We present details of the data processing algorithms, validation, and error assessment for the F7/C2 global positioning system (GPS) absolute TEC observations. The data processing includes estimation and application of solar panel dependent pseudorange multipath maps, phase to pseudorange leveling, and estimation of separate L1C-L2C and L1C-L2P receiver differential code biases. We additionally perform a validation of the F7/C2 GPS absolute TEC observations through comparison with colocated, independent, TEC observations from the Swarm-B satellite. Based on this comparison, we conclude that the accuracy of the F7/C2 GPS absolute TEC observations is less than 3.0 TEC units. Results are also presented that illustrate the suitability of the F7/C2 GPS absolute TEC observations for studying the climatology and variability of the topside ionosphere and plasmasphere (i.e., altitudes above the F7/C2 orbit of ∼550 km). These results demonstrate that F7/C2 provides high quality GPS absolute TEC observations that can be used for ionosphere-thermosphere data assimilation as well as scientific studies of the topside ionosphere and plasmasphere.

Possible ionospheric anomalies associated with the 2009 M w 6.4 Taiwan earthquake from DEMETER and GNSS TEC

Abstract: The recent advances in satellite based ionosphere monitoring provided more evidence about earthquake (EQ) precursors from lithosphere ionosphere coupling mechanism. In this paper, we investigate ionospheric anomalies associated with the December 19, 2009, Taiwan EQ (Mw = 6.4), that occurred on UT = 13:02 h. Seismo ionospheric anomalies are evaluated during 31 days (20 day before followed by 10 days after the EQ) in the data of French Satellite Detection of Electro-Magnetic Emissions Transmitted from Earthquake Regions (DEMETER) and validated from Global Navigation Satellite System (GNSS) retrieved Total Electron Content (TEC). The day time values of ISL (Langmuir Probe) and IAP (Ion Analyzer) from DEMETER point to significant ionospheric perturbations within 5 days associated with EQ day. Moreover, GNSS stations of International GNSS Service (IGS) within EQ preparation zone also validate anomalies in ionosphere prior/after the Mw 6.4, Taiwan EQ. Moreover, spatial and temporal analyses of daily ionospheric indices from DEMETER and GNSS point to simultaneous enhancement in electron density, ion density, electron temperature and TEC related to the main shock during quiet geomagnetic storm (Dst < − 30 nT, Kp ≤ 3). All these evidence aids in promoting the lithosphere- ionosphere coupling over the epicenter of Mw 6.4 during the preparation period from DEMETER and GNSS TEC.

E-CHAIM as a Model of Total Electron Content: Performance and Diagnostics

Abstract: Here we assess to what extent the Empirical Canadian High Arctic Ionospheric Model (E-CHAIM) can reproduce the climatological variations of vertical Total Electron Content (vTEC) in the Canadian se...

The nighttime ionospheric response and occurrence of equatorial plasma irregularities during geomagnetic storms: a case study

Abstract: Recent studies revealed that the long-lasting daytime ionospheric enhancements of Total Electron Content (TEC) were sometimes observed in the Asian sector during the recovery phase of geomagnetic storms (e.g., Lei (J Geophys Res Space Phys 123: 3217–3232, 2018), Li (J Geophys Res Space Phys 125: e2020JA028238, 2020). However, they focused only on the dayside ionosphere, and no dedicated studies have been performed to investigate the nighttime ionospheric behavior during such kinds of storm recovery phases. In this study, we focused on two geomagnetic storms that happened on 7–8 September 2017 and 25–26 August 2018, which showed the prominent daytime TEC enhancements in the Asian sector during their recovery phases, to explore the nighttime large-scale ionospheric responses as well as the small-scale Equatorial Plasma Irregularities (EPIs). It is found that during the September 2017 storm recovery phase, the nighttime ionosphere in the American sector is largely depressed, which is similar to the daytime ionospheric response in the same longitude sector; while in the Asian sector, only a small TEC increase is observed at nighttime, which is much weaker than the prominent daytime TEC enhancement in this longitude sector. During the recovery phase of the August 2018 storm, a slight TEC increase is observed on the night side at all longitudes, which is also weaker than the prominent daytime TEC enhancement. For the small-scale EPIs, they are enhanced and extended to higher latitudes during the main phase of both storms. However, during the recovery phases of the first storm, the EPIs are largely enhanced and suppressed in the Asian and American sectors, respectively, while no prominent nighttime EPIs are observed during the second storm recovery phase. The clear north–south asymmetry of equatorial ionization anomaly crests during the second storm should be responsible for the suppression of EPIs during this storm. In addition, our results also suggest that the dusk side ionospheric response could be affected by the daytime ionospheric plasma density/TEC variations during the recovery phase of geomagnetic storms, which further modulates the vertical plasma drift and plasma gradient. As a result, the growth rate of post-sunset EPIs will be enhanced or inhibited.

Atmospheric and ionospheric coupling phenomena associated with large earthquakes

Abstract: This paper explores multi-instrument space-borne observations in order to validate physical concepts of Lithosphere-Atmosphere-Ionosphere Coupling (LAIC) in relation to a selection of major seismic events. In this study we apply some validated techniques to observations in order to identify atmospheric and ionospheric precursors associated with some of recent most destructive earthquakes: M8.6 of March 28, 2005 and M8.5 of Sept. 12, 2007 in Sumatra, and M7.9 of May 12, 2008 in Wenchuan, China. New investigations are also presented concerning these three earthquakes and for the M7.2 of March 2008 in the Xinjiang-Xizang border region, China (the Yutian earthquake). It concerns the ionospheric density, the Global Ionospheric Maps (GIM) of the Total Electron Content (TEC), the Thermal Infra-Red (TIR) anomalies, and the Outgoing Longwave Radiation (OLR) data. It is shown that all these anomalies are identified as short-term precursors, which can be explained by the LAIC concept proposed in [S. Pulinets, D. Ouzounov, J. Asian Earth Sci. 41, 371 (2011)].

Observation of the Ionosphere in Middle Latitudes during 2009, 2018 and 2018/2019 Sudden Stratospheric Warming Events

Abstract: The ionospheric weather is affected not only from above by the Sun but also from below by processes in the lower-lying atmospheric layers. One of the most pronounced atmospheric phenomena is the sudden stratospheric warming (SSW). Three major SSW events from the periods of very low solar activity during January 2009, February 2018, and December 2018/January 2019 were studied to evaluate this effect of the neutral atmosphere on the thermosphere and the ionosphere. The main question is to what extent the ionosphere responds to the SSW events with focus on middle latitudes over Europe. The source of the ionospheric data was ground-based measurements by Digisondes, and the total electron content (TEC). In all three events, the ionospheric response was demonstrated as an increase in electron density around the peak height of the F2 region, in TEC, and presence of wave activity. We presume that neutral atmosphere forcing and geomagnetic activity contributed differently in individual events. The ionospheric response during SSW 2009 was predominantly influenced by the neutral lower atmosphere. The ionospheric changes observed during 2018 and 2018/2019 SSWs are a combination of both geomagnetic and SSW forcing. The ionospheric response to geomagnetic forcing was noticeably lower during time intervals outside of SSWs.

Deep learning of total electron content

Abstract: 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.