skip to main content

Explore Research Products in the NSF-PAR

Title: Using Deep Learning to Map Ionospheric Total Electron Content over Brazil
The low-latitude ionosphere has an active behavior causing the total electron content (TEC) to vary spatially and temporally very dynamically. The solar activity and the geomagnetic field have a strong influence over the spatiotemporal distribution of TEC. These facts make it a challenge to attempt modeling the ionization response. Single frequency GNSS users are particularly vulnerable due to these ionospheric variations that cause degradation of positioning performance. Motivated by recent applications of machine learning, temporal series of TEC available in map formats were employed to build an independent TEC estimator model for low-latitude environments. A TEC dataset was applied along with geophysical indices of solar flux and magnetic activity to train a feedforward artificial neural network based on a multilayer perceptron (MLP) approach. The forecast for the next 24 h was made relying on TEC maps over the Brazilian region using data collected on the previous 5 days. The performance of this approach was evaluated and compared with real data. The accuracy of the model was evaluated taking into account seasonality, spatial coverage and dependence on solar flux and geomagnetic activity indices. The results of the analysis show that the developed model has a superior capacity describing the TEC behavior across Brazil, when compared to global ionosphere maps and the NeQuick G model. TEC predictions were applied in single point positioning. The achieved errors were 27% and 33% lower when compared to the results obtained using the NeQuick G and global ionosphere maps, respectively, showing success in estimating TEC with small recent datasets using MLP.  more » « less
Award ID(s):
1916055
NSF-PAR ID:
10435831
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
Remote Sensing
Volume:
15
Issue:
2
ISSN:
2072-4292
Page Range / eLocation ID:
412
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; ; ; ( , Journal of Geophysical Research: Space Physics)
    Abstract

    We present a new high‐resolution empirical model for the ionospheric total electron content (TEC). TEC data are obtained from the global navigation satellite system (GNSS) receivers with a 1° × 1° spatial resolution and 5‐min temporal resolution. The linear regression model is developed at 45°N, 0°E for the years 2000–2019 with 30‐min temporal resolution, unprecedented for typical empirical ionospheric models. The model describes dependency of TEC on solar flux, season, geomagnetic activity, and local time. Parameters describing solar and geomagnetic activity are evaluated. In particular, several options for solar flux input to the model are compared, including the 10.7 cm solar radio flux (F10.7), the Mg II core‐to‐wing ratio, and formulations of the solar extreme ultraviolet flux (EUV). Ultimately, the extreme ultraviolet flux presented by the Flare Irradiance Spectral Model, integrated from 0.05 to 105.05 nm, best represents the solar flux input to the model. TEC time delays to this solar parameter on the order of several days as well as seasonal modulation of the solar flux terms are included. TheAp3index and its history are used to reflect the influence of geomagnetic activity. The root mean squared error of the model (relative to the mean TEC observed in the 30‐min window) is 1.9539 TECu. A validation of this model for the first 3 months of 2020 shows excellent agreement with data. The new model shows significant improvement over the International Reference Ionosphere 2016 (IRI‐2016) when the two are compared during 2008 and 2012.

     
    more » « less
  2. ; ; ; ; ; ; ; ; ( , Space Weather)
    Abstract

    This study reconstructs total electron content (TEC) maps in the vicinity of the Korean Peninsula by employing a deep convolutional generative adversarial network and Poisson blending (DCGAN‐PB). Our interest is to rebuild small‐scale ionosphere structures on the TEC map in a local region where pronounced ionospheric structures, such as the equatorial ionization anomaly, are absent. The reconstructed regional TEC maps have a domain of 120°–135.5°E longitude and 25.5°–41°N latitude with 0.5° resolution. To achieve this, we first train a DCGAN model by using the International Reference Ionosphere‐based TEC maps from 2002 to 2019 (except for 2010 and 2014) as a training data set. Next, the trained DCGAN model generates synthetic complete TEC maps from observation‐based incomplete TEC maps. Final TEC maps are produced by blending of synthetic TEC maps with observed TEC data by PB. The performance of the DCGAN‐PB model is evaluated by testing the regeneration of the masked TEC observations in 2010 (solar minimum) and 2014 (solar maximum). Our results show that a good correlation between the masked and model‐generated TEC values is maintained even with a large percentage (∼80%) of masking. The performance of the DCGAN‐PB model is not sensitive to local time, solar activity, and magnetic activity. Thus, the DCGAN‐PB model can reconstruct fine ionospheric structures in regions where observations are sparse and distinguishing ionospheric structures are absent. This model can contribute to near real‐time monitoring of the ionosphere by immediately providing complete TEC maps.

     
    more » « less
  3. ; ; ; ; ; ; ; ; ; ; et al ( , Journal of Geophysical Research: Space Physics)
    Abstract

    During geomagnetically quiet and solar minimum conditions, spatial variations of the early morning thermosphere‐ionosphere (TI) system are expected to be mainly governed by wave dynamics. To study the postmidnight dynamical coupling, we investigated the early morning equatorial ionization anomaly (EIA) using Global‐scale Observations of the Limb and Disk (GOLD) measurements of OI‐135.6 nm nightglow emission and global navigation satellite system (GNSS)‐based total electron content (TEC) maps. The EIA structures in the OI‐135.6 nm emission over the American landmass resemble, spatially and temporally, those observed in the GNSS‐TEC maps. The early morning EIA (EM‐EIA) crests are well separated in latitude and mostly located over the middle of South America during October–November. In February–April the crests are less separated in latitude and predominantly located over the west coast sector of South America. Whole Atmosphere Community Climate Model with thermosphere and ionosphere eXtension (WACCMX) simulations with constant solar minimum and quiet‐geomagnetic conditions show that EM‐EIA can occur globally and shows properties similar to longitudinal Wave 4 pattern. Thus, we propose that EM‐EIA is driven by dynamical changes associated with the lower atmospheric waves.

     
    more » « less
  4. ; ( , Journal of Geophysical Research: Space Physics)
    Abstract

    The present study investigates the effect of the major sudden stratospheric warming (SSW) event of 2009, on the small‐scale gravity wave (GW) activity in the ionosphere. Small‐scale fluctuations with time periods within the range of 10–90 min observed in Global Positioning System total electron content (TEC) data have been used as a proxy for GW activity in the ionosphere. TEC data from five longitudinally separated Global Positioning System stations located around 60∘N latitude have been utilized for this purpose. In the initial phase of the major warming, when the stratospheric conditions are similar to a minor warming during which the mean zonal flow starts to weaken, the ionopsheric GW activity tends to increase. However, during the peak phase of the SSW, as the zonal mean wind starts to reverse its direction, and after the peak warming, as the winds remain weak, conditions are less favorable for upward propagation of a spectrum of GWs, and thus the ionospheric GW activity is reduced, as seen from the behavior of the small‐scale TEC fluctuations during the latter period of the SSW. Similar reduction in GW activity is also observed in the middle atmosphere (65–100 km) as seen from GWs derived from SABER (Sounding of the Atmosphere using Broadband Emission Radiometry) temperature profiles. The reductions in GW activity is more prominent during local daytime as compared to nighttime period. The reduction in GW activity shows a longitudinal variation with some locations showing relatively more reduction in the GW activity as compared to others.

     
    more » « less
  5. ; ; ; ; ; ; ; ; ; ; et al ( , Journal of Geophysical Research: Space Physics)
    Abstract

    In this study, we utilized both ground‐based and space‐borne observations including total electron content (TEC) from Beidou geostationary satellites, two‐dimensional TEC maps from the worldwide dense Global Navigation Satellite System receivers, ionosondes, and in situ electron density (Ne) and electron temperature (Te) from both Swarm and China Seismo‐Electromagnetic Satellite satellites, to investigate the low‐latitude ionospheric responses to the annular solar eclipse on 21 June 2020. The decrease in TEC during the eclipse at low latitudes showed a local time dependence with the largest depletions in the noon and afternoon sectors. It was also found that the TEC depletions at different latitudes in the equatorial ionization anomaly (EIA) region over the East Asian sector cannot solely be explained by the solar flux changes associated with the obscuration rate. The differences in TEC reduction between stations can be more than a factor of 2 at latitudes with the same obscuration rate of over 90%. Compared with TEC variations in the Northern Hemisphere, the TEC also underwent a considerable decrease in the EIA region in the conjugate hemisphere without eclipse shadow. Meanwhile, thehmF2near the magnetic equator increased around the onset of the eclipse, indicating an enhancement of the eastward equatorial electric field. Furthermore, the TEC decrease during the eclipse in the EIA region in both hemispheres lasted for a long period of more than 7 hr after the eclipse, with a TEC depletion of 2–6 TEC units. TheNefrom Swarm and China Seismo‐Electromagnetic Satellite satellites showed a complicated variation after the eclipse, whereas no visible change was observed inTe. The enhanced equatorial electric field, neutral wind changes, and the associated plasma transport act together to generate the observed ionospheric effects at low latitudes during the eclipse. Our results also suggest that the eclipse‐induced perturbations of dynamic processes can continue to impact the ionosphere after the eclipse.

     
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email