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...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/2/412 |
| _version_ | 1797437411994632192 |
|---|---|
| author | Andre Silva Alison Moraes Jonas Sousasantos Marcos Maximo Bruno Vani Clodoaldo Faria |
| author_facet | Andre Silva Alison Moraes Jonas Sousasantos Marcos Maximo Bruno Vani Clodoaldo Faria |
| author_sort | Andre Silva |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T11:19:57Z |
| format | Article |
| id | doaj.art-212f53714c074c4693afb8fdf946fe6d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T11:19:57Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-212f53714c074c4693afb8fdf946fe6d2023-12-01T00:20:22ZengMDPI AGRemote Sensing2072-42922023-01-0115241210.3390/rs15020412Using Deep Learning to Map Ionospheric Total Electron Content over BrazilAndre Silva0Alison Moraes1Jonas Sousasantos2Marcos Maximo3Bruno Vani4Clodoaldo Faria5Instituto Tecnológico de Aeronáutica, São José dos Campos 12228-900, SP, BrazilInstituto de Aeronáutica e Espaço, São José dos Campos 12228-904, SP, BrazilWilliam B. Hanson Center for Space Sciences, The University of Texas at Dallas, Richardson, TX 75080, USAInstituto Tecnológico de Aeronáutica, São José dos Campos 12228-900, SP, BrazilInstituto Federal de Educação, Ciência e Tecnologia de São Paulo, Presidente Epitácio 19470-000, SP, BrazilInstituto Federal de Educação, Ciência e Tecnologia de São Paulo, Presidente Epitácio 19470-000, SP, BrazilThe 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.https://www.mdpi.com/2072-4292/15/2/412GNSSionospheric modelsmachine learningsingle point positioningtotal electron content |
| spellingShingle | Andre Silva Alison Moraes Jonas Sousasantos Marcos Maximo Bruno Vani Clodoaldo Faria Using Deep Learning to Map Ionospheric Total Electron Content over Brazil Remote Sensing GNSS ionospheric models machine learning single point positioning total electron content |
| title | Using Deep Learning to Map Ionospheric Total Electron Content over Brazil |
| title_full | Using Deep Learning to Map Ionospheric Total Electron Content over Brazil |
| title_fullStr | Using Deep Learning to Map Ionospheric Total Electron Content over Brazil |
| title_full_unstemmed | Using Deep Learning to Map Ionospheric Total Electron Content over Brazil |
| title_short | Using Deep Learning to Map Ionospheric Total Electron Content over Brazil |
| title_sort | using deep learning to map ionospheric total electron content over brazil |
| topic | GNSS ionospheric models machine learning single point positioning total electron content |
| url | https://www.mdpi.com/2072-4292/15/2/412 |
| work_keys_str_mv | AT andresilva usingdeeplearningtomapionospherictotalelectroncontentoverbrazil AT alisonmoraes usingdeeplearningtomapionospherictotalelectroncontentoverbrazil AT jonassousasantos usingdeeplearningtomapionospherictotalelectroncontentoverbrazil AT marcosmaximo usingdeeplearningtomapionospherictotalelectroncontentoverbrazil AT brunovani usingdeeplearningtomapionospherictotalelectroncontentoverbrazil AT clodoaldofaria usingdeeplearningtomapionospherictotalelectroncontentoverbrazil |