One‐Day Forecasting of Global TEC Using a Novel Deep Learning Model
Abstract In this study, we make a global total electron content (TEC) forecasting using a novel deep learning method, which is based on conditional generative adversarial networks. For training, we use the International GNSS Service (IGS) TEC maps from 2003 to 2012 with 2‐h time cadence. Our model h...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2020SW002600 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536500826636288 |
|---|---|
| author | Sujin Lee Eun‐Young Ji Yong‐Jae Moon Eunsu Park |
| author_facet | Sujin Lee Eun‐Young Ji Yong‐Jae Moon Eunsu Park |
| author_sort | Sujin Lee |
| collection | DOAJ |
| description | Abstract In this study, we make a global total electron content (TEC) forecasting using a novel deep learning method, which is based on conditional generative adversarial networks. For training, we use the International GNSS Service (IGS) TEC maps from 2003 to 2012 with 2‐h time cadence. Our model has two input images (IGS TEC map and 1‐day difference map between the present day and the previous day) and one output image (1‐day future map). The model is tested with two data sets: solar maximum period (2013–2014) and solar minimum period (2017–2018). Then, we compare the results of our model with those of 1‐day Center for Orbit Determination in Europe (CODE) prediction model. Our major results can be summarized as follows. First, we successfully apply our model to the forecast of global TEC maps. Second, our model well predicts daily TEC maps with 1 day in advance using only previous TEC maps. The averaged root mean square error, bias, and standard deviation between AI‐generated and IGS TEC maps are 2.74 TECU, −0.32 TECU, and 2.59 TECU, respectively. Third, our model generates some peak structures around equatorial regions. Fourth, our model shows better performance than 1‐day CODE prediction model during both solar maximum and minimum periods. Fifth, another model with additional input data Kp index gives a slight improvement of the results. Our study shows that our deep learning model based on an image translation method will be effective for forecasting of future images using previous data. |
| format | Article |
| id | doaj-art-8b3df5532f8e4d228b2ad6c5d0be74a6 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-8b3df5532f8e4d228b2ad6c5d0be74a62025-01-14T16:27:00ZengWileySpace Weather1542-73902021-01-01191n/an/a10.1029/2020SW002600One‐Day Forecasting of Global TEC Using a Novel Deep Learning ModelSujin Lee0Eun‐Young Ji1Yong‐Jae Moon2Eunsu Park3Department of Astronomy and Space Science College of Applied Science, Kyung Hee University Yongin South KoreaDepartment of Astronomy and Space Science College of Applied Science, Kyung Hee University Yongin South KoreaDepartment of Astronomy and Space Science College of Applied Science, Kyung Hee University Yongin South KoreaDepartment of Astronomy and Space Science College of Applied Science, Kyung Hee University Yongin South KoreaAbstract In this study, we make a global total electron content (TEC) forecasting using a novel deep learning method, which is based on conditional generative adversarial networks. For training, we use the International GNSS Service (IGS) TEC maps from 2003 to 2012 with 2‐h time cadence. Our model has two input images (IGS TEC map and 1‐day difference map between the present day and the previous day) and one output image (1‐day future map). The model is tested with two data sets: solar maximum period (2013–2014) and solar minimum period (2017–2018). Then, we compare the results of our model with those of 1‐day Center for Orbit Determination in Europe (CODE) prediction model. Our major results can be summarized as follows. First, we successfully apply our model to the forecast of global TEC maps. Second, our model well predicts daily TEC maps with 1 day in advance using only previous TEC maps. The averaged root mean square error, bias, and standard deviation between AI‐generated and IGS TEC maps are 2.74 TECU, −0.32 TECU, and 2.59 TECU, respectively. Third, our model generates some peak structures around equatorial regions. Fourth, our model shows better performance than 1‐day CODE prediction model during both solar maximum and minimum periods. Fifth, another model with additional input data Kp index gives a slight improvement of the results. Our study shows that our deep learning model based on an image translation method will be effective for forecasting of future images using previous data.https://doi.org/10.1029/2020SW002600deep learningionosphereTEC forecasting |
| spellingShingle | Sujin Lee Eun‐Young Ji Yong‐Jae Moon Eunsu Park One‐Day Forecasting of Global TEC Using a Novel Deep Learning Model Space Weather deep learning ionosphere TEC forecasting |
| title | One‐Day Forecasting of Global TEC Using a Novel Deep Learning Model |
| title_full | One‐Day Forecasting of Global TEC Using a Novel Deep Learning Model |
| title_fullStr | One‐Day Forecasting of Global TEC Using a Novel Deep Learning Model |
| title_full_unstemmed | One‐Day Forecasting of Global TEC Using a Novel Deep Learning Model |
| title_short | One‐Day Forecasting of Global TEC Using a Novel Deep Learning Model |
| title_sort | one day forecasting of global tec using a novel deep learning model |
| topic | deep learning ionosphere TEC forecasting |
| url | https://doi.org/10.1029/2020SW002600 |
| work_keys_str_mv | AT sujinlee onedayforecastingofglobaltecusinganoveldeeplearningmodel AT eunyoungji onedayforecastingofglobaltecusinganoveldeeplearningmodel AT yongjaemoon onedayforecastingofglobaltecusinganoveldeeplearningmodel AT eunsupark onedayforecastingofglobaltecusinganoveldeeplearningmodel |