ML Prediction of Global Ionospheric TEC Maps
Abstract This paper applies the convolutional long short‐term memory (convLSTM)‐based machine learning models to forecast global ionospheric total electron content (TEC) maps with up to 24 hr of lead time at a 1‐hr interval. Four convLSTM‐based models were investigated, and the one that implements t...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-09-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2022SW003135 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536302310227968 |
|---|---|
| author | Lei Liu Y. Jade Morton Yunxiang Liu |
| author_facet | Lei Liu Y. Jade Morton Yunxiang Liu |
| author_sort | Lei Liu |
| collection | DOAJ |
| description | Abstract This paper applies the convolutional long short‐term memory (convLSTM)‐based machine learning models to forecast global ionospheric total electron content (TEC) maps with up to 24 hr of lead time at a 1‐hr interval. Four convLSTM‐based models were investigated, and the one that implements the L1 loss function and the residual prediction strategy demonstrates the best performance. The convLSTM models are trained and evaluated using Center for Orbit Determination in Europe (CODE) global TEC maps over a period of nearly seven years from 19 October 2014 to 21 July 2021. Results show that the best convLSTM model outperforms the 1‐day predicted global TEC products released by CODE analysis center (c1pg) and persistence models under various levels of solar and geomagnetic activities, except for a lead time beyond 8 hr during the storm time where the c1pg has slightly better performance. The convLSTM forecasting performance degrades as the lead time increases. |
| format | Article |
| id | doaj-art-0589f86951054906ae50c9f70fe230c8 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2022-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-0589f86951054906ae50c9f70fe230c82025-01-14T16:31:13ZengWileySpace Weather1542-73902022-09-01209n/an/a10.1029/2022SW003135ML Prediction of Global Ionospheric TEC MapsLei Liu0Y. Jade Morton1Yunxiang Liu2Ann and H. J. Smead Aerospace Engineering Sciences Department University of Colorado Boulder Boulder CO USAAnn and H. J. Smead Aerospace Engineering Sciences Department University of Colorado Boulder Boulder CO USAAnn and H. J. Smead Aerospace Engineering Sciences Department University of Colorado Boulder Boulder CO USAAbstract This paper applies the convolutional long short‐term memory (convLSTM)‐based machine learning models to forecast global ionospheric total electron content (TEC) maps with up to 24 hr of lead time at a 1‐hr interval. Four convLSTM‐based models were investigated, and the one that implements the L1 loss function and the residual prediction strategy demonstrates the best performance. The convLSTM models are trained and evaluated using Center for Orbit Determination in Europe (CODE) global TEC maps over a period of nearly seven years from 19 October 2014 to 21 July 2021. Results show that the best convLSTM model outperforms the 1‐day predicted global TEC products released by CODE analysis center (c1pg) and persistence models under various levels of solar and geomagnetic activities, except for a lead time beyond 8 hr during the storm time where the c1pg has slightly better performance. The convLSTM forecasting performance degrades as the lead time increases.https://doi.org/10.1029/2022SW003135 |
| spellingShingle | Lei Liu Y. Jade Morton Yunxiang Liu ML Prediction of Global Ionospheric TEC Maps Space Weather |
| title | ML Prediction of Global Ionospheric TEC Maps |
| title_full | ML Prediction of Global Ionospheric TEC Maps |
| title_fullStr | ML Prediction of Global Ionospheric TEC Maps |
| title_full_unstemmed | ML Prediction of Global Ionospheric TEC Maps |
| title_short | ML Prediction of Global Ionospheric TEC Maps |
| title_sort | ml prediction of global ionospheric tec maps |
| url | https://doi.org/10.1029/2022SW003135 |
| work_keys_str_mv | AT leiliu mlpredictionofglobalionospherictecmaps AT yjademorton mlpredictionofglobalionospherictecmaps AT yunxiangliu mlpredictionofglobalionospherictecmaps |