Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach
Abstract This study evaluates the performance of deep learning approach in the prediction of the ionospheric total electron content (TEC) during magnetically quiet periods. Two deep learning techniques, long short‐term memory (LSTM) and convolutional LSTM (ConvLSTM), are employed to predict TEC valu...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2023SW003763 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536466152325120 |
|---|---|
| author | Se‐Heon Jeong Woo Kyoung Lee Hyosub Kil Soojeong Jang Jeong‐Heon Kim Young‐Sil Kwak |
| author_facet | Se‐Heon Jeong Woo Kyoung Lee Hyosub Kil Soojeong Jang Jeong‐Heon Kim Young‐Sil Kwak |
| author_sort | Se‐Heon Jeong |
| collection | DOAJ |
| description | Abstract This study evaluates the performance of deep learning approach in the prediction of the ionospheric total electron content (TEC) during magnetically quiet periods. Two deep learning techniques, long short‐term memory (LSTM) and convolutional LSTM (ConvLSTM), are employed to predict TEC values 24 hr ahead in the vicinity of the Korean Peninsula (26.5°–40°N, 121°–134.5°E). The LSTM method predicts TEC at a single point based on time series of data at that point, whereas the ConvLSTM method simultaneously predicts TEC values at multiple points using spatiotemporal distribution of TEC. Both the LSTM and ConvLSTM models are trained using the complete regional TEC maps reconstructed by applying the Deep Convolutional Generative Adversarial Network–Poisson Blending (DCGAN‐PB) method to observed TEC data. The training period spans from 2002 to 2018, and the model performance is evaluated using 2019 data. Our results show that the ConvLSTM method outperforms the LSTM method, generating more reliable TEC maps with smaller root mean square errors when compared to the ground truth (DCGAN‐PB TEC maps). This outcome indicates that deep learning models can improve the prediction accuracy of TEC at a specific point by taking into account spatial information of TEC. We conclude that ConvLSTM is a reliable and efficient approach for the prompt ionospheric prediction. |
| format | Article |
| id | doaj-art-260e5e08229543b09d69acf999c54080 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-260e5e08229543b09d69acf999c540802025-01-14T16:26:56ZengWileySpace Weather1542-73902024-01-01221n/an/a10.1029/2023SW003763Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM ApproachSe‐Heon Jeong0Woo Kyoung Lee1Hyosub Kil2Soojeong Jang3Jeong‐Heon Kim4Young‐Sil Kwak5Korea Astronomy and Space Science Institute Daejeon South KoreaKorea Astronomy and Space Science Institute Daejeon South KoreaJohns Hopkins University Applied Physics Laboratory Laurel MD USAKyung Hee University Yongin South KoreaKorea Astronomy and Space Science Institute Daejeon South KoreaKorea Astronomy and Space Science Institute Daejeon South KoreaAbstract This study evaluates the performance of deep learning approach in the prediction of the ionospheric total electron content (TEC) during magnetically quiet periods. Two deep learning techniques, long short‐term memory (LSTM) and convolutional LSTM (ConvLSTM), are employed to predict TEC values 24 hr ahead in the vicinity of the Korean Peninsula (26.5°–40°N, 121°–134.5°E). The LSTM method predicts TEC at a single point based on time series of data at that point, whereas the ConvLSTM method simultaneously predicts TEC values at multiple points using spatiotemporal distribution of TEC. Both the LSTM and ConvLSTM models are trained using the complete regional TEC maps reconstructed by applying the Deep Convolutional Generative Adversarial Network–Poisson Blending (DCGAN‐PB) method to observed TEC data. The training period spans from 2002 to 2018, and the model performance is evaluated using 2019 data. Our results show that the ConvLSTM method outperforms the LSTM method, generating more reliable TEC maps with smaller root mean square errors when compared to the ground truth (DCGAN‐PB TEC maps). This outcome indicates that deep learning models can improve the prediction accuracy of TEC at a specific point by taking into account spatial information of TEC. We conclude that ConvLSTM is a reliable and efficient approach for the prompt ionospheric prediction.https://doi.org/10.1029/2023SW003763 |
| spellingShingle | Se‐Heon Jeong Woo Kyoung Lee Hyosub Kil Soojeong Jang Jeong‐Heon Kim Young‐Sil Kwak Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach Space Weather |
| title | Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach |
| title_full | Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach |
| title_fullStr | Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach |
| title_full_unstemmed | Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach |
| title_short | Deep Learning‐Based Regional Ionospheric Total Electron Content Prediction—Long Short‐Term Memory (LSTM) and Convolutional LSTM Approach |
| title_sort | deep learning based regional ionospheric total electron content prediction long short term memory lstm and convolutional lstm approach |
| url | https://doi.org/10.1029/2023SW003763 |
| work_keys_str_mv | AT seheonjeong deeplearningbasedregionalionospherictotalelectroncontentpredictionlongshorttermmemorylstmandconvolutionallstmapproach AT wookyounglee deeplearningbasedregionalionospherictotalelectroncontentpredictionlongshorttermmemorylstmandconvolutionallstmapproach AT hyosubkil deeplearningbasedregionalionospherictotalelectroncontentpredictionlongshorttermmemorylstmandconvolutionallstmapproach AT soojeongjang deeplearningbasedregionalionospherictotalelectroncontentpredictionlongshorttermmemorylstmandconvolutionallstmapproach AT jeongheonkim deeplearningbasedregionalionospherictotalelectroncontentpredictionlongshorttermmemorylstmandconvolutionallstmapproach AT youngsilkwak deeplearningbasedregionalionospherictotalelectroncontentpredictionlongshorttermmemorylstmandconvolutionallstmapproach |