Comparative Analysis of TPA‐LSTM and Transformer Models for Forecasting GEO Radiation Belt Electron Fluxes
Abstract The geosynchronous orbit (GEO) is a region filled with energetic electrons and it hosts hundreds of satellites. Electron fluxes at GEO can change sharply within hours, making high‐time‐resolution prediction crucial. In this study, we develop and compare two neural networks for persistent hi...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-11-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2024SW004119 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536491221680128 |
|---|---|
| author | Mengli Tan Xu Si Shangchun Teng Xinming Wu Xin Tao |
| author_facet | Mengli Tan Xu Si Shangchun Teng Xinming Wu Xin Tao |
| author_sort | Mengli Tan |
| collection | DOAJ |
| description | Abstract The geosynchronous orbit (GEO) is a region filled with energetic electrons and it hosts hundreds of satellites. Electron fluxes at GEO can change sharply within hours, making high‐time‐resolution prediction crucial. In this study, we develop and compare two neural networks for persistent high‐time‐resolution prediction: long short‐term memory with temporal pattern attention (TPA‐LSTM) and Transformer. Unlike most previous models, which only output electron fluxes, our models output the same parameters as the inputs, including magnetic local time, solar wind speed, solar wind dynamic pressure, AE, Kp, Dst, the north‐south component of the interplanetary magnetic field, and electron flux data from GOES‐15. The models are trained on approximately six years of data (2012–2016) and validated using about one year of data (2017–2018). We compare the TPA‐LSTM and Transformer models using >0.8 MeV electron fluxes and find that while the Transformer model performs slightly better, the difference is not statistically significant. Considering the Transformer's higher computational cost, we use the TPA‐LSTM model to develop prediction models for electron fluxes of 275, 475, >0.8 MeV, and >2 MeV with a 5‐min resolution at GEO, up to 3 days. The prediction efficiencies (PE) for 275, 475, >0.8 and >2 MeV electron fluxes based on about one year of test data (2018–2019) are 0.799, 0.831, 0.849, 0.881 (1‐day prediction); and 0.551, 0.618, 0.663 and 0.710 (3‐day prediction), respectively. Our high‐time‐resolution persistent models should be useful for both protecting satellites at GEO and serving as boundary conditions for physics‐based radiation belt models. |
| format | Article |
| id | doaj-art-6e908755c26d4adeb295e55620242805 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-6e908755c26d4adeb295e556202428052025-01-14T16:26:51ZengWileySpace Weather1542-73902024-11-012211n/an/a10.1029/2024SW004119Comparative Analysis of TPA‐LSTM and Transformer Models for Forecasting GEO Radiation Belt Electron FluxesMengli Tan0Xu Si1Shangchun Teng2Xinming Wu3Xin Tao4School of Earth and Space Sciences University of Science and Technology of China Hefei ChinaSchool of Earth and Space Sciences University of Science and Technology of China Hefei ChinaNWU‐HKU Joint Center of Earth and Planetary Sciences Department of Earth Sciences The University of Hong Kong Hong Kong ChinaSchool of Earth and Space Sciences University of Science and Technology of China Hefei ChinaSchool of Earth and Space Sciences University of Science and Technology of China Hefei ChinaAbstract The geosynchronous orbit (GEO) is a region filled with energetic electrons and it hosts hundreds of satellites. Electron fluxes at GEO can change sharply within hours, making high‐time‐resolution prediction crucial. In this study, we develop and compare two neural networks for persistent high‐time‐resolution prediction: long short‐term memory with temporal pattern attention (TPA‐LSTM) and Transformer. Unlike most previous models, which only output electron fluxes, our models output the same parameters as the inputs, including magnetic local time, solar wind speed, solar wind dynamic pressure, AE, Kp, Dst, the north‐south component of the interplanetary magnetic field, and electron flux data from GOES‐15. The models are trained on approximately six years of data (2012–2016) and validated using about one year of data (2017–2018). We compare the TPA‐LSTM and Transformer models using >0.8 MeV electron fluxes and find that while the Transformer model performs slightly better, the difference is not statistically significant. Considering the Transformer's higher computational cost, we use the TPA‐LSTM model to develop prediction models for electron fluxes of 275, 475, >0.8 MeV, and >2 MeV with a 5‐min resolution at GEO, up to 3 days. The prediction efficiencies (PE) for 275, 475, >0.8 and >2 MeV electron fluxes based on about one year of test data (2018–2019) are 0.799, 0.831, 0.849, 0.881 (1‐day prediction); and 0.551, 0.618, 0.663 and 0.710 (3‐day prediction), respectively. Our high‐time‐resolution persistent models should be useful for both protecting satellites at GEO and serving as boundary conditions for physics‐based radiation belt models.https://doi.org/10.1029/2024SW004119 |
| spellingShingle | Mengli Tan Xu Si Shangchun Teng Xinming Wu Xin Tao Comparative Analysis of TPA‐LSTM and Transformer Models for Forecasting GEO Radiation Belt Electron Fluxes Space Weather |
| title | Comparative Analysis of TPA‐LSTM and Transformer Models for Forecasting GEO Radiation Belt Electron Fluxes |
| title_full | Comparative Analysis of TPA‐LSTM and Transformer Models for Forecasting GEO Radiation Belt Electron Fluxes |
| title_fullStr | Comparative Analysis of TPA‐LSTM and Transformer Models for Forecasting GEO Radiation Belt Electron Fluxes |
| title_full_unstemmed | Comparative Analysis of TPA‐LSTM and Transformer Models for Forecasting GEO Radiation Belt Electron Fluxes |
| title_short | Comparative Analysis of TPA‐LSTM and Transformer Models for Forecasting GEO Radiation Belt Electron Fluxes |
| title_sort | comparative analysis of tpa lstm and transformer models for forecasting geo radiation belt electron fluxes |
| url | https://doi.org/10.1029/2024SW004119 |
| work_keys_str_mv | AT menglitan comparativeanalysisoftpalstmandtransformermodelsforforecastinggeoradiationbeltelectronfluxes AT xusi comparativeanalysisoftpalstmandtransformermodelsforforecastinggeoradiationbeltelectronfluxes AT shangchunteng comparativeanalysisoftpalstmandtransformermodelsforforecastinggeoradiationbeltelectronfluxes AT xinmingwu comparativeanalysisoftpalstmandtransformermodelsforforecastinggeoradiationbeltelectronfluxes AT xintao comparativeanalysisoftpalstmandtransformermodelsforforecastinggeoradiationbeltelectronfluxes |