Prediction Models of ≥2 MeV Electron Daily Fluences for 3 Days at GEO Orbit Using a Long Short-Term Memory Network
Geostationary satellites are exposed to harsh space weather conditions, including ≥2 MeV electrons from the Earth’s radiation belts. To predict ≥2 MeV electron daily fluences at 75°W and 135°W at geostationary orbit for the following three days, long short-term memory (LSTM) network models have been...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-05-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/10/2538 |
_version_ | 1797598440014741504 |
---|---|
author | Xiaojing Sun Ruilin Lin Siqing Liu Bingxian Luo Liqin Shi Qiuzhen Zhong Xi Luo Jiancun Gong Ming Li |
author_facet | Xiaojing Sun Ruilin Lin Siqing Liu Bingxian Luo Liqin Shi Qiuzhen Zhong Xi Luo Jiancun Gong Ming Li |
author_sort | Xiaojing Sun |
collection | DOAJ |
description | Geostationary satellites are exposed to harsh space weather conditions, including ≥2 MeV electrons from the Earth’s radiation belts. To predict ≥2 MeV electron daily fluences at 75°W and 135°W at geostationary orbit for the following three days, long short-term memory (LSTM) network models have been developed using various parameter combinations. Based on the prediction efficiency (PE) values, the most suitable time step of inputs and best combinations of two or three input parameters of models for predictions are recommended. The highest PE values for the following three days with three input parameters were 0.801, 0.658 and 0.523 for 75°W from 1995 to August 2010, and 0.819, 0.643 and 0.508 for 135°W from 1999 to 2010. Based on yearly PE values, the performances of the above models show the solar cycle dependence. The yearly PE values are significantly inversely correlated with the sunspot number, and they vary from 0.606 to 0.859 in predicting the following day at 75°W from 1995 to 2010. We have proven that the poor yearly PE is related to relativistic electron enhancement events, and the first day of events is the most difficult to predict. Compared with previous models, our models are comparable to the top performances of previous models for the first day, and significantly improve the performance for second and third days. |
first_indexed | 2024-03-11T03:21:15Z |
format | Article |
id | doaj.art-3a4d498531df4fb9b43ec19678c8e437 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-11T03:21:15Z |
publishDate | 2023-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-3a4d498531df4fb9b43ec19678c8e4372023-11-18T03:06:32ZengMDPI AGRemote Sensing2072-42922023-05-011510253810.3390/rs15102538Prediction Models of ≥2 MeV Electron Daily Fluences for 3 Days at GEO Orbit Using a Long Short-Term Memory NetworkXiaojing Sun0Ruilin Lin1Siqing Liu2Bingxian Luo3Liqin Shi4Qiuzhen Zhong5Xi Luo6Jiancun Gong7Ming Li8State Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaState Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaState Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaState Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaState Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaState Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaShandong Institute of Advanced Technology (SDIAT), Jinan 250100, ChinaKey Laboratory of Science and Technology on Environmental Space Situation Awareness, Chinese Academy of Sciences, Beijing 100190, ChinaState Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing 100190, ChinaGeostationary satellites are exposed to harsh space weather conditions, including ≥2 MeV electrons from the Earth’s radiation belts. To predict ≥2 MeV electron daily fluences at 75°W and 135°W at geostationary orbit for the following three days, long short-term memory (LSTM) network models have been developed using various parameter combinations. Based on the prediction efficiency (PE) values, the most suitable time step of inputs and best combinations of two or three input parameters of models for predictions are recommended. The highest PE values for the following three days with three input parameters were 0.801, 0.658 and 0.523 for 75°W from 1995 to August 2010, and 0.819, 0.643 and 0.508 for 135°W from 1999 to 2010. Based on yearly PE values, the performances of the above models show the solar cycle dependence. The yearly PE values are significantly inversely correlated with the sunspot number, and they vary from 0.606 to 0.859 in predicting the following day at 75°W from 1995 to 2010. We have proven that the poor yearly PE is related to relativistic electron enhancement events, and the first day of events is the most difficult to predict. Compared with previous models, our models are comparable to the top performances of previous models for the first day, and significantly improve the performance for second and third days.https://www.mdpi.com/2072-4292/15/10/2538≥2 MeV electron daily fluencesgeostationary orbitprediction model of high-energy electronmachine learningLSTM |
spellingShingle | Xiaojing Sun Ruilin Lin Siqing Liu Bingxian Luo Liqin Shi Qiuzhen Zhong Xi Luo Jiancun Gong Ming Li Prediction Models of ≥2 MeV Electron Daily Fluences for 3 Days at GEO Orbit Using a Long Short-Term Memory Network Remote Sensing ≥2 MeV electron daily fluences geostationary orbit prediction model of high-energy electron machine learning LSTM |
title | Prediction Models of ≥2 MeV Electron Daily Fluences for 3 Days at GEO Orbit Using a Long Short-Term Memory Network |
title_full | Prediction Models of ≥2 MeV Electron Daily Fluences for 3 Days at GEO Orbit Using a Long Short-Term Memory Network |
title_fullStr | Prediction Models of ≥2 MeV Electron Daily Fluences for 3 Days at GEO Orbit Using a Long Short-Term Memory Network |
title_full_unstemmed | Prediction Models of ≥2 MeV Electron Daily Fluences for 3 Days at GEO Orbit Using a Long Short-Term Memory Network |
title_short | Prediction Models of ≥2 MeV Electron Daily Fluences for 3 Days at GEO Orbit Using a Long Short-Term Memory Network |
title_sort | prediction models of ≥2 mev electron daily fluences for 3 days at geo orbit using a long short term memory network |
topic | ≥2 MeV electron daily fluences geostationary orbit prediction model of high-energy electron machine learning LSTM |
url | https://www.mdpi.com/2072-4292/15/10/2538 |
work_keys_str_mv | AT xiaojingsun predictionmodelsof2mevelectrondailyfluencesfor3daysatgeoorbitusingalongshorttermmemorynetwork AT ruilinlin predictionmodelsof2mevelectrondailyfluencesfor3daysatgeoorbitusingalongshorttermmemorynetwork AT siqingliu predictionmodelsof2mevelectrondailyfluencesfor3daysatgeoorbitusingalongshorttermmemorynetwork AT bingxianluo predictionmodelsof2mevelectrondailyfluencesfor3daysatgeoorbitusingalongshorttermmemorynetwork AT liqinshi predictionmodelsof2mevelectrondailyfluencesfor3daysatgeoorbitusingalongshorttermmemorynetwork AT qiuzhenzhong predictionmodelsof2mevelectrondailyfluencesfor3daysatgeoorbitusingalongshorttermmemorynetwork AT xiluo predictionmodelsof2mevelectrondailyfluencesfor3daysatgeoorbitusingalongshorttermmemorynetwork AT jiancungong predictionmodelsof2mevelectrondailyfluencesfor3daysatgeoorbitusingalongshorttermmemorynetwork AT mingli predictionmodelsof2mevelectrondailyfluencesfor3daysatgeoorbitusingalongshorttermmemorynetwork |