Relativistic Electron Flux Prediction at Geosynchronous Orbit Based on the Neural Network and the Quantile Regression Method
Abstract Geosynchronous satellites are exposed to the relativistic electrons, which may cause irreparable damage to the satellites. The prediction of the relativistic electron flux is therefore important for the safety of the satellites. Unlike previous works focusing on the single‐value prediction...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-09-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2020SW002445 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536442787954688 |
|---|---|
| author | Hui Zhang Suiyan Fu Lun Xie Duo Zhao Chao Yue Zuyin Pu Ying Xiong Tong Wu Shaojie Zhao Yixin Sun Bo Cui Zhekai Luo |
| author_facet | Hui Zhang Suiyan Fu Lun Xie Duo Zhao Chao Yue Zuyin Pu Ying Xiong Tong Wu Shaojie Zhao Yixin Sun Bo Cui Zhekai Luo |
| author_sort | Hui Zhang |
| collection | DOAJ |
| description | Abstract Geosynchronous satellites are exposed to the relativistic electrons, which may cause irreparable damage to the satellites. The prediction of the relativistic electron flux is therefore important for the safety of the satellites. Unlike previous works focusing on the single‐value prediction of relativistic electron flux, we predict the relativistic electron flux in a probabilistic approach by using the neural network and the quantile regression method. In this study, a feedforward neural network is first designed to predict average daily flux of relativistic electrons (>2 MeV), or the expectation of the flux from the probabilistic perspective, at geosynchronous orbit 1 day in advance. The neural network performs well, with the average root mean squared error, the average prediction efficiency, and the average linear correlation coefficient between observations and predictions reaching 0.305, 0.832, and 0.916, respectively, during the periods of 2011–2017. We then combine the quantile regression method with the feedforward neural network to predict the quantiles of relativistic electron flux by applying a special loss function to the neural network. We use the multiple‐quantiles prediction model to predict flux ranges of the relativistic electrons and the corresponding probabilities, which is an advantage over the single‐value prediction. Moreover, it appears to be for the first time that the approximate shape of the probability density function of relativistic electron flux is predicted. |
| format | Article |
| id | doaj-art-d58bed9e45b04ab0b19221bba832471d |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2020-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-d58bed9e45b04ab0b19221bba832471d2025-01-14T16:30:54ZengWileySpace Weather1542-73902020-09-01189n/an/a10.1029/2020SW002445Relativistic Electron Flux Prediction at Geosynchronous Orbit Based on the Neural Network and the Quantile Regression MethodHui Zhang0Suiyan Fu1Lun Xie2Duo Zhao3Chao Yue4Zuyin Pu5Ying Xiong6Tong Wu7Shaojie Zhao8Yixin Sun9Bo Cui10Zhekai Luo11School of Earth and Space Sciences Peking University Beijing ChinaSchool of Earth and Space Sciences Peking University Beijing ChinaSchool of Earth and Space Sciences Peking University Beijing ChinaInstitute of Applied Physics and Computational Mathematics Beijing ChinaSchool of Earth and Space Sciences Peking University Beijing ChinaSchool of Earth and Space Sciences Peking University Beijing ChinaSchool of Earth and Space Sciences Peking University Beijing ChinaSchool of Earth and Space Sciences Peking University Beijing ChinaSchool of Earth and Space Sciences Peking University Beijing ChinaSchool of Earth and Space Sciences Peking University Beijing ChinaSchool of Earth and Space Sciences Peking University Beijing ChinaSchool of Earth and Space Sciences Peking University Beijing ChinaAbstract Geosynchronous satellites are exposed to the relativistic electrons, which may cause irreparable damage to the satellites. The prediction of the relativistic electron flux is therefore important for the safety of the satellites. Unlike previous works focusing on the single‐value prediction of relativistic electron flux, we predict the relativistic electron flux in a probabilistic approach by using the neural network and the quantile regression method. In this study, a feedforward neural network is first designed to predict average daily flux of relativistic electrons (>2 MeV), or the expectation of the flux from the probabilistic perspective, at geosynchronous orbit 1 day in advance. The neural network performs well, with the average root mean squared error, the average prediction efficiency, and the average linear correlation coefficient between observations and predictions reaching 0.305, 0.832, and 0.916, respectively, during the periods of 2011–2017. We then combine the quantile regression method with the feedforward neural network to predict the quantiles of relativistic electron flux by applying a special loss function to the neural network. We use the multiple‐quantiles prediction model to predict flux ranges of the relativistic electrons and the corresponding probabilities, which is an advantage over the single‐value prediction. Moreover, it appears to be for the first time that the approximate shape of the probability density function of relativistic electron flux is predicted.https://doi.org/10.1029/2020SW002445relativistic electron fluxprobabilistic forecastfeedforward neural networkquantile regression |
| spellingShingle | Hui Zhang Suiyan Fu Lun Xie Duo Zhao Chao Yue Zuyin Pu Ying Xiong Tong Wu Shaojie Zhao Yixin Sun Bo Cui Zhekai Luo Relativistic Electron Flux Prediction at Geosynchronous Orbit Based on the Neural Network and the Quantile Regression Method Space Weather relativistic electron flux probabilistic forecast feedforward neural network quantile regression |
| title | Relativistic Electron Flux Prediction at Geosynchronous Orbit Based on the Neural Network and the Quantile Regression Method |
| title_full | Relativistic Electron Flux Prediction at Geosynchronous Orbit Based on the Neural Network and the Quantile Regression Method |
| title_fullStr | Relativistic Electron Flux Prediction at Geosynchronous Orbit Based on the Neural Network and the Quantile Regression Method |
| title_full_unstemmed | Relativistic Electron Flux Prediction at Geosynchronous Orbit Based on the Neural Network and the Quantile Regression Method |
| title_short | Relativistic Electron Flux Prediction at Geosynchronous Orbit Based on the Neural Network and the Quantile Regression Method |
| title_sort | relativistic electron flux prediction at geosynchronous orbit based on the neural network and the quantile regression method |
| topic | relativistic electron flux probabilistic forecast feedforward neural network quantile regression |
| url | https://doi.org/10.1029/2020SW002445 |
| work_keys_str_mv | AT huizhang relativisticelectronfluxpredictionatgeosynchronousorbitbasedontheneuralnetworkandthequantileregressionmethod AT suiyanfu relativisticelectronfluxpredictionatgeosynchronousorbitbasedontheneuralnetworkandthequantileregressionmethod AT lunxie relativisticelectronfluxpredictionatgeosynchronousorbitbasedontheneuralnetworkandthequantileregressionmethod AT duozhao relativisticelectronfluxpredictionatgeosynchronousorbitbasedontheneuralnetworkandthequantileregressionmethod AT chaoyue relativisticelectronfluxpredictionatgeosynchronousorbitbasedontheneuralnetworkandthequantileregressionmethod AT zuyinpu relativisticelectronfluxpredictionatgeosynchronousorbitbasedontheneuralnetworkandthequantileregressionmethod AT yingxiong relativisticelectronfluxpredictionatgeosynchronousorbitbasedontheneuralnetworkandthequantileregressionmethod AT tongwu relativisticelectronfluxpredictionatgeosynchronousorbitbasedontheneuralnetworkandthequantileregressionmethod AT shaojiezhao relativisticelectronfluxpredictionatgeosynchronousorbitbasedontheneuralnetworkandthequantileregressionmethod AT yixinsun relativisticelectronfluxpredictionatgeosynchronousorbitbasedontheneuralnetworkandthequantileregressionmethod AT bocui relativisticelectronfluxpredictionatgeosynchronousorbitbasedontheneuralnetworkandthequantileregressionmethod AT zhekailuo relativisticelectronfluxpredictionatgeosynchronousorbitbasedontheneuralnetworkandthequantileregressionmethod |