Machine Learning for the Relationship of High-Energy Electron Flux between GEO and MEO with Application to Missing Values Imputation for Beidou MEO Data

We consider the problem of building the relationship of high-energy electron flux between Geostationary Earth Orbit (GEO) and Medium Earth Orbit (MEO). A time-series decomposition technique is first applied to the original data, resulting in trend and detrended part for both GEO and MEO data. Then w...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Cui Ruifei, Jiang Yu, Tian Chao, Zhang Riwei, Hu Sihui, Li Jiyun
Formato:	article
Lenguaje:	EN
Publicado:	De Gruyter 2021
Materias:	high-energy electron flux geo/meo time-series decomposition random forest feature extraction moving block missing values Astronomy QB1-991
Acceso en línea:	https://doaj.org/article/5ee8cd57e0584634ba0c05f2cc48a084
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5ee8cd57e0584634ba0c05f2cc48a084
record_format	dspace
spelling	oai:doaj.org-article:5ee8cd57e0584634ba0c05f2cc48a0842021-12-05T14:10:40ZMachine Learning for the Relationship of High-Energy Electron Flux between GEO and MEO with Application to Missing Values Imputation for Beidou MEO Data2543-637610.1515/astro-2021-0008https://doaj.org/article/5ee8cd57e0584634ba0c05f2cc48a0842021-11-01T00:00:00Zhttps://doi.org/10.1515/astro-2021-0008https://doaj.org/toc/2543-6376We consider the problem of building the relationship of high-energy electron flux between Geostationary Earth Orbit (GEO) and Medium Earth Orbit (MEO). A time-series decomposition technique is first applied to the original data, resulting in trend and detrended part for both GEO and MEO data. Then we predict MEO trend with GEO data using three machine learning models: Linear Regression (LR), Random Forest (RF), and Multi-Layer Perceptron (MLP). Experiment shows that RF gains best performance in all scenarios. Feature extraction analysis demonstrates that the inclusion of lagged features and (possible) ahead features is substantially helpful to the prediction. At last, an application of imputing missing values for MEO data is presented, in which RF model with selected features is used to handle the trend part while a moving block method is for the detrended part.Cui RuifeiJiang YuTian ChaoZhang RiweiHu SihuiLi JiyunDe Gruyterarticlehigh-energy electron fluxgeo/meotime-series decompositionrandom forestfeature extractionmoving blockmissing valuesAstronomyQB1-991ENOpen Astronomy, Vol 30, Iss 1, Pp 62-72 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	high-energy electron flux geo/meo time-series decomposition random forest feature extraction moving block missing values Astronomy QB1-991
spellingShingle	high-energy electron flux geo/meo time-series decomposition random forest feature extraction moving block missing values Astronomy QB1-991 Cui Ruifei Jiang Yu Tian Chao Zhang Riwei Hu Sihui Li Jiyun Machine Learning for the Relationship of High-Energy Electron Flux between GEO and MEO with Application to Missing Values Imputation for Beidou MEO Data
description	We consider the problem of building the relationship of high-energy electron flux between Geostationary Earth Orbit (GEO) and Medium Earth Orbit (MEO). A time-series decomposition technique is first applied to the original data, resulting in trend and detrended part for both GEO and MEO data. Then we predict MEO trend with GEO data using three machine learning models: Linear Regression (LR), Random Forest (RF), and Multi-Layer Perceptron (MLP). Experiment shows that RF gains best performance in all scenarios. Feature extraction analysis demonstrates that the inclusion of lagged features and (possible) ahead features is substantially helpful to the prediction. At last, an application of imputing missing values for MEO data is presented, in which RF model with selected features is used to handle the trend part while a moving block method is for the detrended part.
format	article
author	Cui Ruifei Jiang Yu Tian Chao Zhang Riwei Hu Sihui Li Jiyun
author_facet	Cui Ruifei Jiang Yu Tian Chao Zhang Riwei Hu Sihui Li Jiyun
author_sort	Cui Ruifei
title	Machine Learning for the Relationship of High-Energy Electron Flux between GEO and MEO with Application to Missing Values Imputation for Beidou MEO Data
title_short	Machine Learning for the Relationship of High-Energy Electron Flux between GEO and MEO with Application to Missing Values Imputation for Beidou MEO Data
title_full	Machine Learning for the Relationship of High-Energy Electron Flux between GEO and MEO with Application to Missing Values Imputation for Beidou MEO Data
title_fullStr	Machine Learning for the Relationship of High-Energy Electron Flux between GEO and MEO with Application to Missing Values Imputation for Beidou MEO Data
title_full_unstemmed	Machine Learning for the Relationship of High-Energy Electron Flux between GEO and MEO with Application to Missing Values Imputation for Beidou MEO Data
title_sort	machine learning for the relationship of high-energy electron flux between geo and meo with application to missing values imputation for beidou meo data
publisher	De Gruyter
publishDate	2021
url	https://doaj.org/article/5ee8cd57e0584634ba0c05f2cc48a084
work_keys_str_mv	AT cuiruifei machinelearningfortherelationshipofhighenergyelectronfluxbetweengeoandmeowithapplicationtomissingvaluesimputationforbeidoumeodata AT jiangyu machinelearningfortherelationshipofhighenergyelectronfluxbetweengeoandmeowithapplicationtomissingvaluesimputationforbeidoumeodata AT tianchao machinelearningfortherelationshipofhighenergyelectronfluxbetweengeoandmeowithapplicationtomissingvaluesimputationforbeidoumeodata AT zhangriwei machinelearningfortherelationshipofhighenergyelectronfluxbetweengeoandmeowithapplicationtomissingvaluesimputationforbeidoumeodata AT husihui machinelearningfortherelationshipofhighenergyelectronfluxbetweengeoandmeowithapplicationtomissingvaluesimputationforbeidoumeodata AT lijiyun machinelearningfortherelationshipofhighenergyelectronfluxbetweengeoandmeowithapplicationtomissingvaluesimputationforbeidoumeodata
_version_	1718371841964244992

Machine Learning for the Relationship of High-Energy Electron Flux between GEO and MEO with Application to Missing Values Imputation for Beidou MEO Data

Ejemplares similares