We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
72‐Hour Time Series Forecasting of Hourly Relativistic Electron Fluxes at Geostationary Orbit by Deep Learning.
- Authors
Son, Jihyeon; Moon, Yong‐Jae; Shin, Seungheon
- Abstract
In this study, we forecast hourly relativistic (>2 MeV) electron fluxes at geostationary orbit for the next 72 hr using a deep learning model based on multilayer perceptron. The input data of the model are solar wind parameters (temperature, density and speed), interplanetary magnetic field (|B| and Bz), geomagnetic indices (Kp and Dst), and electron fluxes themselves. All input data are hourly averaged ones for the preceding 72 consecutive hours. We use electron flux data from Geostationary Operational Environmental Satellite (GOES)‐15 and ‐16, and perform a mapping for matching these two data. Total period of the data is from 2011 January to 2021 March (GOES‐15 data for 2011–2017 and GOES‐16 data for 2018–2021). We divide the data into training set (January–August), validation set (September), and test set (October–December) to consider the solar cycle effect. Our main results are as follows. First, our model successfully predicts hourly electron fluxes for the next 72 hr. Second, root‐mean‐square error of our model is from 0.18 (for 1 hr prediction) to 0.68 (for 72 hr prediction), and prediction efficiency is from 0.97 to 0.53, which are much better than those of the previous studies. Third, our model well predicts both diurnal variation and sudden increases of electron fluxes associated with fast solar winds and interplanetary magnetic fields. Our study implies that the deep learning model can be applied to forecasting long‐term sequential space weather events. Plain Language Summary: Relativistic electron fluxes (>2 MeV) can damage satellites, resulting in loss of function. Thus, forecasting electron fluxes is a necessary task to minimize the loss. We develop a deep learning model to perform time‐series forecasting of hourly relativistic electron fluxes 3 days ahead. For this, we use solar wind parameters, interplanetary magnetic field, geomagnetic indices, and electron fluxes from Geostationary Operational Environmental Satellite‐15 and ‐16. Our model shows outstanding performances for time series forecasting of electron fluxes in view of metrics. In addition, our model successfully predicts the change of electron fluxes such as diurnal variation and sudden increase. Key Points: A deep learning model based on multilayer perceptron is presented to forecast hourly relativistic (>2 MeV) electron fluxes at geostationary orbit for the next 72 hrThe performance of our model is much better than that of previous studies in view of metrics such as prediction efficiency, root‐mean‐square error, and correlation coefficientOur model successfully predicts the change of electron fluxes such as diurnal variation and sudden increase
- Subjects
GOES (Meteorological satellite); DEEP learning; RELATIVISTIC electrons; INTERPLANETARY magnetic fields; SOLAR wind; ORBITS (Astronomy); TIME series analysis; SPACE environment
- Publication
Space Weather: The International Journal of Research & Applications, 2022, Vol 20, Issue 10, p1
- ISSN
1539-4956
- Publication type
Article
- DOI
10.1029/2022SW003153