Work

Prediction of Energetic Electrons in the Inner Radiation Belt and Slot Region With a Double‐Layer LSTM Neural Network Model

Year: 2025

Type: article

Abstract: The prediction of high‐energy radiation belt electrons is vital for preventing their damage to satellites. Previous machine learning models mostly predict the fluxes of high‐energy electrons (hundreds of keV to MeV) in the outer radiation belt and slot region (L > 2.6). Here, we trained a double‐layer long short‐term memory (LSTM) neural network model and successfully predicted the spatial and temporal variations of the 108–749 keV electrons in the inner radiation belt (L ∼ 1.2–2.2) and slot region (L ∼ 2.2–3.2). Under different solar or geomagnetic conditions, the prediction efficiency of the present model maintains 0.6–0.99 in the inner belt and slot region, and its prediction error is less than 0.48. The high‐resolution (∼11 s) LSTM model could predict the rapid injection events of high‐energy electrons within several minutes in the radiation belts.

Source: Space Weather

DOI: 10.1029/2024sw004141

Authors: Ling Yang, Liuyuan Li, Jinbin Cao

Institutions: Beihang University, Ministry of Industry and Information Technology

Language: English

Topic: Ionosphere and magnetosphere dynamics

Subfield: Astronomy and Astrophysics

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,000

Funder: National Natural Science Foundation of China