点击次数：
DOI码：10.1029/2024SW004141
发表刊物：Space Weather
关键字：Inner radiation belt, Energetic electrons, Machine learning prediction
摘要：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.
第一作者：Ling Yang
论文类型：期刊论文
通讯作者：Liuyuan Li
一级学科：地球物理学
文献类型：期刊
卷号：23
是否译文：否
发表时间：2025-01-22
收录刊物：SCI
发布期刊链接：https://doi.org/10.1029/2024SW004141