arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.15752astro-ph.IMastro-ph.EP
收藏

利用监督机器学习算法和时间序列基础模型预测地球磁层外辐射带兆电子伏特电子通量

Forecasting megaelectron-volt electron flux in the Earth's outer radiation belt using supervised machine learning algorithms and a timeseries foundation model

Univ Toulouse(图卢兹大学);CNES(法国国家空间研究中心);CNRS(法国国家科学研究中心);IRAP(天体物理研究所);INRIA, Centre Inria Paris(法国国家信息与自动化研究院,巴黎中心);Augura Space(奥古拉航天);CentraleSupélec(中央理工-高等电力学院)

Rungployphan Kieokaew, Ryad Guezzi, François Ginisty, Hadrien Mariaccia

AI总结:

本文提出利用TimesFM与岭回归结合的方法,通过2013-2023年的数据训练,实现了对1MeV电子通量的高精度预测,该方法在L壳层中表现优异,R²值达到0.9,优于其他模型。

摘要:

准确预测地球外辐射带中的兆电子伏特(MeV)电子通量对于减轻卫星风险和航天器操作至关重要。我们开发了一个基于机器学习的预测管道,专注于6小时的预测范围。使用POES NOAA-15测量的降水电子、GOES测量的近1MeV电子通量、太阳风测量以及地磁活动指数作为输入,在2013-2023年间训练了包括线性回归、一维卷积神经网络、长短期记忆神经网络和Transformer-Encoder在内的算法,以预测McIlwain's L壳层2.8至6.0之间的1MeV电子通量,分辨率为0.1。特别地,我们利用时间序列基础模型TimesFM进行零样本预测和混合应用,结合岭回归对过去的动态协变量进行处理,并结合TimesFM对残差进行推断。使用2024年1月至6月的数据作为外样本测试,发现TimesFM与岭回归的混合应用(TimesFM+Cov)在L壳层中表现最佳,平均R²值为0.9,优于其他模型的平均R²值低于0.78。TimesFM+Cov在L壳层2.8至4.7之间保持R²值高于0.9,但在L=6.0时降至0.77,比第二好的模型分别提高了12%和48%。我们的工作提供了一种预训练基础模型如何适应空间天气预测的替代视角。

英文摘要:

Accurate forecasting of megaelectron-volt (MeV) electrons in the outer Earth's radiation belt, which can pose significant risks to satellites, is essential for risk mitigation and spacecraft operations. We develop a machine-learning-based pipeline for forecasting 1-MeV electron flux variations, focusing first on a 6-hour forecast horizon. Using precipitating electrons measured by POES NOAA-15, near 1-MeV electron flux measured by GOES, solar wind measurements near L1, and geomagnetic activity indices as inputs in 2013-2023, we train algorithms including linear regression, 1-D convolutional and long short-term memory neural networks, and Transformer-Encoder to forecast 1-MeV electron flux in McIlwain's L-shells between 2.8 and 6.0 with 0.1 bin resolution. Particularly, we exploit the timeseries foundation model TimesFM for (1) a zero-shot prediction and (2) a hybrid application involving the ridge regression on the past dynamic covariates combined with the TimesFM inference on the residuals. Using data from January-June 2024 as an out-of-sample test, we find that the hybrid application of TimesFM, named TimesFM+Cov, yields the best results with an average R2 of 0.9 across L-shells, compared to an average R2 under 0.78 for all other models. The R2 of TimesFM+Cov remains above 0.9 for L-shells between 2.8 and 4.7 and drops to 0.77 at L=6.0, indicating improvements of 12% at the lowest L-shell and 48% at the highest L-shell compared to our second-best models. Our work offers an alternative perspective on how a pretrained foundation model could be adapted for space weather forecasting.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑