Ionospheric space weather forecast by the data assimilation of SuperDARN data with AI emulator

片岡 龍峰; 中野 慎也; 藤田 茂; 中溝 葵

講演情報

[E] ポスター発表

セッション記号 P (宇宙惑星科学) » P-EM 太陽地球系科学・宇宙電磁気学・宇宙環境

[P-EM10] Space Weather and Space Climate

2025年5月27日(火) 17:15 〜 19:15 ポスター会場 (幕張メッセ国際展示場 7・8ホール)

コンビーナ:片岡龍峰(国立極地研究所)、Pulkkinen Antti(NASA Goddard Space Flight Center)、Aronne Mary(NASA GSFC/CUA)、伴場由美(国立研究開発法人　情報通信研究機構)

17:15 〜 19:15

[PEM10-P19] Ionospheric space weather forecast by the data assimilation of SuperDARN data with AI emulator

*片岡龍峰¹、中野慎也²、藤田茂²、中溝葵³ (1.国立極地研究所、2.統計数理研究所、3.情報通信研究機構)

キーワード：機械学習、宇宙天気予報、データ同化

Physics-based auroral simulations, such as Japanese REProduce Plasma Universe (REPPU) code, are not practically fast enough for the purpose of real-time space weather forecast, even using the designated super computers. Here we developed a million-times-faster “emulator” to surrogate the outputs of the physics-based simulation, using the machine-learning technique called Echo State Network. The newly developed emulator, the surrogate model for REPPU auroral Ionosphere version 2 (SMRAI2), enables us to realize the real-time space weather forecast of the auroral current system as well as emsemble forecast and data assimilation forecast. In this talk we show several examples rather than technical details.