Toward the surrogate model for REPPU auroral ionosphere ver3 (SMRAI3)

Ryuho Kataoka; Shin ya Nakano; Shigeru Fujita; Aoi Nakamizo

Presentation information

[E] Poster

P (Space and Planetary Sciences ) » P-EM Solar-Terrestrial Sciences, Space Electromagnetism & Space Environment

[P-EM11] Space Weather and Space Climate

Mon. May 27, 2024 5:15 PM - 6:45 PM Poster Hall (Exhibition Hall 6, Makuhari Messe)

convener:Ryuho Kataoka(National Institute of Polar Research), Mary Aronne(NASA Goddard Space Flight Center), Yumi Bamba(National Institute of Information and Communications Technology), Antti Pulkkinen(NASA Goddard Space Flight Center)

5:15 PM - 6:45 PM

[PEM11-P23] Toward the surrogate model for REPPU auroral ionosphere ver3 (SMRAI3)

*Ryuho Kataoka¹, Shin ya Nakano², Shigeru Fujita², Aoi Nakamizo³ (1.National Institute of Polar Research, 2.ISM, 3.NICT)

Keywords:aurora, machine learning

Physics-based auroral current-system 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. 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, named the surrogate model for REPPU auroral Ionosphere version 2 (SMRAI2, doi.org/10.1029/2023SW003720). We show the current development status to discuss further improvement.