潜在ベクトルとスパース回帰を用いた流れ場時系列解析：

データ駆動型流れ制御に向けて

抄録

Machine learning has recently emerged as a powerful tool for a variety of analyses in fluid mechanics. We here introduce our recent efforts on applications of reduced-order modeling aided by autoencoder and sparse regression to fluid flow data. The present method is able to extract low-dimensional manifolds of fluid flows utilizing autoencoder while deriving its dynamics as an ordinary differential equation with the assistance of sparse identification of nonlinear dynamics. The extension of the present machine-learning-based reduced-order modeling to flow control applications will also be introduced in the talk.