採択課題【詳細】

jh250081	End-to-End Differentiable Fluid-Particle Simulations
課題代表者	John Molina(Kyoto University Dept. Chemical Engineering) John Molina (Kyoto University / Department of Chemical Engineering)
概要	We will develop an end-to-end differentiable direct numerical simulation (DNS) method for solving inverse fluid-particle problems. For this, we will adopt the Smooth Profile Method, which allows us to directly solve the Navier-Stokes equation, while efficiently and accurately accounting for the fluid-particle interactions. The method will be implemented in JAX/Python, which provides Automatic Differentiation support on multi-GPU systems. This will allow us to (1) solve large-scale inverse flow problems (e.g., optimizing for the fluid/particle properties), as well as (2) incorporate the DNS method within existing Machine-Learning frameworks. This will pave the way towards "designer" soft-matter systems, as well as provide a valuable tool to analyze experimental data.
関連Webページ
報告書等	研究紹介ポスター／最終報告書
業績一覧	(1) 学術論文（査読あり）
	該当なし
	(2) 国際会議プロシーディングス（査読あり）
	該当なし
	(3) 国際会議発表（査読なし）
	該当なし
	(4) 国内会議発表（査読なし）
	該当なし
	(5) 公開したライブラリなど
	該当なし
	(6) その他（特許，プレスリリース，著書等）
	該当なし

採択課題 【詳細】