Undergraduate, Semester 6, 2025-

• 15 classes in a quarter.

• Exam-based class. 1.5 hrs × 2 days per week.

  • Evaluation: 7 HWs (35%), 2 Midterms (20%), and Final (45%)

• Covering the fundamental compressible fluid dynamics.

Graduate, Summer Intensive Lecture, 2025-

• 12 classes over 3 days.

• Project-based class. 4 classes (90 mins/class) × 3 days.

• Covering 1. fundamentals of numerical simulation (by Prof. Soshi Kawai), 2. data-driven fluid dynamics (by Kai F), and 3. their industrial applications (by a guest lecturer). 

Undergraduate, Semester 6, 2025-

• 15 classes in a quarter.

• Project-based class. 5 hrs per week.

• Covering the fundamentals of Computer Aided Design (CAD).

Undergraduate (IMAC-G), Semester 5, 2025-

• 14 classes in a quarter.

• Report-based class. 1.5 hrs × 2 days per week.

• (For Kai F's class): Covering the fundamentals of data-driven analysis for aerodynamics.

Undergraduate, 2025-

• A quarter-based course.

• Learning literature survey.

• Evaluated with presentation and submission of a summary for a paper.

Undergraduate, 2026

• An omnibus-type course.

• Introducing data-driven fluid mechanics.

Graduate, Spring 2022

• Project-based class. 2 hrs × 2 days per week. 

• Grading for progress and final project reports for all students. 

• TA office hours (2 hrs per week) were also held.  

• Kai F offered 3 lectures about machine learning and fluid mechanics including

  • Lecture 8: Basic applications of supervised learning to fluid flows (overview of Fukami et al., Theor. Comp. Fluid Dyn., 2020)

  • Lecture 9: Coding-based class for machine-learning-based aerodynamic coefficient prediction  and super-resolution reconstruction

  • Lecture 10: Overview of machine-learning-based global flow field reconstruction (generalized super-resolution analysis)

Graduate, Spring 2024

• Kai F offered 3 lectures about machine learning and fluid mechanics including

  • Lecture 4: Regression and neural networks for fluid flows

  • Lecture 5: Convolutional neural networks for fluid flows

  • Lecture 6: Overview of machine-learning-based global flow field reconstruction (generalized super-resolution analysis)