On 7/4/2025, CASTRO Michael, Sakai lab, Department of Nuclear Engineering and Management, (D1), received the “Best Poster Award” at the 10th International Conference on Discrete Element Methods (DEM10).

〈Name of award and short explanation about the award〉

Best Poster Award

This award is given to young researchers who delivered outstanding poster presentations at the 10th International Conference on Discrete Element Methods (DEM10).

〈About awarded research〉

Poster Title: Reduced-order Modeling of Heat Transfer in Gas–Solid Flows with Deep Learning

Summary: Particle-fluid flows with heat transfer are important in many industrial processes, such as fluidized beds for heating and cooling, and high temperature gas cooled reactors. Reduced-order models (ROM) of such systems can be used to create digital twins, which are useful for model predictive control. In this work, we created ROMs of a fluidized bed to time forecast and parameterize the fluid and particle temperatures in a fluidized bed. The ROM was created via proper orthogonal decomposition (POD) and neural networks. The ROM was able to forecast and parametrize the temperatures orders-of-magnitude faster than a full-order model.

〈Your impression & future plan〉

I am honored to have received the “Best Poster Award”. I am also thankful to the members of Sakai Laboratory, especially Professor Mikio SAKAI, Project Assistant Professor Shuo LI, Project Researcher Dr. Toshiki IMATANI, and Mr. Kai-en YANG for their guidance and contribution toward this research.