profile

Nationality

Japanese

Language

Japanese (Native)
English (Fluent)
French (Intermediate)

Education

Ph.D. in Engineering, Kyoto University, 2021
Visiting student, EPFL, 2019.6-9
M.S. Architecture, Kyoto University, 2018
Visiting Student, Massachusetts Institute of Technology, 2017.1-3
B.S. Architecture, Kyoto University, 2016

Experience

Assistant Professor, Kyoto University, 2021-

Specialty

Architectural Design
Structural Optimization
Computational Morphogenesis
Data Analysis
Machine Learning
Graph Embedding
Discrete Differential Geometry

Licensure

passed P.E. exam
1st-class Kenchikushi (Japanese architect license)

Programming

Fortran
Python
C#
Matlab
JavaScript

Awards

Best presentation award for young researchers, Annual Convention of Architectural Institute of Japan (AIJ), Nov. 2, 2022.
Young Encouragement Award, Kyoto University, Sep. 22, 2022.
Hangai Prize, International Association for Shell and Spatial Structures (IASS), Sep. 19, 2022.
Best Presentation Award, Machine learning model using graph embedding for extracting features of skeletal structures, the 66th National Congress of Theoretical and Applied Mechanics, The Japan Federation of Engineering Societies (JFES) Theoretical Applied Mechanics Consortium, Jul. 29, 2022.
AIJISA Young Presentation Award, 43rd symposium on Computer Technology of Information, Systems and Applications, Architectural Institute of Japan (AIJ), Dec. 11, 2020.
Best student paper award, Asian Congress of Structural and Multidisciplinary Optimization (ACSMO), Nov. 23, 2020.
1st prize, International Student Competition in Structural Optimization (ISCSO), Dec. 15, 2019.
Best presentation award for young researchers, Annual Convention of Architectural Institute of Japan (AIJ), Nov. 26, 2018.
Highest prize, the structural design competition in the symposium of Subcommittee on Computational Morphogenesis, Oct. 19, 2018.
Honor Prize (master thesis), Kyoto University, Jun. 21, 2018.
Best 100, SDA Award, Nov. 17, 2017. →See this project.
Best presentation award for young researchers, Annual Convention of Architectural Institute of Japan (AIJ), Oct. 16, 2017.
Best presentation award, the symposium of Subcommittee on Computational Morphogenesis, Oct. 28, 2016.
Honor Prize (diploma design), Kyoto University, Feb. 17, 2016. →See this project.

Journal papers

Kazuki Hayashi, Yoshiki Jikumaru, Makoto Ohsaki, Takashi Kagaya, Yohei Yokosuka, Mean curvature flow for generating discrete surfaces with piecewise constant mean curvatures, Computer Aided Geometric Design, 2023.
Kazuki Hayashi, Makoto Ohsaki, Masaya Kotera, Assembly sequence optimization of spatial trusses using graph embedding and reinforcement learning. Journal of International Association for Shell and Spatial Structures, 2022.
Shaojun Zhu, Makoto Ohsaki, Kazuki Hayashi, Shaohan Zong, Xiaonong Guo, Deep reinforcement learning-based critical element identification and demolition planning of frame structures. Frontiers of Civil and Structural Engineering, 2022.
Chi-tathon Kupwiwat, Kazuki Hayashi, Makoto Ohsaki, Deep deterministic policy gradient and graph convolutional network for bracing direction optimization of grid shells. Frontiers in Built Environment, 2022.
Kazuki Hayashi, Makoto Ohsaki. Graph-based reinforcement learning for discrete cross-section optimization of planar steel frames. Advanced Engineering Informatics, Volume 51, 2022.
Kazuki Hayashi, Makoto Ohsaki. Reinforcement learning for optimum design of a plane frame under static loads. Engineering with Computers, Volume 37, pp. 1999-2011, 2021.
Shaojun Zhu, Makoto Ohsaki, Kazuki Hayashi, Xiaonong Guo, Machine-specified ground structures for topology optimization of binary trusses using graph embedding policy network, Advances in Engineering Software, 2021.
Kazuki Hayashi, Yoshiki Jikumaru, Makoto Ohsaki, Takashi Kagaya, Yohei Yokosuka, Discrete Gaussian curvature flow for piecewise constant Gaussian curvature surface, Computer-Aided Design, 2021.
Hiroto Ota, Takuya Ito, Kazuki Hayashi. Design review system with “Live AHP” to visualize and share jury’s own decision evaluation. The AIJ Journal of Technology and Design, Volume 27, Number 65, pp. 562-567, 2021 (in Japanese).
Kazuki Hayashi, Makoto Ohsaki. Reinforcement learning and graph embedding for binary topology optimization under stress and displacement constraints. Frontiers in Built Environment, 2020.
Kazuki Hayashi, Makoto Ohsaki. FDMopt: Force density method for optimal geometry and topology of trusses. Advances in Engineering Software, Volume 133, pp.12-19, 2019.
Makoto Ohsaki, Kazuki Hayashi. Force density method for simultaneous optimization of geometry and topology of trusses. Structural and Multidisciplinary Optimization, pp.1-12, 2017.

Journal Reviewer

(International journal)

(Japanese journal)