Home Publications Research Achievements
Language
Shota Kato

Shota Kato

PhD (Informatics)

Kyoto, Japan

About Me

I am Shota Kato, an Assistant Professor at Kyoto University, specializing in chemical engineering, machine learning, and natural language processing. My CV is available here.

Experiences

Visiting Researcher

Apr. 2024 – Present · University of Manchester

  • Collaboration with the group of Dr. Dongda Zhang in the Department of Chemical Engineering, Faculty of Science and Engineering.

JST ACT-X Researcher [NextAI-math-info]

Oct. 1, 2023 – Present · JST ACT-X

  • Theme: Development of an automated physical model building AI that understands the terminology and mathematical formulas of manufacturing processes
  • Program homepage

Assistant Professor

Apr. 1, 2022 – Present · Kyoto University

Kyoto University Graduate Division fellow

Oct. 1, 2021 – Mar. 23, 2022 · Kyoto University

Education

Ph.D. in Informatics

2019 – 2022 · Kyoto University

Thesis: Gray-box modeling and model-based control of Czochralski process producing 300 mm diameter Silicon ingots

M.S. in Engineering

2017 – 2019 · Kyoto University

B.S. in Engineering

2013 – 2017 · Kyoto University

Publications

Below are selected publications. For the full list, please visit the Full Publication List page.

Journal Articles

S. Kato and M. Kano. Simple Algorithm for Judging Equivalence of Differential-Algebraic Equation Systems. Scientific Reports, vol. 13, no. 11534. 2023.

S. Kato, S. Kim, M. Kano, T. Fujiwara, and M. Mizuta. Gray-box Modeling of 300 mm Diameter Czochralski Single-crystal Si Production Process. Journal of Crystal Growth, vol. 553, p. 125929. 2021.

Proceedings

K. Nagayama, S. Kato, and M. Kano. Data Augmentation Method Utilizing Template Sentences for Variable Definition Extraction. NLDB, pp. 151–165. 2024.

S. Kato and M. Kano. Prototype of Automated Physical Model Builder: Challenges and Opportunities. Computer Aided Chemical Engineering, vol. 53, pp. 2839–2844. 2024.

Research

AutoPMoB: Automated Physical Model Builder

AutoPMoB is an AI system aiming to automate the construction of physical models from literature information. This theme focuses on developing methods to extract relevant information from papers and build physical models based on textual information. As part of this research, I am also working on AI systems that can understand mathematical expressions.

Data Analysis and NLP for Practical Solutions

This research involves the development of data analysis and natural language processing (NLP) techniques to solve practical issues, such as creating methods for accurately predicting product quality and developing document-based approaches for proactive problem prevention.

Skills

Programming: Python, MATLAB
Domain Knowledge: Chemical Engineering (Process Systems Engineering)
Domain Knowledge: Natural Language Processing and Machine Learning

Hobbies

  • Cycling
  • Drinking (especially whisky and beer)
  • Gaming
  • Anime and Manga