Nobuaki Yasuo
Papers
2
Total Citations
19
H-Index
2
About
Nobuaki Yasuo is a rising figure in computational materials science, specializing in the application of Bayesian optimization to accelerate materials synthesis. His research focuses on developing and tuning Bayesian optimization algorithms for navigating the complex, multidimensional parameter spaces—including chemical composition, temperature, and pressure—that are critical to discovering new materials. Yasuo’s major contributions are demonstrated through his highly cited simulation studies, beginning with the foundational one-dimensional case (10 citations) and extending to more realistic two- and three-dimensional scenarios (9 citations). These works systematically address the challenge of optimizing multiple synthesis parameters simultaneously, showing how careful hyperparameter selection can dramatically improve the efficiency of Bayesian optimization in materials exploration. By providing a rigorous, simulation-based framework for tuning these algorithms, Yasuo is helping to bridge the gap between computational optimization and practical laboratory synthesis. His work is particularly valuable for students and researchers seeking to apply machine learning to accelerate the discovery of functional materials, offering clear guidance on how to adapt Bayesian methods to real-world, high-dimensional experimental settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2