Kwangsik Han
Papers
1
Total Citations
13
H-Index
1
About
Kwangsik Han is a researcher at the forefront of applying machine learning to accelerate materials discovery, with a particular focus on high-throughput experimental methods. His most-cited work, "Machine-Learning-Based phase diagram construction for high-throughput batch experiments" (2022, 13 citations), introduces a novel approach to efficiently map phase diagrams—a critical but time-consuming step in developing new materials. Han developed the PDC (Phase Diagram Construction) package, which leverages uncertainty sampling to intelligently guide experiments, reducing the number of measurements needed while maintaining accuracy. This contribution builds on foundational work by collaborators like K. Terayama, demonstrating Han's ability to integrate computational and experimental strategies. By streamlining the construction of phase diagrams, his research directly addresses a key bottleneck in materials science, enabling faster identification of novel compounds with desirable properties. Though early in his career, Han's work signals a promising trajectory in the intersection of machine learning and materials informatics, offering practical tools for the research community to accelerate the design of advanced materials.
Research Focus
Key Achievements
Top Papers
- 1