Big data Smart Lab

Professor DAM Hieu-Chi
  • Development of data mining and deep learning methods for analyzing material imaging data
  • Development of similarity measures for mining of materials data
  • Development of interpretable and explainable data-driven AI methods for elucidating physicochemical mechanisms from materials data
Data science, Data-driven AI, Materials Informatics
Research Activities

Development of data science and data-driven AI technologies for analyzing and utilizing big data

Today, there is an urgent need to shorten the time and reduce the cost of materials development. In addition to traditional experimental and computational approaches, new data-driven materials development approaches that extract valuable information and knowledge attract attention. The goal of materials research and development using data science approaches is to quantitatively evaluate the accuracy and uncertainty of results derived from existing data, reduce the number of costly experiments in the search for new materials, and efficiently propose composition combinations and fabrication conditions. To achieve this goal, we focus on developing fundamental and applied technologies of data science adapted to materials science to effectively analyze and utilize measured and computed big data in materials science.