Creating Materials Process Data Science
This research aims to create an interdisciplinary academic field called "Materials Process Data Science" by integrating data science with materials process engineering.
In recent years, data-driven research has gained attention in the field of materials science, but data science focused on material synthesis processes is still in its developing stages. This endowed research division focuses on nanomaterial synthesis processes and aims to systematically elucidate the correlation between process conditions and material properties.
Specific Research Objectives
- Comprehensively construct a materials-process integrated database for nanoparticle synthesis
- Extract process characteristic factors that determine material structure and function from the constructed database
- Establish materials process informatics as a guideline for creating high-performance nanomaterials
Expected Outcomes
This research is expected to facilitate a transition from traditional empirical and trial-and-error material development to efficient data-driven material design. Additionally, optimization of process conditions will enable stable supply of high-quality nanomaterials, with anticipated applications in various fields including energy, environment, and medicine.
Research Approach
We will utilize machine learning and AI technologies to extract significant features from vast amounts of process data. Automated experimental systems will be introduced for experimental data collection to achieve efficient and comprehensive data acquisition. Furthermore, through collaboration with theoretical calculations, we aim to understand process-structure-property correlations at the atomic and molecular level.