Chemical and materials informatics leverages data to correlate a compound’s structure with its properties, enabling the exploration of vast chemical spaces through modeling. Although this approach has the potential to reveal novel materials with desired characteristics, it frequently generates designs that cannot be synthesized, leading to demanding time and resources in experimental attempts. In this talk, I will talk about our recent efforts to build machine learning models to predict inorganic and organic synthesizability and reactivities, and their synthesis pathways. In particular, one important aspect of synthesis prediction is its explainability that can further enhance chemist understanding of synthesis to go beyond the blackbox prediction of most ML models. I will introduce some of recent endeavors to propose explainable models for inorganic and organic synthesis along with the high predictive accuracy.
Biography:
Professor Yousung Jung teaches Chemical and Biological Engineering at Seoul National University. His research background and interests involve quantum chemistry and machine learning to develop efficient methods for fast and accurate simulations of complex molecular and materials systems, and their applications towards the understanding of molecules and materials for new discovery. Some of his recent works include the use of data science and machine learning to understand the structure-property-synthesizability relations for molecules and materials and use the obtained knowledge for inverse design. He received his Ph.D. in Theoretical Chemistry from the University of California, Berkeley, with Martin Head-Gordon. After a postdoctoral work at Caltech with Rudy Marcus, he joined the faculty at KAIST in 2009. He received the Hanseong Science Award from the Hanseong Son Jae Han Foundation, the KAIST Technology Innovation Award, the Pole Medal from the Asia-Pacific Association of Theoretical and Computational Chemists, the Korean Chemical Society Young Physical Chemist Award, and the KCS-Wiley Young Chemist Award. (Source)
