Title: Computational materials engineering with active learning
When: Friday, February 27, 2026, 12:00
Place: Department of Theoretical Condensed Matter Physics, Faculty of Sciences, Module 5, Seminar Room (5th Floor)
Speaker: Prof. Milica Todorovic / University of Turku (Finland)
Data-driven materials science based on artificial intelligence (AI) algorithms has facilitated breakthroughs in materials optimization and design. Of particular interest are active learning algorithms, where datasets are collected on-the-fly in the search for optimal solutions. We encoded such a probabilistic algorithm into the Bayesian Optimization Structure Search (BOSS) Python tool for materials research. We utilized this versatile tool to study molecular surface adsorbates, thin film growth, solid-solid interfaces, molecular conformers and even optimise experimental outcomes. New multi-task algorithm developments will allow us to harness the information from different data sources for next-generation materials engineering.
