Regensburg 2025 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

SYFD: Symposium Pushing the Boundaries of Fair Data Practices for Condensed Matter Insights: From Workflows to Machine Learning

SYFD 1: Pushing the Boundaries of Fair Data Practices for Condensed Matter Insights

SYFD 1.4: Invited Talk

Wednesday, March 19, 2025, 11:15–11:45, H1

Data-Driven Materials Science for Energy-Sustainable Applications — •Jacqueline Cole — Cavendish Laboratory, University of Cambridge, Cambridge, UK

Data-driven materials discovery is coming of age, given the rise of 'big data' and machine-learning (ML) methods. However, the most sophisticated ML methods need a lot of data to train them. Such data may be custom materials databases that comprise chemical names and their cognate properties for a given functional application; or data may comprise a large corpus of text to train a language model. This talk showcases our home-grown open-source software tools that have been developed to auto-generate custom materials databases for a given application. The presentation will also demonstrate how domain-specific language models can now be used as interactive engines for data-driven materials science. The talk illustrates the application of these data-science methods using case studies from the energy sector. The talk concludes with a forecast of how this 'paradigm shift' away from the use of static databases will likely evolve materials science.

Keywords: energy sustainability; language models; natural language processing; materials science; materials physics