From Edison's trial-and-error approach to the inverse design of materials and molecules

DESCRIPTION

The goals of this chair are to develop methods to dramatically accelerate the rate at which new materials can be discovered. We will do this using a two-pronged strategy. On the one hand, we will use physics-informed equivariant neural networks to accelerate quantum mechanical calculations of material properties in the search for new spin-crossover materials. On the other hand, we will use generative modeling to train machine learning models to propose entirely new atomic arrangements that are statistically likely to possess the material properties we are seeking. Together, these represent a significant step forward for the field and will be part of a transformation in the way we discover new materials.

CHAIR ACTIVITIES

Two PhDs have been hired, one to work on "the development of physics-based machine learning models for accelerated materials discovery" and the other on "the development of generative machine learning methods for the inverse design of materials and molecules."

CHAIR EVENTS

Upcoming invited talk at the "Machine Learning Interatomic Potentials: Theory and Practice" conference, November 6–10, Helsinki, Finland.

Published on October 13, 2026
Updated on October 13, 2026