Materials Intelligence

Rhone Group at a glance

Artificial intelligence for materials

The Rhone research group is at the intersection of materials science and artificial intelligence. Machine learning tools are exploited to uncover hidden patterns in materials data and to predict new materials with novel properties for advances in science and industrial innovation.

High-throughput DFT calculations

High-throughput density functional theory (DFT) calculations are used to simulate the materials properties of quantum materials. The resulting data are used to create a database of materials properties that are used to perform screening for materials discovery and to train machine learning models.

Quantum Materials

We explore emergent phenomena in correlated quantum systems. In particular, we focus on spin properties and magnetic ordering of layered materials with intrinsic magnetic order.

Materials characterization

Experimental probes are used to confirm both AI predictions and first principles calculations of materials properties. In particular, Kerr spectroscopy is used to interrogate magnetic order of van der Waals materials down to a single atomic layer.