Machine Learning & Electron Microscopy for Nanoalloys

This project combines deep learning with electron microscopy to improve nanoalloy analysis. By training neural networks on simulated microscope images, we aim to automate the process of identifying nanoalloy structures and properties. This approach could speed up research and development in areas like catalysis, sensing, and data storage technologies.

Stability and Properties of High Entropy Nanoalloys

This project investigates the structure and properties of high entropy nanoalloys through numerical simulation. These materials combine five or more elements in nearly equal proportions making their modelization challenging. By developing novel machine learning approaches for interatomic potential parametrization, we explore how entropy stabilization competes with surface effects at the nanoscale. Our research may help advance energy applications such as hydrogen evolution, carbon dioxide conversion, and rechargeable batteries.