Predicting battery recycling processes

The extraction of transition metals from oxides is a cost-determining step in the recycling of spent lithium-ion batteries. The Urban group has been developing methods for the computational design of more energy-efficient metal-extraction processes using a combination of atomic-scale first-principles calculations, materials theory, and machine learning.

We are looking for a summer student with interest in data science for the integration of different models that we have developed and for help with the design of a web application for the interactive prediction of metal extraction. As a summer student, you will learn about the working principles of lithium-ion batteries and metal recycling, and you will employ data-science methods (Gaussian process and tree-based models) to data from atomistic first-principles calculations. You will conduct research on the integration of models for the prediction of different thermodynamic properties.