Rapid Assessment of Materials Properties for Reversible Solid Oxide Fuel Cells through Machine Learning

To address the urgent problem of climate change, it is important to look for alternatives to fossil fuels. Renewable energy sources, such as solar or wind power, are attractive but are often criticized for being intermittent: the energy produced varies with time of day or season of the year. There is a mismatch between the availability of the energy produced and the demand based on usage patterns. Thus, renewable energy is still underutilized. Reversible solid oxide fuel cells are devices that convert the electrical energy and store it as chemical energy, and then release it back as electrical energy upon demand. But they can degrade under the harsh conditions of their operation. They can be improved if more robust components of these devices can be developed, but there are many possible candidates. This proposal applies artificial intelligence methods to rapidly search for new materials to make these devices more reliable.

Faculty Supervisor:

Arthur Mar

Student:

Partner:

SeeO2 Energy

Discipline:

Physics

Sector:

Professional, scientific and technical services

University:

University of Alberta

Program: