Active learning based acceleration of water-splitting material optimization

Self-driving laboratories are becoming more feasible thanks to the advances in the robotics and machine learning fields. Development of these laboratories to deal with scientific challenges are promising as they can operate faster while being cost and labor efficient. Despite harvesting of renewable energy sources such as solar and wind power is becoming cheaper and more efficient day by day, the storage of the energy is still a crucial challenge in transition to carbon-neutrality. Hydrogen is a viable option for energy storage as storage medium thanks to its energy density and clean conversion. However, cheap hydrogen production from water depends on the quality of a special material used to make the process more efficient. Therefore, this project aims to use machine learning to design new experiments and evaluate the previous data to accelerate optimization and discovery of new materials for green hydrogen storage technologies.

Faculty Supervisor:

Alán Aspuru-Guzik

Student:

Partner:

Forschungszentrum Jülich

Discipline:

Life Sciences

Sector:

Sustainability & the Environment; Environmental Science and Technology

University:

University of Toronto

Program: