Energy systems generate diverse datasets, including technical performance data, physical resources; financial market data, infrastructure, energy demand, and the use and perception of energy. Our Energy, date and learning theme seeks to manage and benefit from this data with applications across energy technologies, devices, sciences, and policy.

Energy related data science is highly interdisciplinary, bringing together mathematicians, computer scientists, engineers, human geographers, environmental scientists, legal theorists and ethicists and others. The work here is cross cutting, and includes:

• Climate models are used to predict the impact of climate change on the operation of energy networks and the design and location of renewable energy farms.
• Data on human behaviour in the consumption of energy is collected through the use of sensors, surveys and engagement with citizens and stakeholders, improving energy literacy and co-developing effective energy services and reducing energy waste.
• Using machine learning techniques to propose modified behaviours to help reduce energy use.