AI for Megacities: Understanding the impact of climate extremes

Regional and local-scale extreme events (such as heat waves) will become more frequent over the next few decades, with rising mean temperature and increased climate variability. While climate models capture broad-scale spatial changes in climate phenomena, they struggle to represent extreme events on local scales. Such events are crucial to providing actionable and robust climate information to forecast, among other things, energy demand.

Around 50-55% of the world’s population currently live in cities, accounting for 60-80% of energy consumption worldwide. Current projections estimate the proportion of population living in cities will rise to around 70% by the year 2050, concentrating power infrastructure further. In addition, unique features of cities, such as the urban heat island effect can exacerbate extremes and fuel energy consumption (e.g. for air conditioning). Simultaneously, the occurrence of various types of extreme weather events is expected to increase, presenting a major source of uncertainty for forecasting power generation (e.g., wind turbine efficiencies) and power distribution (e.g., the complete destruction of pylons), and thereby threatening energy security.

The student will apply Bayesian statistics and machine learning in new and innovative ways to help transform the field of environmental data science. There is an abundance of data relevant to the forecasting of power demand (e.g., details of the built environment, socio-economic forecasts) and also human health (mortality rates). However, such data are not routinely incorporated into future climate risk projections.

The student will work closely with members of the Cambridge Machine Learning group and help develop a climate downscaling framework (incorporating probability distribution modelling) to improve the representation of high-impact climate events within localised urban environments. It is expected that the student will provide intellectual input into the project design throughout the project, and lead their own research activities on a daily-to-weekly basis.