Event Details

DSNE seminar with Duncan Watson-Parris, University of Oxford

One of the most pressing climate questions we currently face is that of the effect of anthropogenic aerosol on the climate system, particularly through their interactions with clouds.

Here I will describe recent work using advances in machine learning (ML) to aid in better understanding these interactions. Firstly, by introducing the use of climate model emulation for the reduction of parametric uncertainty in GCMs. And secondly, describing the use of deep convolutional neural networks to look for two particular cloud perturbations in satellite imagery and assess their properties and prevalence, providing valuable insights into their climatic effects. Finally, I will discuss the ways causal ML models can allow us to unpick aerosol-cloud relationships in observations and determine the role of aerosol in driving cloud properties, hence improving our understanding of the changing climate.

Join Microsoft Teams Meeting

Learn more about Teams | Meeting options

By using this service you agree to LU T&Cs - Use the Help Button for tips

Help | Legal