Coupling a new convection parameterisation trained using high-resolution simulations to the Community Atmospheric Model

A commonly observed issue in general circulation models is biases in the frequency distribution of precipitation, including too much weak rain (the drizzle problem) and either too much or too little heavy precipitation.  High resolution models perform better on this front, but are restricted in the spatial and temporal scales they can simulate.

Previous work (Yuval, O'Gorman, Hill (2021)) demonstrated that training a neural network parameterisation on high-resolution convection-resolving simulations and deploying it within the same model running at lower horizontal resolution can maintain a good representation of precipitation. 

Our work builds on this seeking to redeploy the parameterisation within a global atmospheric model, the Community Atmosphere Model (CAM), as a deep convection scheme, with the aim of running stable simulations with improved precipitation prediction.  To do so requires interfacing the scheme to operate on a different vertical grid using a different system of variables to the original model in which it was trained.

In this talk we will present this work discussing the objectives alongside the challenges faced moving the parameterisation from one model to another.  We share the results from validation in single-column mode against field campaign observations, and of running the scheme globally in an aquaplanet configuration.  We will also discuss software architecture and engineering considerations when seeking to develop and redeploy portable machine-learnt parameterisation schemes.