Our Research Projects

Predicting ocean dynamics using data-driven methods

This is a project which is currently making use of HPC facilities at Newcastle University. It is active.

Project Contacts

For further information about this project, please contact:


Project Description

The goal of this project is to run idealised numerical simulations augmented by machine-learning-driven forcing terms. This forcing will represent unresolved small-scale processes and allow for low resolution simulations to include effects that would normally require high resolution to model.



Simulations will consist of:



highly parallelised jobs using Python (Dedalus)

GPU simulations and machine learning using Python (JAX) and Julia (Oceananigans, GeophysicalFlows)


Software or Compute Methods

Julia (with Oceananigans and GeophysicalFlows packages)

Python (Anaconda with Pytorch, CUDA, Dedalus, JAX)

Matlab (for data processing and visualisation)