Ira is studying for a PhD, under the supervision of Professor Peter Haynes FRS and Professor Rich Kerswell FRS, as part of the Atmosphere-Ocean Dynamics group and as part of the UKRI Centre for Doctoral Training in the Application of Artificial Intelligence to the study of Environmental Risks.

Research

Ira's research is currently focused on using Machine Learning to determine the predictive nature of turbulent fluid flows, specifically investigating the Beta-Plane System - an idealised model analogous to the tropospheric mid-latitudinal regions of our atmosphere, that govern jet streams.

We are using Machine Learning to learn the dynamics of the system in order to produce a forecast or long-term emulation that can dramatically reduce the associated computational cost compared to numerical integration. In learning the underlying dynamics we use Machine Learning to find a Reduced Order Model to find the inertial manifold that the system lies on, however, the Beta-Plane System is a stochastically forced system with a non-stationary manifold, requiring a probabilistic map - more information can be found here.