Doctoral Candidate at TU Munich

in uncertainty quantification / machine learning

applied to fluid mechanics

After graduating with first class honours from the University of
York, UK in 2016 with a Bachelor of Science in Mathematics, I obtained a Master of Science in Applied Mathematics from
Imperial College London, UK at the end of 2017. Since November of 2017
I am now a PhD student of Professor Nikolaus A. Adams
at the Chair of Aerodynamics and Fluid Mechanics of the
Technical University of Munich, where I work on the Uncertainty Quantification of Turbulent
Reactive Flows and the application of Scientific Machine Learning to problems originating from Fluid mechanics.

Working with collaborators I combine approaches from classical machine learning, uncertainty quantification and bayesian statistics. The
application of uncertainty quantification in conjunction with bayesian statistics to complex, non-linear turbulent flows uncovers new problems,
such as insurmountable computational costs, which require new, modern approaches such as multifidelity, multiscale approaches and machine learning.
By applying machine learning approaches to more and more complex flow configurations we want to eventually be able to amalgamate the two
approaches and uncover new machine learning algorithms and new insights into the underlying fluid dynamics in the process.