Gabriel Diaz-Aylwin

Gabriel Diaz-Aylwin, M.A. - University of Lancaster, United Kingdom Atomic Energy Authority

Bayesian Optimization for Fusion Reactor Design

Abstract: I will discuss approaches to adapting the traditional Bayesian optimization loop to the structured but challenging physical environment of tokamak fusion reactors.

In particular, two challenges arise:

First, we have to deal with constraint functions on the state—that is, the solution of a PDE—as opposed to the parameters defining its boundary conditions or residual operator.

Second, we have a range of objective functions, each with varying levels of accuracy and corresponding run times ranging from seconds to weeks.

I will address both challenges by constructing geometry-trust regions and integrating multi-fidelity modeling into the optimization loop.

Biography: Having previously studied mathematics and theoretical physics at the University of Oxford and worked on practical machine learning problems in the aerospace industry, I am currently pursuing a PhD in applied mathematics at the University of Lancaster. Here, I work on computational approaches to engineering design optimization. Specifically, my project focuses on divertor optimization in fusion reactors and is sponsored by the UK Atomic Energy Authority.

‍