I am currently at Princeton University studying ways to advance science through the use
of machine learning. Previously I was at the Australian National University where I performed numerical experiments and helped develop a code to simulate cosmic ray propagation through turbulent
plasma. I have previously worked as a data scientist/computational statistician in fields of
information geometry and biology.
Currently: PhD student Princeton University
2021: Honours in Astrophysics Australian National University
Major: Computational astrophysics
2020: Bachelor of Mathematics Queensland University of Technology
Major: Applied and computational
2020: Bachelor of Science Queensland University of Technology
Cosmic Ray Transport
Score-based diffusion models
Currently working on a neural network that utalises a score based
diffusion model to perform source seperation on galaxy images. The model succesfully seperates, then reconstructs an
image with individually rendered galaxies, which may then be analysed.
2nd order uncertainty quantification
Neural networks have shown significant promise in helping to solve inverse problems in science,
specifically in the upscaling/inpainting of images in low resolution datasets. However, hallucinations are an unwanted
artifact in these reconstructed images. I am working with my supervisor on a computationally efficient 2nd order method for
quantifying the uncertainty of image features being halluninations.
Cosmic ray diffusion
I also work on simulating cosmic ray propagation, specifically on larger scales where we do not
resolve the cosmic ray gyroradius. I assisted in the development of a propagation code
CRIPTIC with my former supervisors
Mark Krumholz and Roland Crocker.
I'm always happy to talk about astrophysics, machine learning and really anything
Address: Peyton Hall
4 Ivy Lane, Princeton
Public profile links: