Projects

Mass-Mapping with cGANs

My first main PhD project uses a regularised conditional generative adversarial network (rcGAN) and applyies it to weak gravitational lensing convergence map reconstruction. Recent developments in cGANs mean the model is easy to train, and suffers no mode collapse. This code is for the planar setting, and has been tested on the COSMOS field data. Both the code, and a paper on the ArXiV are publicly available.

View my code View the paper

Spherical Mass-Mapping

My current research focuses on spherical mass mapping techniques, watch this space for more details.

S2WAV

S2WAV is a Python package for automatically differentiable wavelet transforms on the sphere. The package is headed by Matt Price, and it was great experience to help develop this package alongside other collaborators Alicja Polanska, and Prof. Jason McEwen.

View the code View the paper

Calibration methods for ML models with uncertainty quantification

Watch this space for a paper very soon talking about coverage and calibration as it relates to MMGAN, and machine learning methods with uncertainty quantification more generally.