Strong gravitational lensing is a promising probe of the substructure of dark matter to better understand its underlying nature. Deep learning methods have the potential to accurately identify images containing substructure and differentiate WIMP particle dark matter from other well-motivated models, including axions and axion-like particles, warm dark matter, etc.
Traditional simulations of gravitational lensing are time-consuming and require extensive computational resources. This project proposes the use of diffusion models, a class of generative models known for their ability to produce high-quality, detailed images from a distribution of noise, to simulate strong gravitational lensing images. We aim to generate realistic simulations of gravitational lensing events that can be used to augment datasets for machine learning models and facilitate the development of better domain adaptation and self-supervised models aimed at bridging the gap between simulated and real images of gravitational lensing. Furthermore, we will also investigate leveraging conditional diffusion models to generate gravitational lensing simulations by conditioning the model on specific parameters related to the lensing events, such as the mass distribution of the lensing galaxy, orientation, and the redshift of both the source and the lens.
Total project length: 175/350 hours.
Please use this link to access the test for this project.
Please DO NOT contact mentors directly by email. Instead, please email email@example.com with Project Title and include your CV and test results. The relevant mentors will then get in touch with you.