Strong gravitational lensing is a powerful tool in exploring various astrophysical questions, including probing the substructure in dark matter haloes of the lensing galaxies. However one of the main limitations of such analysis is the relatively small number of known lens candidates and confirmed lens systems. Recent works have shown the potential of CNNs in the task of lens finding — classification of images obtained from the telescopes into lensed and non-lensed systems. Since the number of real lenses is insufficient for training a machine learning algorithm, training datasets heavily rely on simulations. Even though simulated systems are designed to resemble observational data as closely as possible, there is still a need to bridge the gap between simulated data used for training and real images showing a wider variety of object morphologies.
The goal of this project is to develop and test methods to identify lensed systems in the data from wide-area surveys (such as Hyper Suprime-Cam or Dark Energy Survey) with the focus on applying domain adaptation techniques with simulated data as source and real observational images as target.
Total project length: 175/350 hours.
Python, PyTorch and relevant past experience in Machine Learning.
Please DO NOT contact mentors directly by email. Instead, please email ml4-sci@cern.ch with Project Title and include your CV and test results. The relevant mentors will then get in touch with you.