Strong gravitational lensing is a powerful tool for studying dark matter and the large-scale structure of the universe. Strong gravitational lensing images encode subtle signatures of dark matter substructure that can distinguish between competing theoretical models (Cold Dark Matter, Axion or Fuzzy Dark Matter, no substructure). While classical deep learning has shown promise in this classification task, the high dimensional feature spaces and complex correlations in lensing images may benefit from quantum computational approaches. This project proposes the development of Quantum Machine Learning (QML) models for dark matter substructure classification. Quantum neural networks leverage quantum phenomena such as superposition and entanglement to explore exponentially large Hilbert spaces, potentially capturing correlations that classical networks miss. Hybrid quantum classical architectures, where quantum circuits serve as trainable feature extractors within classical pipelines, offer a practical near term approach compatible with current NISQ (Noisy Intermediate Scale Quantum) devices.
Total project length: 175/350 hours.
Advanced
Please use this link to access the test for this project.
Please DO NOT contact mentors directly by email. Questions should instead be directed to ml4-sci@cern.ch which is forwarded to mentors. To submit your proposal, CV, and test task solutions, please use this Google form.