The goal of this thesis is to apply deep learning to the detection of galaxy clusters in astronomical surveys.  Clusters are the most massive objects in the universe, hosting hundreds of galaxies and a gaseous intra-cluster medium (ICM) at temperatures of tens of millions of Kelvin.  They are detected as galaxy over-densities in optical/near-infrared (NIR) imaging, through the X-ray emission of their ICM or via the Sunyaev-Zeldovich (SZ) effect, a distortion of the cosmic microwave background spectrum generated by photon-electron scattering in the ICM.  Clusters serve as powerful probes of

Many popular theories of the early Universe predict that gravitational waves were generated in the very first moments of its life. These theories generally invoke new physics from beyond the standard model of the particle physics and the primordial gravitational waves are believed to carry clues about the nature of those new physics laws. Detecting the primordial gravitational waves would thus have revolutionary impact on our understanding of cosmology and fundamental physics.

During the last decade, cosmology has entered a precision era, leading to the prevalence of the standard cosmological model, ΛCDM. Nevertheless the main ingredient of this model, dark energy, while dominating the energy budget of our Universe, remains mysterious and its comprehension is the current Graal of the domain.

L’étude des fluctuations polarisées du rayonnement fossile à 3K (Cosmic Microwave Background, CMB) apparaît aujourd’hui comme une voie incontournable pour progresser dans notre compréhension de l’Univers. Le niveau de signal attendu, quelques nK pour le mode B le plus faible, requiert une chaîne de détection à la fois ultra sensible et extrêmement immune aux effets parasites instrumentaux.