2024
Master’s Projects
@Physics/Astronomy
#diffusion models
#image processing
#deconvolution
🎉This project has been accepted at the ML4Physics workshop at NeurIPS!
Project Summary
This project tackles the problem of deconvolving astronomical images to uncover the intrinsic properties of celestial objects, especially in ground-based observations. It explores the use of diffusion models (DMs) and the Diffusion Posterior Sampling (DPS) algorithm to address this challenge. Score-based DMs, trained on high-resolution cosmological simulations, are used in a Bayesian framework to compute posterior distributions based on observations. By incorporating redshift and pixel scale, the method adapts to various datasets. Tests on Hyper Supreme Camera (HSC) data achieve resolutions comparable to Hubble Space Telescope (HST) images, while also quantifying uncertainties and identifying prior-driven features for scientific use.
Alexandre Boucaud
aboucaud@apc.in2p3.fr
- Scientific Software Engineer at Laboratoire Astroparticule et Cosmologie (APC), CNRS
Alessio Spagnoletti
aspagnol@ens-paris-saclay.fr
Marc Huertas-Company
Projects in the same discipline
Deeply Learning from Neutrino Interactions with the KM3NeT neutrino telescope
2022 PhD/ DIAI Projects @AstronomyParticle physics and graph neural networks Santiago PENA MARTINEZ Project Summary A new generation of neutrino experiments is in the horizon looking to explore many of the open questions on neutrino properties and searching for...
Learning the magneto-ionic side of the turbulence in the interstellar medium in radio-astronomy
2022 PhD/DIAI Projects @AstrophysiqueJack Berat(LPENS, UPC)Project Summary The phase transition from warm neutral medium to cold neutral medium in the interstellar medium (ISM) is affected by the magnetic field. The polarization of the synchrotron emission is one of...
Machine Learning for Photometric redshift estimation of LSST galaxies
2023Masters Projects@Physics & Astronomy +Computer Science+Mathematics/Statistics #machine learning#convolutional networks#astrophysics Project Summaryto be updated. Simona Mei Projects in the same discipline
“Search for features in astrophysical objects close to cosmic neutrinos”. An indirect approach to cosmic neutrino association with astrophysical objects
2022Masters Projects@Physics & Astronomy +Computer Science #Neutrino and Gamma-Ray Astronomy#Deep Learning#Real Data Analysis#Data Augmentation Project SummaryThe work proposed here is in the field of Astroparticle Physics, a sub-branch of Physics dealing with the...