Study the galaxy distribution characterisation via Bayesian statistical learning of spatial marked point processes
Résumé
Galaxies are not uniformly distributed in the observable Universe. Their positions induce structures such as filaments, void zones or even clusters of galaxies. The complexity of these structures and the amount of data available on the subject led to the idea of a probabilistic approach to explain the characteristics of these structures, based on point process models ([7] , [5]). An important part of this probabilistic framework is to use algorithms able to estimate the parameters of the models proposed to fit the observed data such as Approximate Bayesian Computation (ABC) algorithms ([3, 8, 10]).
Origine | Fichiers produits par l'(les) auteur(s) |
---|