PIRSA:24110058

Video URL

https://pirsa.org/24110058

Geometric Machine Learning for cosmological galaxy models

Jespersen, C.K. (2024). Geometric Machine Learning for cosmological galaxy models. Perimeter Institute for Theoretical Physics. https://pirsa.org/24110058

Jespersen, Christian Kragh. Geometric Machine Learning for cosmological galaxy models. Perimeter Institute for Theoretical Physics, Nov. 05, 2024, https://pirsa.org/24110058 

          @misc{ scivideos_PIRSA:24110058,
            doi = {10.48660/24110058},
            url = {https://pirsa.org/24110058},
            author = {Jespersen, Christian Kragh},
            keywords = {Cosmology},
            language = {en},
            title = {Geometric Machine Learning for cosmological galaxy models},
            publisher = {Perimeter Institute for Theoretical Physics},
            year = {2024},
            month = {nov},
            note = {PIRSA:24110058 see, \url{https://scivideos.org/pirsa/24110058}}
          }

Christian Kragh Jespersen Princeton University

Talk numberPIRSA:24110058
DOI10.48660/24110058
Source RepositoryPIRSA
Collection
Talk Type Scientific Series
Subject

Abstract

Galaxies are the medium through which we study the structure of the universe. However, widely applied statistical models of galaxies are generally over-simplified: even recently proposed models cannot capture the dependencies on environment or formation history. To solve this problem, I will introduce Graph Neural Networks (GNNs), a general and ideal tool for physical modelling. Geometrically constrained GNNs vastly improve our models, and allow us to ask detailed questions about the importance of formation history and environment for cosmological galaxy modeling. I will also prove a surprising equivalence between these two aspects of galaxy formation.