Oral Presentation

Exploring the Link Between the Star Formation History and the Morphology of Galaxies in the SDSS-IV MaNGA Survey Using CNNs

Author(s): Alfonzo Juan Pablo (University of Toronto/ Tohoku University), Iyer Kartheik (University of Toronto/Columbia University), Akiyama Masayuki (Tohoku University)

Presenter: Juan Pablo Alfonzo (Tohoku University (東北大学）)

We study the connection between the factors regulating star formation in galaxies on different spatial and temporal scales and connect morphological features with their integrated star formation on different timescales. This is being done using machine learning methods, specifically using CNNs. We focus on interpretability of the trained network using Grad-CAM, to see what parts of galaxy images the network is focusing on to make its predictions.