Presentation #301.03 in the session “Machine Learning in Astronomy: Data Compression, Representation and Visualization (Meeting-in-a-Meeting)”.
As available data sets grow in size and complexity, advanced visualization tools enabling their exploration and analysis become more important. In modern astronomy, integral field spectroscopic galaxy surveys are a clear example of increasing dimensionality and complexity of datasets, which challenge the traditional methods used to extract the physical information they contain. We present the use of a novel self-supervised learning method to visualize the multi-dimensional information on stellar population and kinematics in the MaNGA survey in a two dimensional plane. Our framework is insensitive to non-physical properties such as the size of IFU and is therefore able to order galaxies according to their resolved physical properties. Using the extracted representations, we show that galaxies naturally cluster into three well-known categories from a purely data driven perspective: rotating main-sequence disks, massive slow rotators and low-mass rotation-dominated quenched galaxies.