Description
Over ten years after the survey was concluded, research into the WISE catalogue is still being undertaken. However, one area that has been lacking exploration is applying unsupervised machine learning to the catalogue, especially in the case of outlier detection. Using unsupervised machine learning for outlier detection can be a very powerful tool, allowing you to find underlying structure and patterns in datasets which are not obvious to the naked eye. This work focuses on trying to find rare objects ‘outliers’ within the catalogue, which in this case are hot dust-obscured galaxies (Hot DOGs). Previously, to find these objects, tight colour cuts had to be employed due to the number of sources within the catalogue, resulting in a number of interesting candidates being missed. The aim for this work is both to identify the current known Hot DOGs within the catalogue and to also increase our known number by extracting missed candidates.
