MUWCLASS is a machine learning (ML) pipeline which uses the supervised ML random forest algorithm to classify the X-ray sources based on their multiwavelength properties, which also accounts for measurement uncertainties and absorption/extinction biases. We applied the pipeline to Chandra Source Catalog version 2.0 (CSCv2) and have classified more than 66,000 CSCv2 sources, consisting ~21% of the CSCv2.0, based on a training data set of 2941 X-ray sources of confidently established classes. I will also present the visualization tool XCLASS that we use to plot the multiwavelength properties of our training dataset and classified sources.
Name of software library or topic
Multiwavelength machine learning classification (MUWCLASS)
URL to software repository
https://github.com/huiyang-astro/MUWCLASS_CSCv2 https://home.gwu.edu/~kargaltsev/XCLASS/
Name of person who will give the talk
Hui Yang (The George Washington University)
Brief abstract
MUWCLASS is a machine learning (ML) pipeline which uses the supervised ML random forest algorithm to classify the X-ray sources based on their multiwavelength properties, which also accounts for measurement uncertainties and absorption/extinction biases. We applied the pipeline to Chandra Source Catalog version 2.0 (CSCv2) and have classified more than 66,000 CSCv2 sources, consisting ~21% of the CSCv2.0, based on a training data set of 2941 X-ray sources of confidently established classes. I will also present the visualization tool XCLASS that we use to plot the multiwavelength properties of our training dataset and classified sources.