Misclassifications of galaxies in the Zone of Avoidance using Machine Learning tools
Event Timeslots (1)
Monday 8th
-
Misclassifications of galaxies in the Zone of Avoidance using Machine Learning tools
Automated methods for classifying extragalactic objects in extensive surveys are essential for efficiency. However, the Zone of Avoidance (ZoA) presents significant challenges with dust extinction, star crowding, and limited data. Zhang et al. (2021) recently implemented machine learning techniques to classify stars, galaxies, and qso in the 4XMM-DR9, containing the ZoA. We investigate the challenges and advantages of using ML tools for galaxy classification in the ZoA and explore the implications of environmental factors on classification results and their reliability. Our analysis reveals significant differences between the sample galaxies and those present all over the Galactic disc, mainly due to the lack of information on galaxies in the Galactic plane in the training set. Some chosen regions within the ZoA exhibit a high probability of being a galaxy in X-ray data but they closely resemble extended Galactic objects. Our findings highlight the complexities of machine learning-based galaxy classification in the ZoA, emphasizing the need to consider environmental factors and refine data distribution for more robust future studies in this challenging region.