Exploring TeV Candidates of Fermi Blazars through Machine Learning

In this work, we make use of a supervised machine learning algorithm based on Logistic Regression (LR) to select TeV blazar candidates from the 4FGL-DR2 / 4LAC-DR2, 3FHL, 3HSP, and 2BIGB catalogs. LR constructs hyperplane selection optimal parameters, named features, hyper-parameters whose values control process determine features that ends up learning, discriminate blazars non-TeV blazars. addition, it gives probability (or logistic) source may be considered as candidate. Non-TeV with logistics greater than 80% are high-confidence candidates. Using technique, identify 40 4LAC-DR2 build feature hyper-plane distinguish We also calculate hyper-planes for 2BIGB. Finally, construct broadband spectral energy distributions (SED) candidates, testing their detectability various instruments. find 7 them likely detected by existing or upcoming IACT observatories, while 1 could observed EAS particle detector arrays.