An all-sky Support Vector Machine selection of WISE YSO Candidates
G\'abor Marton, L. Viktor T\'oth, Roberta Paladini, M\'aria Kun,, Sarolta Zahorecz, Peregrine McGehee, Csaba Kiss

TL;DR
This paper presents a new all-sky selection of nearly 134,000 YSO candidates using Support Vector Machine classification on combined infrared and dust data, outperforming previous methods in accuracy and contamination control.
Contribution
The study introduces an SVM-based classification scheme for YSO candidate selection that integrates multi-wavelength data and dust opacity, achieving higher detection rates and lower contamination than existing methods.
Findings
Identified 133,980 YSO candidates across the sky.
Contamination estimated below 1%.
Recovered over 90% of known YSOs in comparison datasets.
Abstract
We explored the AllWISE catalogue of the Wide-field Infrared Survey Explorer mission and identified Young Stellar Object candidates. Reliable 2MASS and WISE photometric data combined with Planck dust opacity values were used to build our dataset and to find the best classification scheme. A sophisticated statistical method, the Support Vector Machine (SVM) is used to analyse the multi-dimensional data space and to remove source types identified as contaminants (extragalactic sources, main sequence stars, evolved stars and sources related to the interstellar medium). Objects listed in the SIMBAD database are used to identify the already known sources and to train our method. A new all-sky selection of 133,980 Class I/II YSO candidates is presented. The estimated contamination was found to be well below 1% based on comparison with our SIMBAD training set. We also compare our results to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
