Research Paper#Astronomy, Quasars, Galactic Plane, Machine Learning🔬 ResearchAnalyzed: Jan 3, 2026 19:17
Identifying Quasar Candidates Behind the Galactic Plane Using Chandra and Machine Learning
Published:Dec 28, 2025 20:04
•1 min read
•ArXiv
Analysis
This paper addresses the challenge of finding quasars obscured by the Galactic plane, a region where observations are difficult due to dust and source confusion. The authors leverage the Chandra X-ray data, combined with optical and infrared data, and employ a Random Forest classifier to identify quasar candidates. The use of machine learning and multi-wavelength data is a key strength, allowing for the identification of fainter quasars and improving the census of these objects. The paper's significance lies in its contribution to a more complete quasar sample, which is crucial for various astronomical studies, including refining astrometric reference frames and probing the Milky Way's interstellar medium.
Key Takeaways
- •Employs Chandra X-ray data, Gaia, and CatWISE2020 data to find quasars behind the Galactic plane.
- •Utilizes a Random Forest classifier and regression model for candidate selection and redshift estimation.
- •Identifies a significant number of quasar candidates, including high-confidence Galactic Plane Quasar candidates.
- •Provides a valuable target sample for future spectroscopic follow-up.
- •Improves the census of Galactic Plane Quasars and enables studies of the Milky Way's interstellar and circumgalactic media.
Reference
“The study identifies 6286 quasar candidates, including 863 Galactic Plane Quasar (GPQ) candidates at |b|<20°, of which 514 are high-confidence candidates.”