Predicting Galactic OH Masers from Dense Clump Properties with Neural Networks and Generalized Linear Models
Year: 2025
Type: conference-paper
Abstract: We present predictive models for OH maser occurrence in Galactic star-forming regions by integrating dense-clump physical properties from ATLASGAL and Hi-GAL catalogs with maser detections and non-detections compiled in the MaserDB.net database. We compare two predictive modeling approaches: a Generalized Linear Model (GLM) and a compact binary neural network (BNN). For the 1 665/1 667 MHz lines, both models achieve a recall of 90 % with a precision of approximately 50 %, while for the excited-state 6 031/6 035 MHz lines, precision reaches roughly 20 % at the same recall. We found no statistically significant difference between the BNN and GLM performance. This implies that maser occurrence may be expressed as a monotonic trend without requiring nonlinear interactions. Across different catalogs and transition lines, luminosity, luminosity-to-mass ratio (L/M), dust temperature, and density metrics are the most influential features. These variables support a physical picture in which radiative pumping favors warm, luminous, and compact clump environments. An accessible online tool based on these models has been implemented on MaserDB.net to aid in the discovery of new maser sources.
Institution: Ural Federal University
Language: English
Subfield: Astronomy and Astrophysics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W4416719081