Artificial neural network based calibrations for the prediction of galactic [NII] $\lambda$ 6584 and H$\alpha$ line luminosities

Abstract

The artificial neural network (ANN) is a well-established mathematical technique for data prediction, based on the identification of correlations and pattern recognition in input training sets. We present the application of ANNs to predict the emission line luminosities of H$\alpha$ and [NII] $\lambda$6584 in galaxies. These important spectral diagnostics are used for metallicities, active galactic nuclei (AGN) classification and star formation rates, yet are shifted into the infra-red for galaxies above $z\sim 0.5$, or may not be covered in spectra with limited wavelength coverage. The ANN is trained with a large sample of emission line galaxies selected from the Sloan Digital Sky Survey using various combinations of emission lines and stellar mass. The ANN is tested for galaxies dominated by both star formation and AGN; in both cases the H$\alpha$ and [NII] $\lambda$6584 line luminosities can be predicted with a scatter $\sigma <$ 0.1 dex. We also show that the performance of the ANN does not depend significantly on the covering fraction, mass or metallicity of the data. Polynomial functions are derived that allow easy application of the ANN predictions to determine H$\alpha$ and [NII] $\lambda$6584 line luminosities. An ANN calibration for the Balmer decrement (H$\alpha$/H$\beta$) based on line equivalent widths and colours is also presented. The effectiveness of the ANN calibration is demonstrated with an independent dataset (the Galaxy Mass and Assembly Survey). We demonstrate the application of our line luminosities to the determination of gas-phase metallicities and AGN classification. The ANN technique yields a significant improvement in the measurement of metallicities that require [NII] and H$\alpha$ when compared with the function based conversions of Kewley & Ellison. The AGN classification is successful for 86 per cent of SDSS galaxies.

26 pages, 17 figures, Accepted for publication in MNRAS

References in corpus (5)

• Theoretical Evolution of Optical Strong Lines across Cosmic Time
• The Cosmic BPT Diagram: Confronting Theory with Observations
• New insights into the stellar content and physical conditions of star-forming galaxies at z = 2-3 from spectral modelling
• Metallicities and Physical Conditions in Star-forming Galaxies at z~1.0-1.5
• AEGIS: Demographics of X-ray and Optically Selected AGNs

Cited by in corpus (8)

• Deep learning predictions of galaxy merger stage and the importance of observational realism
• An Artificial Neural Network Approach For Ranking Quenching Parameters In Central Galaxies
• The infra-red luminosities of ~332,000 SDSS galaxies predicted from artificial neural networks and the Herschel Stripe 82 survey
• Pattern recognition in the ALFALFA.70 and Sloan Digital Sky Surveys: A catalog of $\sim$ 500,000 HI gas fraction estimates based on artificial neural networks
• A re-assessment of strong line metallicity conversions in the machine learning era
• The discrimination between star-forming and AGN galaxies in the absence of Hα and [NII]: A machine learning approach
• Assessment of astronomical images using combined machine learning models
• An astronomical image content-based recommendation system using combined deep learning models in a fully unsupervised mode