Paper detail

Artificial neural network based calibrations for the prediction of galactic [NII] $λ$ 6584 and H$α$ line luminosities

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$α$ and [NII] $λ$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$α$ and [NII] $λ$6584 line luminosities can be predicted with a scatter $σ<$ 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$α$ and [NII] $λ$6584 line luminosities. An ANN calibration for the Balmer decrement (H$α$/H$β$) based on line equivalent widths and colours is also presented. The effectiveness of the ANN calibration is demonstrated with an independent dataset (the Galaxy Mass and Assembly Survey). We demonstrate the application of our line luminosities to the determination of gas-phase metallicities and AGN classification. The ANN technique yields a significant improvement in the measurement of metallicities that require [NII] and H$α$ when compared with the function based conversions of Kewley & Ellison. The AGN classification is successful for 86 per cent of SDSS galaxies.