Using an Artificial Neural Network to Classify Multi-component Emission Line Fits

TL;DR

This paper introduces 'The Machine,' an artificial neural network designed to automatically classify the number of Gaussian components in emission lines from integral field spectroscopic data, significantly reducing manual effort.

Contribution

The paper presents a novel neural network model that automates emission line component classification, replacing time-consuming manual methods in large spectroscopic surveys.

Findings

Successfully classifies emission lines into 1, 2, or 3 Gaussian components

Reduces classification time from hours per galaxy to automated processing

Demonstrates applicability on data from S7 and SAMI surveys

Abstract

We present The Machine, an artificial neural network (ANN) capable of differentiating between the numbers of Gaussian components needed to describe the emission lines of Integral Field Spectroscopic (IFS) observations. Here we show the preliminary results of the S7 first data release (Siding Spring Southern Seyfert Spectro- scopic Snapshot Survey, Dopita et al. 2015) and SAMI Galaxy Survey (Sydney-AAO Multi-object Integral Field Unit, Croom et al. 2012) to classify whether the emission lines in each spatial pixel are composed of 1, 2, or 3 different Gaussian components. Previously this classification has been done by individual people, taking an hour per galaxy. This time investment is no longer feasible with the large spectroscopic surveys coming online.