Spatio-Spectroscopic Representation Learning using Unsupervised Convolutional Long-Short Term Memory Networks

TL;DR

This paper introduces an unsupervised deep learning framework using Convolutional LSTM Autoencoders to learn joint spatial and spectroscopic features from IFS galaxy data, revealing new insights into galaxy evolution.

Contribution

It presents a novel unsupervised learning approach for encoding combined spatial and spectroscopic features in galaxy surveys, enabling analysis of large IFS datasets.

Findings

Successfully encoded features across 19 optical emission lines.

Identified anomalous AGN with scientifically interesting characteristics.

Demonstrated the model on a sample of 9000 galaxies from MaNGA.

Abstract

Integral Field Spectroscopy (IFS) surveys offer a unique new landscape in which to learn in both spatial and spectroscopic dimensions and could help uncover previously unknown insights into galaxy evolution. In this work, we demonstrate a new unsupervised deep learning framework using Convolutional Long-Short Term Memory Network Autoencoders to encode generalized feature representations across both spatial and spectroscopic dimensions spanning $19$ optical emission lines (3800A $< \lambda <$ 8000A) among a sample of $\sim 9000$ galaxies from the MaNGA IFS survey. As a demonstrative exercise, we assess our model on a sample of $290$ Active Galactic Nuclei (AGN) and highlight scientifically interesting characteristics of some highly anomalous AGN.