Identification of single spectral lines through supervised machine learning in a large HST survey (WISP): a pilot study for Euclid and WFIRST

TL;DR

This study develops a supervised machine learning method to accurately identify single emission lines in large near-infrared galaxy surveys, aiding future dark energy missions like Euclid and WFIRST.

Contribution

It introduces a novel combined SED fitting and machine learning approach for classifying single spectral lines, demonstrating improved accuracy over traditional methods.

Findings

Achieves 82.6% accuracy in line classification

Outperforms SED fitting alone (~50% accuracy)

Provides a scalable method for future large surveys

Abstract

Future surveys focusing on understanding the nature of dark energy (e.g., Euclid and WFIRST) will cover large fractions of the extragalactic sky in near-IR slitless spectroscopy. These surveys will detect a large number of galaxies that will have only one emission line in the covered spectral range. In order to maximize the scientific return of these missions, it is imperative that single emission lines are correctly identified. Using a supervised machine-learning approach, we classified a sample of single emission lines extracted from the WFC3 IR Spectroscopic Parallel survey (WISP), one of the closest existing analogs to future slitless surveys. Our automatic software integrates a SED fitting strategy with additional independent sources of information. We calibrated it and tested it on a "gold" sample of securely identified objects with multiple lines detected. The algorithm correctly classifies real emission lines with an accuracy of 82.6%, whereas the accuracy of the SED fitting technique alone is low (~50%) due to the limited amount of photometric data available (<=6 bands). While not specifically designed for the Euclid and WFIRST surveys, the algorithm represents an important precursor of similar algorithms to be used in these future missions.