Broad Absorption Line Quasar catalogues with Supervised Neural Networks

TL;DR

This paper introduces a supervised neural network approach using LVQ to create a more robust and complete catalogue of broad absorption line quasars from SDSS data, improving upon traditional methods.

Contribution

The paper presents a novel application of LVQ neural networks for identifying BALQSOs, addressing limitations of previous cataloguing techniques.

Findings

The LVQ-based catalogue is more robust than traditional BI/AI methods.

The method improves the completeness of BALQSO detection.

The approach demonstrates the effectiveness of supervised neural networks in spectral classification.

Abstract

We have applied a Learning Vector Quantization (LVQ) algorithm to SDSS DR5 quasar spectra in order to create a large catalogue of broad absorption line quasars (BALQSOs). We first discuss the problems with BALQSO catalogues constructed using the conventional balnicity and/or absorption indices (BI and AI), and then describe the supervised LVQ network we have trained to recognise BALQSOs. The resulting BALQSO catalogue should be substantially more robust and complete than BI- or AI-based ones.