Detection of Dispersed Radio Pulses: A machine learning approach to candidate identification and classification

TL;DR

This paper introduces a novel two-stage machine learning approach for detecting and classifying dispersed radio pulses in astronomical data, improving accuracy and enabling potential new pulsar discoveries.

Contribution

It presents a new peak identification algorithm and benchmarks multiple classifiers, identifying the most effective methods for large-scale pulsar candidate classification.

Findings

Classifiers with imbalance treatments had higher recall.

Multiclass ensemble tree classifiers with oversampling performed best.

Six potential new pulsar discoveries were made.

Abstract

Searching for extraterrestrial, transient signals in astronomical data sets is an active area of current research. However, machine learning techniques are lacking in the literature concerning single-pulse detection. This paper presents a new, two-stage approach for identifying and classifying dispersed pulse groups (DPGs) in single-pulse search output. The first stage identified DPGs and extracted features to characterize them using a new peak identification algorithm which tracks sloping tendencies around local maxima in plots of signal-to-noise ratio vs. dispersion measure. The second stage used supervised machine learning to classify DPGs. We created four benchmark data sets: one unbalanced and three balanced versions using three different imbalance treatments.We empirically evaluated 48 classifiers by training and testing binary and multiclass versions of six machine learning algorithms on each of the four benchmark versions. While each classifier had advantages and disadvantages, all classifiers with imbalance treatments had higher recall values than those with unbalanced data, regardless of the machine learning algorithm used. Based on the benchmarking results, we selected a subset of classifiers to classify the full, unlabelled data set of over 1.5 million DPGs identified in 42,405 observations made by the Green Bank Telescope. Overall, the classifiers using a multiclass ensemble tree learner in combination with two oversampling imbalance treatments were the most efficient; they identified additional known pulsars not in the benchmark data set and provided six potential discoveries, with significantly less false positives than the other classifiers.