Detecting Pulsars with Neural Networks: A Proof of Concept

Abstract

Pulsar searches are computationally demanding efforts to discover dispersed periodic signals in time- and frequency-resolved data from radio telescopes. The complexity and computational expense of simultaneously determining the frequency-dependent delay (dispersion) and the periodicity of the signal is further exacerbated by the presence of various types of radio-frequency interference (RFI) and observing-system effects. New observing systems with wider bandwidths, higher bit rates and greater overall sensitivity (also to RFI) further enhance these challenges. We present a novel approach to the analysis of pulsar search data. Specifically, we present a neural-network-based pipeline that efficiently suppresses a wide range of RFI signals and instrumental instabilities and furthermore corrects for (a priori unknown) interstellar dispersion. After initial training of the network, our analysis can be run in real time on a standard desktop computer with a commonly available, consumer-grade GPU. We complement our neural network with standard algorithms for periodicity searches. In particular with the Fast Fourier Transform (FFT) and the Fast Folding Algorithm (FFA) and demonstrate that with these straightforward extensions, our method is capable of identifying even faint pulsars, while maintaining an extremely low number of false positives. We furthermore apply our analysis to a subset of the PALFA survey and demonstrate that in most cases the automated dispersion removal of our network produces a time series of similar quality as dedispersing using the actual dispersion measure of the pulsar in question. On our test data we are able to make predictions whether a pulsar is present in the data or not 200 times faster than real time.

arXiv commentAccepted for publication in MNRAS. 17 pages, 16 figures

References in corpus (23)

• Adam: A Method for Stochastic Optimization
• Deep Residual Learning for Image Recognition
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Deep learning for time series classification: a review
• Astrophysics Source Code Library
• Fourier Techniques for Very Long Astrophysical Time Series Analysis
• Arecibo Pulsar Survey Using ALFA. I. Survey Strategy and First Discoveries
• Fifty Years of Pulsar Candidate Selection: From simple filters to a new principled real-time classification approach
• Fast Radio Burst 121102 Pulse Detection and Periodicity: A Machine Learning Approach
• The Parkes Multibeam Pulsar Survey: V. Finding binary and millisecond pulsars
• FETCH: A deep-learning based classifier for fast transient classification
• Searching for pulsars using image pattern recognition
• Arecibo Pulsar Survey Using ALFA. IV. Mock Spectrometer Data Analysis, Survey Sensitivity, and the Discovery of 41 Pulsars
• Optimal periodicity searching: Revisiting the Fast Folding Algorithm for large-scale pulsar surveys
• An Interference Removal Technique for Radio Pulsar Searches
• Applying Deep Learning to Fast Radio Burst Classification
• PEACE: Pulsar Evaluation Algorithm for Candidate Extraction -- A software package for post-analysis processing of pulsar survey candidates
• A coherent acceleration search of the Parkes multi-beam pulsar survey - techniques and the discovery and timing of 16 pulsars
• An investigation of pulsar searching techniques with the Fast Folding Algorithm
• The implementation of a Fast-Folding pipeline for long-period pulsar searching in the PALFA survey
• A novel single-pulse search approach to detection of dispersed radio pulses using clustering and supervised machine learning
• The Pulsar Search Collaboratory: Current Status and Future Prospects
• Fine-Grained Semantic Segmentation of Motion Capture Data using Dilated Temporal Fully-Convolutional Networks

Cited by in corpus (1)

• SPARKESX: Single-dish PARKES data sets for finding the uneXpected -- A data challenge