Pulsar Candidate Sifting Using Multi-input Convolution Neural Networks

TL;DR

This paper introduces MICNN, a multi-input convolutional neural network framework that effectively sifts pulsar candidates from large sky surveys by addressing class imbalance with novel training techniques.

Contribution

The work presents a new deep learning architecture with four diagnostic plots as inputs and a three-stage training strategy to improve pulsar candidate sifting accuracy.

Findings

Achieved 0.962 recall and 0.967 precision on HTRU data.

Demonstrated robustness and effectiveness of the proposed methods.

Addresses class imbalance in pulsar candidate classification.

Abstract

Pulsar candidate sifting is an essential process for discovering new pulsars. It aims to search for the most promising pulsar candidates from an all-sky survey, such as High Time Resolution Universe (HTRU), Green Bank Northern Celestial Cap (GBNCC), Five-hundred-meter Aperture Spherical radio Telescope (FAST), etc. Recently, machine learning (ML) is a hot topic in pulsar candidate sifting investigations. However, one typical challenge in ML for pulsar candidate sifting comes from the learning difficulty arising from the highly class-imbalance between the observation numbers of pulsars and non-pulsars. Therefore, this work proposes a novel framework for candidate sifting, named multi-input convolutional neural networks (MICNN). The MICNN is an architecture of deep learning with four diagnostic plots of a pulsar candidate as its inputs. To train our MICNN in a highly class-imbalanced dataset, a novel image augment technique, as well as a three-stage training strategy, is proposed. Experiments on observations from HTRU and GBNCC show the effectiveness and robustness of these proposed techniques. In the experiments on HTRU, our MICNN model achieves a recall of 0.962 and a precision rate of 0.967 even in a highly class-imbalanced test dataset.