Document Type

Poster

Publication Date

Summer 2025

Abstract

Neutron stars are the super-dense remnants of dead stars: too massive to form a white dwarf but not massive enough to form black holes. A typical neutron star is 1-3 times the mass of our sun, but its radius is only 10-15 kilometers (roughly the size of New York City). Pulsars are rapidly spinning neutron stars that emit radio waves from their magnetic poles. We have discovered more than 3,000 pulsars through manual search methods. Past researchers at Kenyon created PAC-MANN (PulsAr-Classifier Machine-Learning Algorithm with Neural Networks). PACMANN's goal is to create a machine learning algorithm that will be able to sift through pulsar candidates and find the most promising among them. My research this summer worked to fill in a vital missing piece of PAC-MANN: a lack of pulsar candidates. However, we encountered a dilemma: to train our model to find more pulsars, we need more pulsars. We decided to create an algorithm to solve this issue, which we named MSPAC (Machine-Sequenced PulsAr Candidates). MSPAC generates artificial pulsar candidates based on distributions from real pulsar data. Our goal with these machine-sequenced pulsars is to create a pulsar population indistinguishable from real pulsar populations and use these populations to train PAC-MANN.

Download

Share

COinS
 

Rights Statement

In Copyright - Non-Commercial Use Permitted