Back to Search Start Over

Accelerating Pulsar Parameter Estimation Using Convolutional Neural Networks

Authors :
Olmschenk, Greg
Broadbent, Emily
Kalapotharakos, Constantinos
Wallace, Wendy
Lechien, Thibault
Wadiasingh, Zorawar
Kazanas, Demosthenes
Harding, Alice
Publication Year :
2025

Abstract

Accurate models of neutron stars are essential for constraining the dense matter equation of state. However, realistic models incorporating magnetic fields structures are exceedingly computationally intensive. In this work, we develop a neural network (NN) emulator to generate model thermal bolometric X-ray light curves of millisecond pulsars with multipolar magnetic fields. We assess the NN's predictive and computational performance across a broad parameter space. We find that for a static vacuum field (SVF) model, the NN provides a >400 times speedup. We integrate this NN emulator into a Markov Chain Monte Carlo (MCMC) framework to replace the computationally expensive physical model during parameter exploration. Applied to PSR J0030+0451, this approach allows the MCMC to reach equilibrium, which is infeasible to obtain with the original physical model alone. We compare posterior distributions by running equivalent MCMC iterations with both the NN and the physical model and evaluate differences in distributions when continuing the physical model MCMC from the NN MCMC equilibrium state. Our NN architecture is agnostic to the underlying physics of the physical model and can be trained for any other physical model. The NN speed remains the same regardless of the complexity of the physical model it was trained to emulate, allowing for greater speedups compared to physical models that are more complex than the SVF model.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2501.12383
Document Type :
Working Paper