Inference of cosmic-ray source properties by conditional invertible neural networks

TL;DR

This paper demonstrates that conditional invertible neural networks can efficiently infer cosmic-ray source properties from observations, matching traditional MCMC results while offering faster computation.

Contribution

The study introduces the application of cINNs to cosmic-ray physics, showing they can accurately and efficiently infer source parameters compared to MCMC methods.

Findings

cINNs produce posterior distributions consistent with MCMC.

cINNs offer significantly faster inference times.

The methods agree well on physical parameter estimates.

Abstract

The inference of physical parameters from measured distributions constitutes a core task in physics data analyses. Among recent deep learning methods, so-called conditional invertible neural networks provide an elegant approach owing to their probability-preserving bijective mapping properties. They enable training the parameter-observation correspondence in one mapping direction and evaluating the parameter posterior distributions in the reverse direction. Here, we study the inference of cosmic-ray source properties from cosmic-ray observations on Earth using extensive astrophysical simulations. We compare the performance of conditional invertible neural networks (cINNs) with the frequently used Markov Chain Monte Carlo (MCMC) method. While cINNs are trained to directly predict the parameters' posterior distributions, the MCMC method extracts the posterior distributions through a likelihood function that matches simulations with observations. Overall, we find good agreement between the physics parameters derived by the two different methods. As a result of its computational efficiency, the cINN method allows for a swift assessment of inference quality.