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

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.

10 pages, 8 figures

References in corpus (3)

• Guided Image Generation with Conditional Invertible Neural Networks
• Measurement of the cosmic-ray energy spectrum above $2.5\times 10^{18}$ eV using the Pierre Auger Observatory
• A Living Review of Machine Learning for Particle Physics

Cited by in corpus (16)

• Ultra-High-Energy Cosmic Rays: The Intersection of the Cosmic and Energy Frontiers
• Neural posterior estimation for exoplanetary atmospheric retrieval
• MadNIS -- Neural Multi-Channel Importance Sampling
• Two Invertible Networks for the Matrix Element Method
• What's Anomalous in LHC Jets?
• CaloFlow for CaloChallenge Dataset 1
• Anomaly detection with flow-based fast calorimeter simulators
• A deep-learning approach to the 3D reconstruction of dust density and temperature in star-forming regions
• Unifying Simulation and Inference with Normalizing Flows
• Reconstructing axion-like particles from beam dumps with simulation-based inference
• Unifying supervised learning and VAEs -- coverage, systematics and goodness-of-fit in normalizing-flow based neural network models for astro-particle reconstructions
• Deep Learning the Forecast of Galactic Cosmic-Ray Spectra
• Map Reconstruction of radio observations with Conditional Invertible Neural Networks
• What exactly did the Transformer learn from our physics data?
• Spectral classification of young stars using conditional invertible neural networks II. Application to Trumpler 14 in Carina
• A method to derive self-consistent NLTE astrophysical parameters for 4 million high-resolution 4MOST stellar spectra in half a day with invertible neural networks