A Machine Learning Method for Monte Carlo Calculations of Radiative Processes

TL;DR

This paper introduces a machine learning technique to accelerate Monte Carlo simulations of radiative processes like inverse Compton scattering in astrophysics, achieving up to tenfold speed improvements over traditional methods.

Contribution

The paper presents a novel ML-based sampling method that enhances the efficiency of Monte Carlo calculations for stochastic radiative processes in astrophysics.

Findings

ML method is up to ten times faster than traditional sampling techniques

Effective in simulating inverse Compton radiation

Applicable to arbitrary probability distributions in astrophysical contexts

Abstract

Radiative processes such as synchrotron radiation and Compton scattering play an important role in astrophysics. Radiative processes are fundamentally stochastic in nature, and the best tools currently used for resolving these processes computationally are Monte Carlo (MC) methods. These methods typically draw a large number of samples from a complex distribution such as the differential cross section for electron-photon scattering, and then use these samples to compute the radiation properties such as angular distribution, spectrum, and polarization. In this work we propose a machine learning (ML) technique for efficient sampling from arbitrary known probability distributions that can be used to accelerate Monte Carlo calculation of radiative processes in astrophysical scenarios. In particular, we apply our technique to inverse Compton radiation and find that our ML method can be up to an order of magnitude faster than traditional methods currently in use.