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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68378271%3A_____%2F22%3A00564461" target="_blank" >RIV/68378271:_____/22:00564461 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1140/epjc/s10052-022-10138-x" target="_blank" >https://doi.org/10.1140/epjc/s10052-022-10138-x</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1140/epjc/s10052-022-10138-x" target="_blank" >10.1140/epjc/s10052-022-10138-x</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10303 - Particles and field physics

Projekt

—

Návaznosti

—

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

European Physical Journal C

ISSN

1434-6044

e-ISSN

1434-6052

Svazek periodika

82

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

10

Strana od-do

171

Kód UT WoS článku

000760965400006

EID výsledku v databázi Scopus

2-s2.0-85125497014