IrisML: Neural Posterior Estimation for the Spectral Energy Distribution fitting

TL;DR

IrisML introduces a neural posterior estimation method for spectral energy distribution fitting, providing a scalable, automatic, and efficient alternative to traditional Bayesian inference methods like MCMC in astronomical data analysis.

Contribution

The paper presents a novel neural network-based approach for spectral energy distribution fitting that automates and accelerates the inference process compared to traditional Bayesian methods.

Findings

Achieves faster inference than MCMC methods.

Provides robust and automatic parameter estimation.

Scales well with large astronomical datasets.

Abstract

Over the past 30 years, numerous large-scale photometric astronomical surveys have been conducted, including SDSS, Pan-STARRS, Gaia,2MASS, WISE, and others. These surveys provide extensive photometric measurements that can be used to infer a wide range of physical parameters of astronomical objects. Traditionally, Bayesian approaches, such as Markov Chain Monte Carlo (MCMC) sampling have been employed for such inference tasks. However, these methods tend to be computationally intensive and often require manual tuning or expert supervision. In this work, we propose a novel machine learning model designed to perform automatic and robust inference from photometric data, offering a scalable and efficient alternative to conventional techniques.