Accelerating Stellar Photometric Distance Estimates with Neural Networks

Building on the Bayesian approach to estimating stellar distances from broadband photometry, we show that the computation can be accelerated by about an order of magnitude by using neural networks. Focusing on the case of the ugrizy filter complement for Rubin’s Legacy Survey of Space and Time (LSST...

Full description

Saved in:
Bibliographic Details
Main Authors: Karlo Mrakovčić, Željko Ivezić, Lovro Palaversa
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:The Astronomical Journal
Subjects:
Online Access:https://doi.org/10.3847/1538-3881/addf51
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849320090464419840
author Karlo Mrakovčić
Željko Ivezić
Lovro Palaversa
author_facet Karlo Mrakovčić
Željko Ivezić
Lovro Palaversa
author_sort Karlo Mrakovčić
collection DOAJ
description Building on the Bayesian approach to estimating stellar distances from broadband photometry, we show that the computation can be accelerated by about an order of magnitude by using neural networks. Focusing on the case of the ugrizy filter complement for Rubin’s Legacy Survey of Space and Time (LSST), we show that the Bayesian approach is equivalent to mapping from a 10-dimensional space of five measured colors and their uncertainties to a three-dimensional space of absolute magnitude, metallicity, and interstellar dust extinction along the line of sight. Once the neural network is trained, this mapping is faster by more than an order of magnitude compared to the Bayesian approach, for both optimized grid search and Markov chain Monte Carlo implementation methods. We have developed and tested a pipeline that achieves significant acceleration by first running the Bayesian method on 5%–10% of the sample, then using it to train a neural network, and finally processing the entire sample with the resulting neural network. This computation is done in patches of about 10 deg ^2 due to the variation of Bayesian priors across the sky. We present an analysis of pipeline performance, including speed and biases as functions of input stellar parameters and signal-to-noise ratio, using TRILEGAL-based simulated LSST catalogs by P. Dal Tio et al. We intend to run this pipeline on LSST data releases and make its outputs publicly available.
format Article
id doaj-art-ebf5019bb80b4e7da74e159a43e084bc
institution Kabale University
issn 1538-3881
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series The Astronomical Journal
spelling doaj-art-ebf5019bb80b4e7da74e159a43e084bc2025-08-20T03:50:12ZengIOP PublishingThe Astronomical Journal1538-38812025-01-0117027210.3847/1538-3881/addf51Accelerating Stellar Photometric Distance Estimates with Neural NetworksKarlo Mrakovčić0https://orcid.org/0009-0009-8154-3827Željko Ivezić1https://orcid.org/0000-0001-5250-2633Lovro Palaversa2https://orcid.org/0000-0003-3710-0331Faculty of Physics, University of Rijeka , Radmile Matejčić 2, 51000 Rijeka, Croatia ; karlo.mrakovcic@uniri.hrDepartment of Astronomy and the DiRAC Institute, University of Washington , 3910 15th Avenue NE, Seattle, WA 98195, USA; Ruđer Bošković Institute , Bijenička cesta 54, 10000 Zagreb, CroatiaRuđer Bošković Institute , Bijenička cesta 54, 10000 Zagreb, CroatiaBuilding on the Bayesian approach to estimating stellar distances from broadband photometry, we show that the computation can be accelerated by about an order of magnitude by using neural networks. Focusing on the case of the ugrizy filter complement for Rubin’s Legacy Survey of Space and Time (LSST), we show that the Bayesian approach is equivalent to mapping from a 10-dimensional space of five measured colors and their uncertainties to a three-dimensional space of absolute magnitude, metallicity, and interstellar dust extinction along the line of sight. Once the neural network is trained, this mapping is faster by more than an order of magnitude compared to the Bayesian approach, for both optimized grid search and Markov chain Monte Carlo implementation methods. We have developed and tested a pipeline that achieves significant acceleration by first running the Bayesian method on 5%–10% of the sample, then using it to train a neural network, and finally processing the entire sample with the resulting neural network. This computation is done in patches of about 10 deg ^2 due to the variation of Bayesian priors across the sky. We present an analysis of pipeline performance, including speed and biases as functions of input stellar parameters and signal-to-noise ratio, using TRILEGAL-based simulated LSST catalogs by P. Dal Tio et al. We intend to run this pipeline on LSST data releases and make its outputs publicly available.https://doi.org/10.3847/1538-3881/addf51Neural networksDistance measureDistance indicatorsStellar distanceExtinctionInterstellar extinction
spellingShingle Karlo Mrakovčić
Željko Ivezić
Lovro Palaversa
Accelerating Stellar Photometric Distance Estimates with Neural Networks
The Astronomical Journal
Neural networks
Distance measure
Distance indicators
Stellar distance
Extinction
Interstellar extinction
title Accelerating Stellar Photometric Distance Estimates with Neural Networks
title_full Accelerating Stellar Photometric Distance Estimates with Neural Networks
title_fullStr Accelerating Stellar Photometric Distance Estimates with Neural Networks
title_full_unstemmed Accelerating Stellar Photometric Distance Estimates with Neural Networks
title_short Accelerating Stellar Photometric Distance Estimates with Neural Networks
title_sort accelerating stellar photometric distance estimates with neural networks
topic Neural networks
Distance measure
Distance indicators
Stellar distance
Extinction
Interstellar extinction
url https://doi.org/10.3847/1538-3881/addf51
work_keys_str_mv AT karlomrakovcic acceleratingstellarphotometricdistanceestimateswithneuralnetworks
AT zeljkoivezic acceleratingstellarphotometricdistanceestimateswithneuralnetworks
AT lovropalaversa acceleratingstellarphotometricdistanceestimateswithneuralnetworks