Spectroscopic redshift determination with Bayesian convolutional networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985815%3A_____%2F22%3A00562014" target="_blank" >RIV/67985815:_____/22:00562014 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21240/22:00358947

Výsledek na webu

<a href="https://doi.org/10.1016/j.ascom.2022.100615" target="_blank" >https://doi.org/10.1016/j.ascom.2022.100615</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.ascom.2022.100615" target="_blank" >10.1016/j.ascom.2022.100615</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Spectroscopic redshift determination with Bayesian convolutional networks

Popis výsledku v původním jazyce

Astronomy is facing large amounts of data, so astronomers have to rely on automated methods to analyse them. However, automated methods might produce incorrect values. Therefore, we need to develop different automated methods and perform a consistency check to identify them. If there is a lot of labelled data, convolutional neural networks are a powerful method for any task. We illustrate the consistency check on spectroscopic redshift determination with a method based on a Bayesian convolutional neural network inspired by VGG networks. The method provides predictive uncertainties that enable us to (1.) determine unusual or problematic spectra for visual inspection (2.) do thresholding that allows us to balance between the error of redshift predictions and coverage. We used the 12th Sloan Digital Sky Survey quasar superset as the training set for the method. We evaluated its generalisation capability on about three-quarters of a million spectra from the 16th quasar superset of the same survey. On the 16th quasar superset, the method performs better in terms of the root-mean-squared error than the most used template fitting method. Using redshift predictions of the proposed method, we identified spectra with incorrectly determined redshifts that are unrecognised quasars or were misclassified as them.

Název v anglickém jazyce

Spectroscopic redshift determination with Bayesian convolutional networks

Popis výsledku anglicky

Astronomy is facing large amounts of data, so astronomers have to rely on automated methods to analyse them. However, automated methods might produce incorrect values. Therefore, we need to develop different automated methods and perform a consistency check to identify them. If there is a lot of labelled data, convolutional neural networks are a powerful method for any task. We illustrate the consistency check on spectroscopic redshift determination with a method based on a Bayesian convolutional neural network inspired by VGG networks. The method provides predictive uncertainties that enable us to (1.) determine unusual or problematic spectra for visual inspection (2.) do thresholding that allows us to balance between the error of redshift predictions and coverage. We used the 12th Sloan Digital Sky Survey quasar superset as the training set for the method. We evaluated its generalisation capability on about three-quarters of a million spectra from the 16th quasar superset of the same survey. On the 16th quasar superset, the method performs better in terms of the root-mean-squared error than the most used template fitting method. Using redshift predictions of the proposed method, we identified spectra with incorrectly determined redshifts that are unrecognised quasars or were misclassified as them.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10308 - Astronomy (including astrophysics,space science)

Projekt

<a href="/cs/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název periodika

Astronomy and Computing

ISSN

2213-1337

e-ISSN

2213-1345

Svazek periodika

40

Číslo periodika v rámci svazku

July

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

14

Strana od-do

100615

Kód UT WoS článku

000876694100002

EID výsledku v databázi Scopus

2-s2.0-85134881627