Afficher la notice abrégée

Neural network-based emulation of interstellar medium models

hal.structure.identifierLaboratoire d'Etude du Rayonnement et de la Matière en Astrophysique et Atmosphères = Laboratory for Studies of Radiation and Matter in Astrophysics and Atmospheres [LERMA]
hal.structure.identifierCentre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
dc.contributor.authorPALUD, Pierre
hal.structure.identifierInstitut de RadioAstronomie Millimétrique [IRAM]
hal.structure.identifierGIPSA - Signal Images Physique [GIPSA-SIGMAPHY]
dc.contributor.authorEINIG, Lucas
hal.structure.identifierLaboratoire d'Etude du Rayonnement et de la Matière en Astrophysique et Atmosphères = Laboratory for Studies of Radiation and Matter in Astrophysics and Atmospheres [LERMA]
dc.contributor.authorLE PETIT, Franck
hal.structure.identifierLaboratoire d'Etude du Rayonnement et de la Matière en Astrophysique et Atmosphères = Laboratory for Studies of Radiation and Matter in Astrophysics and Atmospheres [LERMA]
dc.contributor.authorBRON, Émeric
hal.structure.identifierCentre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
dc.contributor.authorCHAINAIS, Pierre
hal.structure.identifierGIPSA - Signal Images Physique [GIPSA-SIGMAPHY]
dc.contributor.authorCHANUSSOT, Jocelyn
hal.structure.identifierInstitut de RadioAstronomie Millimétrique [IRAM]
hal.structure.identifierLaboratoire d'Etude du Rayonnement et de la Matière en Astrophysique et Atmosphères = Laboratory for Studies of Radiation and Matter in Astrophysics and Atmospheres [LERMA]
dc.contributor.authorPETY, Jérôme
hal.structure.identifierCentre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
dc.contributor.authorTHOUVENIN, Pierre-Antoine
hal.structure.identifierLaboratoire d'Etude du Rayonnement et de la Matière en Astrophysique et Atmosphères = Laboratory for Studies of Radiation and Matter in Astrophysics and Atmospheres [LERMA]
dc.contributor.authorLANGUIGNON, David
hal.structure.identifierLaboratoire d'Etude du Rayonnement et de la Matière en Astrophysique et Atmosphères = Laboratory for Studies of Radiation and Matter in Astrophysics and Atmospheres [LERMA]
dc.contributor.authorBEŠLIĆ, Ivana
hal.structure.identifierInstituto de Física Fundamental [Madrid] [IFF]
dc.contributor.authorSANTA-MARIA, Miriam
hal.structure.identifierInstitut de RadioAstronomie Millimétrique [IRAM]
dc.contributor.authorORKISZ, Jan
hal.structure.identifierInstitut de RadioAstronomie Millimétrique [IRAM]
hal.structure.identifierInstitut des Matériaux, de Microélectronique et des Nanosciences de Provence [IM2NP]
dc.contributor.authorSÉGAL, Léontine
hal.structure.identifierInstitut de recherche en astrophysique et planétologie [IRAP]
dc.contributor.authorZAKARDJIAN, Antoine
hal.structure.identifierInstitut de RadioAstronomie Millimétrique [IRAM]
dc.contributor.authorBARDEAU, Sébastien
hal.structure.identifierLaboratoire d'Etude du Rayonnement et de la Matière en Astrophysique et Atmosphères = Laboratory for Studies of Radiation and Matter in Astrophysics and Atmospheres [LERMA]
dc.contributor.authorGERIN, Maryvonne
hal.structure.identifierInstituto de Física Fundamental [Madrid] [IFF]
dc.contributor.authorGOICOECHEA, Javier
hal.structure.identifierLaboratoire d'Astrophysique de Bordeaux [Pessac] [LAB]
dc.contributor.authorGRATIER, Pierre
hal.structure.identifierPontificia Universidad Católica de Chile [UC]
dc.contributor.authorGUZMAN, Viviana
hal.structure.identifierInstitut de recherche en astrophysique et planétologie [IRAP]
dc.contributor.authorHUGHES, Annie
hal.structure.identifierLaboratoire de Radioastronomie [LRA]
dc.contributor.authorLEVRIER, François
hal.structure.identifierNational Radio Astronomy Observatory [Charlottesville] [NRAO]
dc.contributor.authorLISZT, Harvey
hal.structure.identifierLaboratoire d'Etude du Rayonnement et de la Matière en Astrophysique et Atmosphères = Laboratory for Studies of Radiation and Matter in Astrophysics and Atmospheres [LERMA]
dc.contributor.authorLE BOURLOT, Jacques
hal.structure.identifierInstitut des Matériaux, de Microélectronique et des Nanosciences de Provence [IM2NP]
dc.contributor.authorROUEFF, Antoine
hal.structure.identifierInstituto de RadioAstronomía Milimétrica [IRAM]
dc.contributor.authorSIEVERS, Albrecht
dc.date.issued2023-10
dc.identifier.issn0004-6361
dc.description.abstractEnContext. The interpretation of observations of atomic and molecular tracers in the galactic and extragalactic interstellar medium (ISM) requires comparisons with state-of-the-art astrophysical models to infer some physical conditions. Usually, ISM models are too timeconsuming for such inference procedures, as they call for numerous model evaluations. As a result, they are often replaced by an interpolation of a grid of precomputed models. Aims. We propose a new general method to derive faster, lighter, and more accurate approximations of the model from a grid of precomputed models for use in inference procedures. Methods. These emulators are defined with artificial neural networks (ANNs) with adapted architectures and are fitted using regression strategies instead of interpolation methods. The specificities inherent in ISM models need to be addressed to design and train adequate ANNs. Indeed, such models often predict numerous observables (e.g., line intensities) from just a few input physical parameters and can yield outliers due to numerical instabilities or physical bistabilities and multistabilities. We propose applying five strategies to address these characteristics: (1) an outlier removal procedure; (2) a clustering method that yields homogeneous subsets of lines that are simpler to predict with different ANNs; (3) a dimension reduction technique that enables us to adequately size the network architecture; (4) the physical inputs are augmented with a polynomial transform to ease the learning of nonlinearities; and (5) a dense architecture to ease the learning of simpler relations between line intensities and physical parameters. Results. We compare the proposed ANNs with four standard classes of interpolation methods, nearest-neighbor, linear, spline, and radial basis function (RBF), to emulate a representative ISM numerical model known as the Meudon PDR code. Combinations of the proposed strategies produce networks that outperform all interpolation methods in terms of accuracy by a factor of 2 in terms of the average error (reaching 4.5% on the Meudon PDR code) and a factor of 3 for the worst-case errors (33%). These networks are also 1000 times faster than accurate interpolation methods and require ten to forty times less memory. Conclusions. This work will enable efficient inferences on wide-field multiline observations of the ISM.
dc.description.sponsorshipInférence rapide et contrôle de l'incertitude: applications aux observations astrophysiques. - ANR-20-CHIA-0031
dc.description.sponsorshipAnalyse Détaillée du Milieu Inter-Stellaire - ANR-21-CE31-0010
dc.language.isoen
dc.publisherEDP Sciences
dc.rights.urihttp://creativecommons.org/licenses/by/
dc.subject.enastrochemistry
dc.subject.enmethods: numerical
dc.subject.enmethods: statistical
dc.subject.enISM: clouds
dc.subject.enISM: lines and bands
dc.title.enNeural network-based emulation of interstellar medium models
dc.typeArticle de revue
dc.identifier.doi10.1051/0004-6361/202347074
dc.subject.halPhysique [physics]/Astrophysique [astro-ph]
dc.subject.halStatistiques [stat]/Applications [stat.AP]
dc.identifier.arxiv2309.01724
bordeaux.journalAstronomy and Astrophysics - A&A
bordeaux.pageA198
bordeaux.volume678
bordeaux.peerReviewedoui
hal.identifierhal-04264319
hal.version1
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-04264319v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Astronomy%20and%20Astrophysics%20-%20A&A&rft.date=2023-10&rft.volume=678&rft.spage=A198&rft.epage=A198&rft.eissn=0004-6361&rft.issn=0004-6361&rft.au=PALUD,%20Pierre&EINIG,%20Lucas&LE%20PETIT,%20Franck&BRON,%20%C3%89meric&CHAINAIS,%20Pierre&rft.genre=article


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée