Machine learning the gap between real and simulated nebulae

A domain-adaptation approach to classify ionised nebulae in nearby galaxies

¹ INAF – Arcetri Astrophysical Observatory, Largo E. Fermi 5, I-50125 Florence, Italy
² Università di Firenze, Dipartimento di Fisica e Astronomia, via G. Sansone 1, 50019 Sesto Fiorentino, Florence, Italy
³ The Observatories of the Carnegie Institution for Science, 813 Santa Barbara St, Pasadena, CA 91101, USA
⁴ Departamento de Astronomía, Universidad de Chile, Camino del Observatorio, 1515 Las Condes, Santiago, Chile
⁵ Université Côte d’Azur, Observatoire de la Côte d’Azur, CNRS, Laboratoire Lagrange, 06000 Nice, France
⁶ Universität Heidelberg, Zentrum für Astronomie, Institut für Theoretische Astrophysik, Albert-Ueberle-Straße 2, D-69120 Heidelberg, Germany
⁷ European Southern Observatory (ESO), Alonso de Córdova 3107, Casilla 19, Santiago 19001, Chile
⁸ International Centre for Radio Astronomy Research, University of Western Australia, 7 Fairway, Crawley, 6009 WA, Australia
⁹ Astronomisches Rechen-Institut, Zentrum für Astronomie der Universität Heidelberg, Mönchhofstraße 12-14, D-69120 Heidelberg, Germany
¹⁰ Universität Heidelberg, Interdisziplinäres Zentrum für Wissenschaftliches Rechnen, Im Neuenheimer Feld 225, 69120 Heidelberg, Germany
¹¹ Center for Astrophysics | Harvard & Smithsonian, 60 Garden Street, Cambridge MA 02138, USA
¹² Radcliffe Institute for Advanced Studies at Harvard University, 10 Garden Street, Cambridge, MA 02138, USA
¹³ Sub-department of Astrophysics, Department of Physics, University of Oxford, Keble Road, Oxford OX1 3RH, UK

^⋆ Corresponding author; francesco.belfiore@inaf.it

Received: 20 August 2024
Accepted: 15 January 2025

Abstract

Classifying ionised nebulae in nearby galaxies is crucial to studying stellar feedback mechanisms and understanding the physical conditions of the interstellar medium. This classification task is generally performed by comparing observed line ratios with photoionisation simulations of different types of nebulae (H II regions, planetary nebulae, and supernova remnants). However, due to simplifying assumptions, such simulations are generally unable to fully reproduce the line ratios in observed nebulae. This discrepancy limits the performance of the classical machine-learning approach, where a model is trained on the simulated data and then used to classify real nebulae. For this study, we used a domain-adversarial neural network (DANN) to bridge the gap between photoionisation models (source domain) and observed ionised nebulae from the PHANGS-MUSE survey (target domain). The DANN is an example of a domain-adaptation algorithm, whose goal is to maximise the performance of a model trained on labelled data in the source domain on an unlabelled target domain by extracting domain-invariant features. Our results indicate a significant improvement in classification performance in the target domain when employing the DANN framework compared to a classical neural network (NN) classifier. Additionally, we investigated the impact of adding noise to the source dataset, finding that noise injection acts as a form of regularisation, further enhancing the performances of both the NN and DANN models on the observational data. The combined use of domain adaptation and noise injection improved the classification accuracy in the target domain by 23%. This study highlights the potential of domain adaptation methods in tackling the domain-shift challenge when using theoretical models to train machine-learning pipelines in astronomy.