S05
Exploring the frontiers of astrophysics with machine learning: New methods and current challenges
Communauté
Contact : nina.kessler@u-bordeaux.fr
Machine learning (ML) has become an integral part of astrophysical research, transforming how data is processed, analyzed and interpreted. The techniques developed by the community are constantly evolving, offering new opportunities and challenges for many topics including cosmological simulations, the study of high-energy phenomena, star characterization, asteroid detection, automatic recognition of land types on planets, or the prediction of critical parameters for Space Weather.
This session aims to bring together members of the astrophysical ML community, as well as those who are curious about the topic, to exchange on the developed methods and their applications for scientific research. We propose a workshop divided into two parts, the first one will focus on presentations covering ML applications in simulations and data analysis. The second part (~1 hour) will be a round-table to address the challenges that are specific to ML approaches, such as model interpretability, data bias, and the integration of ML with traditional methods. This is an occasion to discuss the strengths, limitations, and potential of current methods in solving astrophysical questions, while also identifying the community’s needs.
SOC : Nina Kessler (LAB), Aurelie Marchaudon (IRAP), Paolo Bianchini (ObAS), Sylvain Breton (INAF), Emeric Bron (OBSPM), David Cornu (OBSPM), Pierre Gratier (LAB), Hugo Vivien (LAM)
| Horaire | Contribution | Titre |
|---|---|---|
| 14h | Présentations en anglais (12' + 3' par personne) | |
| 14h00 | Vinh Phat Tran (APC) | YOLO-CL : Deep Machine Learning for Galaxy Cluster Detection with LSST |
| 14h15 | Tristan Boin (OBSPM) | Stellar age determination using deep neural networks |
| 14h30 | Angèle Syty (IAP) | ML approaches for exoplanet atmosphere characterization and detrending methods in the Ariel space mission |
| 14h45 | Théo Bodrito (INRIA) | Deep learning for exoplanet detection and characterization by direct imaging at high contrast |
| 15h00 | Hugo Chambon (IPAG) | Unsupervised classification of spaxels in astronomy |
| 15h15 | Mehdi Noor (IAS) | Generative Diffusion Models for Cosmic Web Environment Emulation |
| 15h30 | Gonzague Radureau (OCA) | Using Artificial Intelligence to speed up Radiative Hydrodynamics simulations |
| 15h45 | Alexis Blaise (CEA) | Leveraging the efficiency of Physics-Informed Neural Networks (PINNs) to monitor the evolution of solar active regions |
| 16h00 | Marian Douspis (IAS) | Emulators in CMB analyses |
| 16h15 | Pause (30') | |
| 16h45 | Flash Talk Posters en anglais (3' par personne) | |
| 16h45 | Merwan Ould-Elhkim (IRAP) | Recovering low-amplitude planetary signals from near-infrared RV data using Wapiti, a PCA-based telluric correction method |
| 16h48 | Amélie Canin (IRAP) | Haute Couture : un algorithme de reconstruction optimale pour les cubes JWST-MIRI |
| 16h51 | Landry Marquis (IRAP) | Fusion of JWST images |
| 16h54 | Hui Yang (IRAP) | Classifying X-ray Sources with Supervised Machine Learning |
| 16h57 | Teng Hu (LAM) | Detecting Halos in the Lyman-α Forest using Neural Networks |
| 17h00 | Kalpa Henadhira Arachchige (CEA) | Machine Learning Approach to Coronal Hole Detection within Solar Cycles and Solar Wind Model Validation |
| 17h03 | Jihane Moultaka (IRAP) | Refining the bimodal distribution of galaxies with ML and GAMA survey |
| 17h10 | Table Ronde en français (20' + 20' par personne) | |
| 17h10 | Simon Dupourqué (IRAP) | Accelerating Bayesian inference in astrophysics through interpretable representations with normalizing flows |
| 17h50 | Nicolas Aunai (LPP Polytechnique) | Interaction magnétosphère-vent solaire : une vision globale apportée par l'apprentissage automatique |
| 18h30 | Fin de l'atelier |
Présentations
| Authors | Title | Type | File |
|---|---|---|---|
| Nicolas Aunai, Bayane Michotte de Welle, Ambre Ghisalberti, Benoit Lavraud, Vincent Génot, Gautier Nguyen, Alexis Jeandet | Interaction magnétosphère-vent solaire : une vision globale apportée par l\'apprentissage automatique | invite | sf2a_abstract_aunai.pdf |
| Amélie Canin, Cédric Févotte, Olivier Berné et Nicolas Dobigeon | Haute Couture : un algorithme de reconstruction optimale pour les cubes JWST-MIRI | poster | Abstract_canin.pdf |
| G. Radureau, C. Michaut | Using Artificial Intelligence to speed up Radiative Hydrodynamics simulations | orale | Radureau_Michaut_2025.pdf |
| Simon Dupourqué | Accelerating Bayesian inference in astrophysics through interpretable representations with normalizing flows | invite | sdupourque.pdf |
| A. Syty (Institut d’Astrophysique de Paris, Sorbonne Université, CNRS), O. Faucoz (CNES), JP. Beaulieu (IAP), P. Drossart (IAP), J. Amiaux (CEA), T. Pichon (CEA), C. Cossou (CEA) | ML approaches for exoplanet atmosphere characterization and detrending methods in the Ariel space mission. | orale | AbstractSF2A.pdf |
| Hui Yang1, Yichao Lin2, Oleg Kargaltsev2, Steven Chen2, Jeremy Hare3 1 Institut de Recherche en Astrophysique et Planétologie (IRAP), Toulouse, France 2 Department of Physics, The George Washington University, Washington, DC, USA 3 NASA Goddard Space Flight Center,Greenbelt, MD, USA | Classifying X-ray Sources with Supervised Machine Learning | poster | MUWCLASS abstract for SF2A 2025 conference.pdf |
| Mehdi Noor, Tony Bonnaire, Aurélien Decelle, Nabila Aghanim | Generative Diffusion Models for Cosmic Web Environment Emulation | orale | SF2A_Abstract_4.pdf |
| Tristan Boin, Laia Casamiquela, Misha Haywood | Stellar age determination using deep neural networks | orale | SF2A_AI.pdf |
| Kalpa Harindra Perera, HENADHIRA ARACHCHIGE Barbara, PERRI Sacha, BRUN Antoine, STRUGAREK Eric, BUCHLIN Victor, REVILLE Marie, AUSSERESSE | Machine Learning Approach to Coronal Hole Detection within Solar Cycles and Solar Wind Model Validation | poster | Abstract_6.pdf |
| Théo Bodrito, Olivier Flasseur, Julien Mairal, Jean Ponce, Maud Langlois, Anne-Marie Lagrange | Deep learning for exoplanet detection and characterization by direct imaging at high contrast | orale | abstract_sf2a_2025_2.pdf |
| Landry Marquis, Olivier Berné, Thomas Oberlin, Nicolas Dobigeon | Fusion of JWST images | poster | Abstract_SF2A_2025 (1).pdf |
| Ould-Elhkim Merwan; Moutou Claire; Donati Jean-François | Recovering low-amplitude planetary signals from near-infrared RV data using Wapiti, a PCA-based telluric correction method | poster | Ould_ElhkimS05.pdf |
| Tran Vinh Phat | YOLO-CL : Deep Machine Learning for Galaxy Cluster Detection with LSST | orale | Abstract YOLO-CL.pdf |
| H.J Chambon, D. Fraix-Burnet | Unsupervised classification of spaxels in astronomy | orale | SF2A_Abstract_MLIFS.pdf |
| Teng Hu, Matthew Pieri, Duarte Muñoz Santos,,Simon Weng | Detecting Halos in the Lyman-α Forest using Neural Networks | poster | Abstract_Hu_SF2A25.pdf |
| Alexis Blaise, Antoine Strugarek, Adam J. Finley, Eric Buchlin, Miho Janvier | Leveraging the efficiency of Physics-Informed Neural Networks (PINNs) to monitor the evolution of solar active regions | orale | Abstract_SF2A_1.pdf |
| Douspis, Gorce, Salvati, McBride | Emulators in CMB analyses | orale | Abstract_Douspis.pdf |
| Jihane Moultaka & Cécilia Beissière-Thygesen | Refining the bimodal distribution of galaxies with ML and GAMA survey | poster | Abstract_SF2A_2025_2.pdf |