Research Interest numerical climate modeling at global scale machine learning, physics informed machine learning hybrid physics and AI-based modeling heterogeneous (mixed GPU and CPU-based) high performance computation Education 2022-present: research scientist. Machine learning for climate modeling, CNRM (Toulouse). 2019-2022: PhD. « Vers une utilisation de l’Intelligence Artificielle dans un modèle numérique de climat ». INP Toulouse. PhD advisors: David Saint-Martin, Aurélien Ribes. 2016-2019: École Nationale de la Météorologie, cycle ingénieur (Toulouse). 2014-2016: CPGE (Paris).
2026 García Cristóbal, J., Wurtz, J., Doury, A., Balogh, B., Masson, V., and Mestre, O. (2026). A Neural Network-based downscaling method for near surface temperature in urban areas. Urban Climate, 68(103076), 103076. 2025 Germain, H., Balogh, B., O. Geoffroy, and D. Saint-Martin, 2025: Improvment of a neural network convection scheme by including triggering and evaluation in present and future climates. Preprint available on arXiv:2511.05074. Balogh, B., D. Saint-Martin, and O. Geoffroy, 2025: Online Test of a Neural Network Deep Convection Parameterization in ARP-GEM1. Artif. Intell. Earth Syst., 4, e240100, https://doi.org/10.1175/AIES-D-24-0100.1. 2022 Balogh, B., Saint-Martin, D., & Ribes, A. (2022). How to calibrate a dynamical system with neural network based physics ? Geophysical Research Letters, 49, e2022GL097872. https://doi.org/10.1029/2022GL097872 2021 Balogh, B., Saint-Martin, D., & Ribes, A. (2021). A toy model to investigate stability of AI-based dynamical systems. Geophysical Research Letters, 48, e2020GL092133. https://doi.org/10.1029/2020GL092133 Presentations & Conferences 2026 Balogh, B. (CNRM, Toulouse), AI for deep convection modeling: identifying and fixing physical inconsistencies, from training to online evaluation. Journées annuelles du GDR « Défis théoriques pour les sciences du climat ». Balogh, B., Germain, H., Geoffroy, O., and Saint-Martin, D.: Online test of a data-driven parameterization of deep-convection: evaluation in present and future climate, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-1118, https://doi.org/10.5194/egusphere-egu26-1118, 2026. 2025 Balogh, B., Germain, H., Geoffroy, O. and Saint-Martin, D.: Climate Simulations with Online Neural Network-based Parameterization of Deep Convection: present and +4K. EXCLAIM! Symposium, Zürich, Swiss, 2-4 June 2025. Event website: https://exclaim-symposium.ethz.ch/ . 2024 Balogh, B., Saint-Martin, D., Geoffroy, O., Bhouri, M. A., and Gentine, P. : Assessment of ARPEGE-Climat using a neural network convection parameterization based upon data from SPCAM 5, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-7455, https://doi.org/10.5194/egusphere-egu24-7455, 2024. 2022 Balogh, B., Saint-Martin, D., and Ribes, A. : How to calibrate a climate model with neural network based physics ?, EGU General Assembly 2022, Vienna, Austria, 23–27 May 2022, EGU22-7135, https://doi.org/10.5194/egusphere-egu22-7135, 2022. 2021 Balogh, B., Saint-Martin, D., and Ribes, A. : A toy model to investigate stability of AI-based dynamical systems, EGU General Assembly 2021, online, 19–30 Apr 2021, EGU21-647, https://doi.org/10.5194/egusphere-egu21-647, 2021.
PN INSU-SUN (2026-2028) : Généralisabilité et Améliorations avec l’IA à travers les résolutions et les Climats
Internships 2026. Stage de M2 (6 mois), Mathurin Moreau (Polytech Lyon). Utilisation de techniques d’IA génératives pour la modélisation de la convection profonde dans ARP-GEM. 2025. Stage de M2 (6 mois), Hugo Germain (ENM, Toulouse). Amélioration d’une paramétrisation IA de la convection profonde dans ARP-GEM.
