We introduce a neural approach to dynamical modeling of galaxies that replaces traditional imaging-based deprojections with a differentiable mapping. Specifically, we train a neural network to translate Nuker profile parameters into analytically deprojectable Multi Gaussian Expansion components, enabling physically realistic stellar mass models without requiring optical observations. We integrate this model into SuperMAGE, a differentiable dynamical modelling pipeline for Bayesian inference of supermassive black hole masses. Applied to ALMA data, our approach finds results consistent with state-of-the-art models while extending applicability to dust-obscured and active galaxies where optical data analysis is challenging.
@article{arxiv.2511.20746,
title = {Neural Deprojection of Galaxy Stellar Mass Profiles},
author = {M. J. Yantovski-Barth and Hengyue Zhang and Nolan Smyth and Connor Stone and Martin Bureau and Yashar Hezaveh and Laurence Perreault-Levasseur},
journal= {arXiv preprint arXiv:2511.20746},
year = {2025}
}
Comments
8 pages, 4 figures, accepted at the Machine Learning and the Physical Sciences Workshop, NeurIPS 2025