Data-driven modeling of rotation curves with artificial neural networks
arXiv:2404.05833 · doi:10.1016/j.dark.2026.102240
Abstract
Galactic rotation curves are crucial for understanding the distribution of mass in galaxies. Despite advances in precision observations, there are discrepancies between the inferred mass from luminosity and the observed rotational velocities, often attributed to dark matter. While traditional parametric models provide valuable insights, they struggle with complex galactic features like prominent bulges and non-circular motions. In this study, we apply artificial neural networks to generate robust, data-driven models, tailored to each galaxy, for the rotation curves of spiral galaxies using high-quality observational data. Our approach demonstrates that neural networks can effectively capture the intricate structure of rotation curves without relying on predefined astrophysical assumptions. By comparing the data-based models with the Navarro-Frenk-White model under two different assumptions for the stellar component, we classify galaxies based on the model that best fits their rotation curves, offering insights into the limitations and strengths of both theoretical and data-based methods. This work highlights the potential of machine learning techniques in identifying galaxies whose dynamics are not well captured by standard theoretical models, pointing to the need for more refined physical descriptions.
11 pages, 3 figures
References in corpus (28)
- Stellar mass-to-light ratios and the Tully-Fisher relation
- THINGS: The HI Nearby Galaxy Survey
- SINGS: The SIRTF Nearby Galaxies Survey
- High-Resolution Rotation Curves and Galaxy Mass Models from THINGS
- Rotation Curves of Spiral Galaxies
- H alpha rotation curves of Low Surface Brightness galaxies
- The dark and baryonic matter content of low surface brightness disk galaxies
- The Universal Rotation Curve of Spiral Galaxies. II The Dark Matter Distribution out to the Virial Radius
- High-resolution dark matter density profiles of THINGS dwarf galaxies: Correcting for non-circular motions
- The universal rotation curve of dwarf disk galaxies
- On The Formation of Disk Galaxies and Massive Central Objects
- Reconstructing Functions and Estimating Parameters with Artificial Neural Networks: A Test with the Hubble Parameter and SNe Ia
- Model-independent reconstruction of the Interacting Dark Energy Kernel: Binned and Gaussian process
- Testing the Mutual Consistency of the Pantheon and SDSS/eBOSS BAO Data Sets with Gaussian Processes
- Model selection applied to reconstructions of the Dark Energy
- The dark matter profile of the Milky Way: a non-parametric reconstruction
- Neural network reconstructions for the Hubble parameter, growth rate and distance modulus
- Defying the laws of Gravity I: model-independent reconstruction of the Universe expansion from growth data
- Automatic detection of low surface brightness galaxies from SDSS images
- Bayesian analysis for rotational curves with -boson stars as a dark matter component
- Neural Networks Optimized by Genetic Algorithms in Cosmology
- Structural properties of faint low surface brightness galaxies
- Non-parametric reconstruction of cosmological observables using Gaussian Processes Regression
- Testing modified gravity at large distances with the HI Nearby Galaxy Survey's rotation curves
- Galaxy rotation curves using a non-parametric regression method: core, cusp and fuzzy scalar field dark matter models
- Shedding Light on Low Surface Brightness Galaxies in Dark Energy Survey with Transformers
- Dark energy reconstruction analysis with artificial neural networks: Application on simulated Supernova Ia data from Rubin Observatory
- Galaxy Rotation Curve Fitting Using Machine Learning Tools