Machine Learning vs. Spectral Energy Distribution Fitting: A Comparative Analysis of Accuracy in Stellar Mass Estimation

Abstract

Traditional spectral energy distribution (SED)-fitting methods for stellar mass estimation face persistent challenges including systematic biases and computational constraints. We present a controlled comparison of machine learning (ML) and SED-fitting methods, assessing their accuracy, robustness, and computational efficiency. Using a sample of COSMOS-like galaxies from the Horizon-AGN simulation as a benchmark with known true masses, we evaluate the Parametric t-SNE (Pt-SNE) algorithm -- trained on noise-injected BC03 models -- against the established SED-fitting code LePhare. Our results demonstrate that Pt-SNE achieves superior accuracy, with a root-mean-square error (sigma_F) of 0.169 dex compared to LePhare's 0.306 dex. Crucially, Pt-SNE exhibits significantly lower bias (0.029 dex) compared to LePhare (0.286 dex). Pt-SNE also shows greater robustness across all stellar mass ranges, particularly for low-mass galaxies (10^9 to 10^10 solar masses), where it reduces errors by 47-53 %. Even when restricted to only six optical bands, Pt-SNE outperforms LePhare using all 26 available photometric bands, underscoring its superior informational efficiency. Computationally, Pt-SNE processes large datasets approximately 3.2 x 10^3 times faster than LePhare. These findings highlight the fundamental advantages of ML methods for stellar mass estimation, demonstrating their potential to deliver more accurate, stable, and scalable measurements for large-scale galaxy surveys.

13 pages, 9 figures, 2 tables, Accepted for Publication in ApJ

References in corpus (28)

• Stellar population synthesis at the resolution of 2003
• Galactic Stellar and Substellar Initial Mass Function
• The Average Star Formation Histories of Galaxies in Dark Matter Halos from z=0-8
• Mass and environment as drivers of galaxy evolution in SDSS and zCOSMOS and the origin of the Schechter function
• The propagation of uncertainties in stellar population synthesis modeling I: The relevance of uncertain aspects of stellar evolution and the IMF to the derived physical properties of galaxies
• EAZY: A Fast, Public Photometric Redshift Code
• Accurate photometric redshifts for the CFHT Legacy Survey calibrated using the VIMOS VLT Deep Survey
• Physical Models of Galaxy Formation in a Cosmological Framework
• The Dependence of Star Formation History and Internal Structure on Stellar Mass for 10^5 Low-Redshift Galaxies
• The COSMOS2015 Catalog: Exploring the 1<z<6 Universe with half a million galaxies
• Modeling the Panchromatic Spectral Energy Distributions of Galaxies
• Dancing in the dark: galactic properties trace spin swings along the cosmic web
• Inferring the star-formation histories of massive quiescent galaxies with BAGPIPES: Evidence for multiple quenching mechanisms
• Deriving Physical Properties from Broadband Photometry with Prospector: Description of the Model and a Demonstration of its Accuracy Using 129 Galaxies in the Local Universe
• The Cosmic Evolution Survey (COSMOS): Subaru Observations of the HST COSMOS Field
• The origin and implications of dark matter anisotropic cosmic infall on ~L* haloes
• An Older, More Quiescent Universe from Panchromatic SED Fitting of the 3D-HST Survey
• The Horizon-AGN simulation: evolution of galaxy properties over cosmic time
• Encoding the infrared excess (IRX) in the NUVrK color diagram for star-forming galaxies
• A Critical Assessment of Stellar Mass Measurement Methods
• Reconstruction of Galaxy Star Formation Histories through SED Fitting: The Dense Basis Approach
• On the importance of using appropriate spectral models to derive physical properties of galaxies at 0.7<z<2.8
• Horizon-AGN virtual observatory - 1. SED-fitting performance and forecasts for future imaging surveys
• COSMOS2020: Manifold Learning to Estimate Physical Parameters in Large Galaxy Surveys
• Simultaneous Estimation of Photometric Redshifts and SED Parameters: Improved Techniques and a Realistic Error Budget
• Leveraging Machine Learning for Accurate and Fast Stellar Mass Estimation of Galaxies
• Semi-supervised classification of stars, galaxies and quasars using K-means and random-forest approaches
• Machine Learning Classification of COSMOS2020 Galaxies: Quiescent vs. Star-Forming

Cited by in corpus (2)

• COSMOS2025: Machine Learning Classification of Early- and Late-type Galaxies at 0 < z < 3
• COSMOS2025: A Machine Learning Census of Massive Quiescent Galaxies at $2.5<\text{z}<5$