Estimating Uncertainty in Galaxy Morphology Classification

2026-08-08

AI Summary

Existing methods for galaxy morphology classification struggle to effectively quantify the uncertainty of their predictions, particularly in the presence of data noise and the intrinsic ambiguity arising from galaxy evolution. To address this limitation, this work proposes the UEGMC framework, which systematically decomposes uncertainty into four distinct sources: model, data, reference standard, and physical essence. Leveraging representations from a frozen foundation model, UEGMC enables efficient and fine-grained posterior uncertainty estimation without requiring model retraining or sampling procedures. Experimental results demonstrate that UEGMC matches or surpasses current state-of-the-art approaches in uncertainty quantification while significantly enhancing the reliability of morphological classifications.

Abstract

Astronomers classify galaxy morphology to investigate cosmic evolution. While deep foundation models are increasingly utilized in Galaxy Morphology Classification (GMC), little work has been done on evaluating the uncertainty of GMC results. Uncertainty evaluation is important because astronomical data are inherently noisy due to instrumental and environmental limitations. Also, the continuous evolution of galaxies creates intrinsic morphological ambiguity. However, current foundation models operate as deterministic point estimators, failing to quantify the uncertainty. To overcome this limitation, we propose UEGMC, a post-hoc framework of Uncertainty Estimation for Galaxy Morphology Classification. It categorizes uncertainty in GMC into distinct types by model parameters, astronomical data, reference standards, or intrinsic physical ambiguities, thereby facilitating better classification. Our framework can directly predict uncertainties from representations extracted from the frozen backbones of foundation models, without computationally expensive sampling, therefore enabling fine-grained uncertainty evaluations. Our experimental results demonstrate that UEGMC provides competitive uncertainty quantification performance compared with previous methods.

Problem

• Galaxy Morphology Classification
• Uncertainty Estimation
• Astronomical Data
• Morphological Ambiguity
• Foundation Models

Innovation

• Uncertainty Estimation
• Galaxy Morphology Classification
• Foundation Models
• Post-hoc Framework
• Astronomical Data