Starkindler: An Uncertainty Aware Objective for Photometric Redshift Estimation

TL;DR

Starkindler introduces a new training objective for photometric redshift estimation that explicitly incorporates observational errors, improving accuracy, calibration, and interpretability of uncertainty estimates in astronomical data analysis.

Contribution

The paper presents Starkindler, a novel method that explicitly models aleatoric uncertainty in photometric redshift estimation, enhancing performance and interpretability over traditional approaches.

Findings

Improved accuracy and calibration in redshift predictions.

Reduction in outlier rate compared to baseline models.

Excluding observational errors degrades model performance.

Abstract

Photometric Redshift is critical for analyzing astronomical objects, but existing ML methods often overlook the aleatoric uncertainties inherent in observed data. We introduce Starkindler, a novel training objective that explicitly incorporates observational errors into the model's objective function, thereby directly accounting for aleatoric uncertainty. Unlike traditional probabilistic models that focus solely on epistemic uncertainty, Starkindler provides uncertainty estimates that are regularised by aleatoric uncertainty, and is designed to be more interpretable. We train a simple convolutional neural network (CNN) using data from Sloan Digital Sky Survey (SDSS) and compare against the Photometric redshift estimates provided by SDSS. We show improvements in accuracy, calibration and reduction in predicted outlier rate. We also conduct an ablation study which confirms that excluding observational errors significantly degrades model performance, underscoring the importance of accounting for aleatoric uncertainty. Our results suggest that Starkindler not only enhances predictive performance but also provides interpretable uncertainty estimates, making it a robust tool for astronomical data analysis.