Year: 2026
Type: preprint
Abstract: Photometric redshifts are essential for large-scale structure analyses, yet extracting optimal point estimates and reliability measures from the probability distribution functions (PDZs) delivered by modern photo-$z$ pipelines remains challenging. We introduce turboPDZ, a machine-learning framework using PDZ features and associated observables to optimize redshift point estimates and derive a data-driven reliability score. We apply it to the three independent HSC-SSP PDR3 pipelines (DEmP, DNNz, Mizuki) across Wide and Deep/UltraDeep layers. Each PDZ is compressed via PCA and combined with summary descriptors. A multilayer perceptron, optimized with Optuna under a composite objective ($σ_{\rm NMAD}$ and $η_{0.15}$), predicts $z_{\rm ml}$. A second network, trained in log-space with MAE and calibrated post hoc, yields an empirical error scale $σ_{\rm ml}$, from which the reliability score $r_{\rm ml}$ is derived via percentile ranking. Relative to catalog point estimates, $z_{\rm ml}$ improves both metrics in all six pipeline-layer combinations. Absolute median bias is smaller in four configurations and tied in two. The reliability score achieves the lowest retained-fraction AUC in 10 of 12 native pipeline-layer/metric comparisons. For the Mizuki template-fitting pipeline, catalog reliability indicators have AUC values up to about 13 times larger than those of $r_{\rm ml}$. Feature importance shows that point estimation is dominated by PCA and location statistics, whereas reliability estimation gives greatest weight to peak, PCA, and shape information. The framework is survey-agnostic, but each PDZ dataset requires its own fitted preprocessing, PCA basis, and trained models. The code will be released as a reusable Python library at \href{https://github.com/valerio-marra/turboPDZ}{github.com/valerio-marra/turboPDZ}.
Source: arXiv (Cornell University)
Authors: Duarte, Rodrigo, Marra, Valerio
Language: English
Subfield: Astronomy and Astrophysics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: green
Funders: Princeton University, Ministry of Education, Culture, Sports, Science and Technology, Academia Sinica, Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Cabinet Office, Government of Japan, Conselho Nacional de Desenvolvimento Científico e Tecnológico, Fundação de Amparo à Pesquisa e Inovação do Espírito Santo, National Astronomical Observatory of Japan, High Energy Accelerator Research Organization, Toray Science Foundation, Japan Society for the Promotion of Science, Japan Science and Technology Agency
OpenAlex ID: W7171770374