arxiv: 2605.06790 · v1 · submitted 2026-05-07 · 🌌 astro-ph.IM · astro-ph.CO· astro-ph.GA

Recognition: 2 theorem links

· Lean Theorem

Machine Learning Techniques for Astrophysics and Cosmology: Photometric Redshifts

Luca Tortorelli , Daniel Gr\"un

Authors on Pith no claims yet

Pith reviewed 2026-05-11 00:46 UTC · model grok-4.3

classification 🌌 astro-ph.IM astro-ph.COastro-ph.GA

keywords photometric redshiftsmachine learningcosmologyastrophysicsgenerative modelsBayesian modelingspectroscopic training datadiscriminative regression

0 comments

The pith

Discriminative machine learning for photometric redshifts has converged because limits now come from spectroscopic training data rather than from the choice of algorithm.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This review surveys the range of artificial intelligence techniques developed to estimate galaxy redshifts from broadband images, a task made necessary because full spectroscopic observations remain expensive. The authors conclude that the many variants of regression-based machine learning have reached a practical plateau. Gains no longer depend on refining the algorithms themselves but instead on the limited size, systematic uncertainties, and selection biases present in the spectroscopic samples used to train them. Advancement therefore requires either far larger and cleaner training data or a shift toward generative models that embed Bayesian reasoning about galaxy populations and the effects of telescope observations.

Core claim

The diversity of discriminative AI methods applied to regress redshift from photometric observables has effectively converged. Progress is now limited not by the AI methodology but by the size and substantial systematic uncertainties and selection effects in spectroscopic training samples. In order to progress, either an unobtainable quantity and quality of training data or a more principled approach in using it is required, in the form of generative models for representing the distribution of intrinsic properties and outcomes of telescope observations of the galaxy population.

What carries the argument

Discriminative regression that maps photometric observables directly to redshift estimates, set against generative models that represent the underlying distribution of galaxy properties and observational effects.

If this is right

Further tuning of existing regression methods will produce only application-specific improvements rather than broad advances in accuracy.
Substantial progress in photometric redshift quality requires spectroscopic training samples that are larger and freer of systematic biases than those currently available.
Integrating artificial intelligence into Bayesian generative modeling allows explicit representation of intrinsic galaxy properties and telescope observation effects.
Generative approaches can capture selection effects and uncertainties in a way that purely discriminative regression cannot.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

Hybrid models that combine physical galaxy evolution with machine learning components could reduce reliance on perfect training data.
Upcoming imaging surveys would see reduced systematic errors in cosmological analyses if generative Bayesian methods replace current photo-z pipelines.
Controlled tests on simulated catalogs with injected selection biases could quantify whether the proposed generative shift improves calibration.

Load-bearing premise

The surveyed variety of AI regression techniques is representative of what is possible, and further large gains from purely discriminative machine learning are not feasible without changes to the training data or the modeling framework.

What would settle it

A new discriminative machine learning algorithm that produces substantially more accurate photometric redshifts than current methods when tested on the same existing spectroscopic samples, without using extra data or generative components, would falsify the convergence claim.

Figures

Figures reproduced from arXiv: 2605.06790 by Daniel Gr\"un, Luca Tortorelli.

**Figure 1.1.** Figure 1.1: Figure 1 of [ [PITH_FULL_IMAGE:figures/full_fig_p005_1_1.png] view at source ↗

**Figure 1.2.** Figure 1.2: Photo-z point estimation from observed magnitudes mi with a fully connected artificial neural network, introduced by ANNz [37, 38], was a key starting point of AI in photo-z and astrophysics more generally. Source [PITH_FULL_IMAGE:figures/full_fig_p009_1_2.png] view at source ↗

**Figure 1.3.** Figure 1.3: Illustration of the effects limiting clustering-based methods for photo- [PITH_FULL_IMAGE:figures/full_fig_p012_1_3.png] view at source ↗

**Figure 1.4.** Figure 1.4: Illustration of the hierarchical formulation of photo- [PITH_FULL_IMAGE:figures/full_fig_p016_1_4.png] view at source ↗

read the original abstract

The cosmological redshift of a galaxy's light is inferable from its observable properties in images. Because imaging is much easier to acquire than spectroscopic observations that would allow the identification of distinct line features, this motivates the technique of photometric redshift estimation (photo-$z$). Photo-$z$ has been an early and sustained driver for the utilization of artificial intelligence (AI) in astrophysics, and conversely AI methods are underlying most of the recent advances in photo-$z$. Here we review the diversity of AI methods applied to the photo-$z$ problem over the years in a discriminative way, that is, to regress redshift from photometric observables. We argue that, besides optimization suiting specific applications, this approach has effectively converged. It is limited not by the AI methodology but by the size and substantial systematic uncertainties and selection effects in spectroscopic training samples. In order to progress, either an unobtainable quantity and quality of training data or a more principled approach in using it is required. We thus outline ongoing research of integrating AI in a Bayesian modeling of galaxy data. This comes in the form of generative models for representing the distribution of intrinsic properties and outcomes of telescope observations of the galaxy population.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This review claims discriminative ML for photo-z has converged due to training data limits and points to generative models, but the convergence argument lacks quantitative support.

read the letter

The key thing to know about this paper is that it reviews AI techniques for photometric redshifts and concludes that the discriminative methods have converged, with the real limits coming from training data rather than algorithms. It recommends exploring generative models instead. It does well by bringing together the history of these methods in one place. The authors cover how different machine learning models have been applied to regress redshifts from photometric observables and note their role in recent advances. What is new is the argument for convergence and the high-level description of integrating AI with Bayesian modeling of galaxy data through generative approaches. The soft spot is the absence of a quantitative basis for the convergence claim. Without benchmarking performance trends or comparing methods systematically on fixed datasets, the assertion that further improvements are not possible remains qualitative. This paper is for people in the photo-z community or those involved in cosmological surveys who want a consolidated view of the ML landscape. It could inform strategies for data acquisition or modeling. I think it should go to peer review. Reviews that synthesize literature and propose directions are worth refereeing, and this one engages honestly with the field. The authors can address the evidence gap in revision.

Referee Report

2 major / 2 minor

Summary. This review surveys the application of discriminative machine learning methods to photometric redshift (photo-z) estimation, arguing that these approaches have effectively converged and are now limited primarily by the size, systematics, and selection effects in spectroscopic training samples rather than by algorithmic innovation. It outlines the historical diversity of AI techniques for regressing redshift from photometric observables and advocates shifting toward generative models integrated with Bayesian galaxy modeling to enable further progress.

Significance. If the convergence assessment holds, the paper would usefully redirect community effort from new discriminative architectures toward data curation and generative frameworks, with potential impact on upcoming surveys (e.g., LSST, Euclid) where photo-z precision is critical. The review synthesizes a broad literature and correctly identifies training-data bottlenecks as a central constraint; however, the absence of quantitative meta-analysis reduces its immediate utility as a definitive benchmark.

major comments (2)

[Abstract] Abstract and opening sections: the central claim that 'this approach has effectively converged' is asserted without a quantitative meta-analysis or trend plot of performance metrics (e.g., σ_NMAD, bias, or catastrophic outlier fraction) versus publication year or model class on fixed benchmark datasets such as SDSS, COSMOS, or DES. A qualitative survey alone cannot rule out incremental gains from architectural or training advances under current data constraints.
[Generative models outline] Section on generative models (final paragraphs): the proposed integration of AI via generative models for galaxy populations and telescope observations is presented at a high level only, without concrete examples, likelihood formulations, or direct performance comparisons against the reviewed discriminative methods on the same datasets.

minor comments (2)

Notation for photometric observables and redshift estimators should be standardized across the review to avoid reader confusion when comparing methods.
A table summarizing key papers, their architectures, and reported metrics on common benchmarks would improve readability and support the convergence argument.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their thoughtful and constructive review. We address each major comment below, providing our response and indicating the revisions we will make to the manuscript.

read point-by-point responses

Referee: [Abstract] Abstract and opening sections: the central claim that 'this approach has effectively converged' is asserted without a quantitative meta-analysis or trend plot of performance metrics (e.g., σ_NMAD, bias, or catastrophic outlier fraction) versus publication year or model class on fixed benchmark datasets such as SDSS, COSMOS, or DES. A qualitative survey alone cannot rule out incremental gains from architectural or training advances under current data constraints.

Authors: We appreciate the referee's point that a quantitative meta-analysis would provide stronger support for the convergence claim. Our review is a synthesis of the existing literature rather than a new benchmark study, and performing a full meta-analysis would require reprocessing heterogeneous datasets and metrics under uniform conditions, which lies outside the scope of this work. However, we acknowledge that the current presentation relies on qualitative assessment. In the revised manuscript, we will expand the introduction and discussion sections to include a summary of representative performance trends drawn from key published studies on common benchmarks (e.g., SDSS and COSMOS), citing papers that report or plot metrics such as σ_NMAD and outlier fractions over time. This will offer additional evidence of saturation without claiming a comprehensive new meta-analysis. revision: partial
Referee: [Generative models outline] Section on generative models (final paragraphs): the proposed integration of AI via generative models for galaxy populations and telescope observations is presented at a high level only, without concrete examples, likelihood formulations, or direct performance comparisons against the reviewed discriminative methods on the same datasets.

Authors: We agree that the generative models section is presented at a high level, as it is intended to outline promising future directions rather than deliver a detailed technical review of that emerging area. To address this, we will revise the final section to incorporate specific examples from recent literature on generative approaches (such as variational autoencoders and normalizing flows applied to galaxy spectral energy distributions and observational effects). We will include brief descriptions of likelihood formulations where they appear in the cited works and note the current status of comparisons to discriminative methods, emphasizing that standardized benchmarks are still developing. This will provide more substance while preserving the review's focus on the shift in research direction. revision: yes

Circularity Check

0 steps flagged

Review synthesis with no derivations or self-referential reductions

full rationale

This paper is a literature review of AI methods for photometric redshift estimation. It presents no equations, derivations, fitted parameters, or predictions that could reduce to inputs by construction. The central claim that discriminative ML approaches have converged (limited by training data rather than methodology) is a qualitative synthesis of external work, not a self-contained derivation or self-citation chain. No load-bearing steps exist that match the enumerated circularity patterns, making the analysis self-contained as a survey.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The paper is a review and introduces no new free parameters, axioms, or invented entities; its claims rest on synthesis of existing methods and data limitations described in the cited literature.

pith-pipeline@v0.9.0 · 5511 in / 1058 out tokens · 65907 ms · 2026-05-11T00:46:14.544520+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Cost/FunctionalEquation.lean washburn_uniqueness_aczel unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

We argue that, besides optimization suiting specific applications, this approach has effectively converged. It is limited not by the AI methodology but by the size and substantial systematic uncertainties and selection effects in spectroscopic training samples.
IndisputableMonolith/Foundation/RealityFromDistinction.lean reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

We thus outline ongoing research of integrating AI in a Bayesian modeling of galaxy data. This comes in the form of generative models for representing the distribution of intrinsic properties and outcomes of telescope observations of the galaxy population.

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

172 extracted references · 161 canonical work pages · 5 internal anchors

[1]

Ivezicet al.(LSST), LSST: from Science Drivers to Reference Design and Anticipated Data Products, As- trophys

ˇZ. Ivezi´c, S. M. Kahn, J. A. Tyson, B. Abel, E. Acosta, R. Allsman et al.,LSST: From Science Drivers to Reference Design and Anticipated Data Products,The Astrophysical Journal873(2019) 111 [0805.2366]

work page arXiv 2019
[2]

Mellieret al.(Euclid), Euclid

Euclid Collaboration, Y . Mellier, Abdurro’uf, J. A. Acevedo Barroso, A. Ach´ucarro, J. Adamek et al.,Euclid: I. Overview of the Euclid mission,Astronomy & Astrophysics697 (2025) A1 [2405.13491]

work page arXiv 2025
[3]

Abareshi, J

DESI Collaboration, B. Abareshi, J. Aguilar, S. Ahlen, S. Alam, D. M. Alexander et al., Overview of the Instrumentation for the Dark Energy Spectroscopic Instrument,The Astronomical Journal164(2022) 207 [2205.10939]

work page arXiv 2022
[4]

R. S. de Jong, O. Agertz, A. A. Berbel, J. Aird, D. A. Alexander, A. Amarsi et al.,4MOST: Project overview and information for the First Call for Proposals,The Messenger175 (2019) 3 [1903.02464]

work page arXiv 2019
[5]

Extragalactic Science, Cosmology and Galactic Archaeology with the Subaru Prime Focus Spectrograph (PFS)

M. Takada, R. S. Ellis, M. Chiba, J. E. Greene, H. Aihara, N. Arimoto et al.,Extragalactic science, cosmology, and Galactic archaeology with the Subaru Prime Focus Spectrograph, Publications of the Astronomical Society of Japan66(2014) R1 [1206.0737]

work page Pith review arXiv 2014
[6]

Report of the Dark Energy Task Force

A. Albrecht, G. Bernstein, R. Cahn, W. L. Freedman, J. Hewitt, W. Hu et al.,Report of the Dark Energy Task Force,arXiv e-prints(2006) astro [astro-ph/0609591]

work page Pith review arXiv 2006
[7]

J. A. Newman and D. Gruen,Photometric Redshifts for Next-Generation Surveys,Annual Review of Astronomy and Astrophysics60(2022) 363 [2206.13633]

work page arXiv 2022
[8]

Salvato, O

M. Salvato, O. Ilbert and B. Hoyle,The many flavours of photometric redshifts,Nature Astronomy3(2019) 212 [1805.12574]

work page arXiv 2019
[9]

Buchs, C

R. Buchs, C. Davis, D. Gruen, J. DeRose, A. Alarcon, G. M. Bernstein et al.,Phenotypic redshifts with self-organizing maps: A novel method to characterize redshift distributions of source galaxies for weak lensing,Monthly Notices of the Royal Astronomical Society489 (2019) 820 [1901.05005]

work page arXiv 2019
[10]

The Dark Energy Survey Collaboration,The Dark Energy Survey,arXiv e-prints(2005) astro [astro-ph/0510346]

work page arXiv 2005
[11]

G. B. Dalton, M. Caldwell, A. K. Ward, M. S. Whalley, G. Woodhouse, R. L. Edeson et al., The VISTA infrared camera, inGround-based and Airborne Instrumentation for Astronomy (I. S. McLean and M. Iye, eds.), vol. 6269 ofSociety of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, p. 62690X, June, 2006, DOI. 22 Luca Tortorelli and Daniel Gr ¨un

2006
[12]

L. J. M. Davies, A. S. G. Robotham, S. P. Driver, C. P. Lagos, L. Cortese, E. Mannering et al.,Deep Extragalactic VIsible Legacy Survey (DEVILS): motivation,design, and target catalogue,Monthly Notices of the Royal Astronomical Society480(2018) 768 [1806.05808]

work page arXiv 2018
[13]

Guzzoet al., A&A566, A108 (2014), arXiv:1303.2623 [astro-ph.CO]

L. Guzzo, M. Scodeggio, B. Garilli, B. R. Granett, A. Fritz, U. Abbas et al.,The VIMOS Public Extragalactic Redshift Survey (VIPERS). An unprecedented view of galaxies and large-scale structure at 0.5 ¡ z ¡ 1.2,Astronomy & Astrophysics566(2014) A108 [1303.2623]

work page arXiv 2014
[14]

S. P. Driver, S. Bellstedt, A. S. G. Robotham, I. K. Baldry, L. J. Davies, J. Liske et al., Galaxy And Mass Assembly (GAMA): Data Release 4 and the z ¡ 0.1 total and z ¡ 0.08 morphological galaxy stellar mass functions,Monthly Notices of the Royal Astronomical Society513(2022) 439 [2203.08539]

work page arXiv 2022
[15]

E. S. Rykoff, E. Rozo, M. T. Busha, C. E. Cunha, A. Finoguenov, A. Evrard et al., redMaPPer. I. Algorithm and SDSS DR8 Catalog,The Astrophysical Journal785(2014) 104 [1303.3562]

work page arXiv 2014
[16]

Oguri,A cluster finding algorithm based on the multiband identification of red sequence galaxies,Monthly Notices of the Royal Astronomical Society444(2014) 147 [1407.4693]

M. Oguri,A cluster finding algorithm based on the multiband identification of red sequence galaxies,Monthly Notices of the Royal Astronomical Society444(2014) 147 [1407.4693]

work page arXiv 2014
[17]

Bellagamba, M

F. Bellagamba, M. Roncarelli, M. Maturi and L. Moscardini,AMICO: optimized detection of galaxy clusters in photometric surveys,Monthly Notices of the Royal Astronomical Society473(2018) 5221 [1705.03029]

work page arXiv 2018
[18]

Aguena, C

M. Aguena, C. Benoist, L. N. da Costa, R. L. C. Ogando, J. Gschwend, H. B. Sampaio-Santos et al.,The WaZP galaxy cluster sample of the dark energy survey year 1, Monthly Notices of the Royal Astronomical Society502(2021) 4435 [2008.08711]

work page arXiv 2021
[19]

Weak lensing for precision cosmology

R. Mandelbaum,Weak Lensing for Precision Cosmology,Annual Review of Astronomy and Astrophysics56(2018) 393 [1710.03235]

work page Pith review arXiv 2018
[20]

Prat and D

J. Prat and D. Bacon,Weak gravitational lensing, inEncyclopedia of Astrophysics, Volume 5, vol. 5, pp. 508–537, Jan., 2026,2501.07938, DOI

work page arXiv 2026
[21]

KiDS-1000 Cosmology: Cosmic shear constraints and comparison between two point statistics

M. Asgari, C.-A. Lin, B. Joachimi, B. Giblin, C. Heymans, H. Hildebrandt et al., KiDS-1000 cosmology: Cosmic shear constraints and comparison between two point statistics,Astronomy & Astrophysics645(2021) A104 [2007.15633]

work page arXiv 2021
[22]

and Sugiyama, Sunao and Zhang, Tianqing and Rau, Markus M

R. Dalal, X. Li, A. Nicola, J. Zuntz, M. A. Strauss, S. Sugiyama et al.,Hyper Suprime-Cam Year 3 results: Cosmology from cosmic shear power spectra,Physical Review D108(2023) 123519 [2304.00701]

work page arXiv 2023
[23]

A. Amon, D. Gruen, M. A. Troxel, N. MacCrann, S. Dodelson, A. Choi et al.,Dark Energy Survey Year 3 results: Cosmology from cosmic shear and robustness to data calibration, Physical Review D105(2022) 023514 [2105.13543]

work page arXiv 2022
[25]

Pantos and L

I. Pantos and L. Perivolaropoulos,Status of the S 8 tension: A 2026 review of probe discrepancies,Physics of the Dark Universe52(2026) 102286 [2602.12238]

work page arXiv 2026
[26]

Planck 2018 results. VI. Cosmological parameters

Planck Collaboration, N. Aghanim, Y . Akrami, M. Ashdown, J. Aumont, C. Baccigalupi et al.,Planck 2018 results. VI. Cosmological parameters,Astronomy & Astrophysics641 (2020) A6 [1807.06209]

work page internal anchor Pith review Pith/arXiv arXiv 2018
[27]

Amon and G

A. Amon and G. Efstathiou,A non-linear solution to the S 8 tension?,Monthly Notices of the Royal Astronomical Society516(2022) 5355 [2206.11794]

work page arXiv 2022
[28]

A. H. Wright, B. St ¨olzner, M. Asgari, M. Bilicki, B. Giblin, C. Heymans et al., KiDS-Legacy: Cosmological constraints from cosmic shear with the complete Kilo-Degree Survey,Astronomy & Astrophysics703(2025) A158 [2503.19441]

work page arXiv 2025
[29]

Cosmic Shear constraints from HSC Year 3 with clustering calibration of the tomographic redshift distributions from DESI

J. Choppin de Janvry, B. Dai, S. G. A. Gontcho, U. Seljak and T. Zhang,Cosmic Shear constraints from HSC Year 3 with clustering calibration of the tomographic redshift distributions from DESI,arXiv e-prints(2025) arXiv:2511.18134 [2511.18134]. 1 Photometric Redshifts 23

work page internal anchor Pith review Pith/arXiv arXiv 2025
[30]

Bigwood, J

L. Bigwood, J. McCullough, J. Siegel, A. Amon, G. Efstathiou, D. Sanchez-Cid et al., Confronting cosmic shear astrophysical uncertainties: DES Year 3 revisited,arXiv e-prints (2025) arXiv:2512.04209 [2512.04209]

work page arXiv 2025
[31]

2018, arXiv e-prints, arXiv:1809.01669

The LSST Dark Energy Science Collaboration, R. Mandelbaum, T. Eifler, R. Hlo ˇzek, T. Collett, E. Gawiser et al.,The LSST Dark Energy Science Collaboration (DESC) Science Requirements Document,arXiv e-prints(2018) arXiv:1809.01669 [1809.01669]

work page arXiv 2018
[32]

Euclid Definition Study Report

R. Laureijs, J. Amiaux, S. Arduini, J. L. Augu `eres, J. Brinchmann, R. Cole et al.,Euclid Definition Study Report,arXiv e-prints(2011) arXiv:1110.3193 [1110.3193]

work page internal anchor Pith review Pith/arXiv arXiv 2011
[33]

M. M. Rau, R. Dalal, T. Zhang, X. Li, A. J. Nishizawa, S. More et al.,Weak lensing tomographic redshift distribution inference for the Hyper Suprime-Cam Subaru Strategic Program three-year shape catalogue,Monthly Notices of the Royal Astronomical Society 524(2023) 5109 [2211.16516]

work page arXiv 2023
[34]

A. H. Wright, H. Hildebrandt, J. L. van den Busch, M. Bilicki, C. Heymans, B. Joachimi et al.,KiDS-Legacy: Redshift distributions and their calibration,Astronomy & Astrophysics 703(2025) A144 [2503.19440]

work page arXiv 2025
[35]

B. Yin, A. Amon, A. Campos, M. A. Troxel, W. d’Assignies, G. M. Bernstein et al.,Dark Energy Survey Year 6 Results: Redshift Calibration of the Weak Lensing Source Galaxies, arXiv e-prints(2025) arXiv:2510.23566 [2510.23566]

work page arXiv 2025
[36]

Redshift inference from the combination of galaxy colors and clustering in a hierarchical Bayesian model

C. S ´anchez and G. M. Bernstein,Redshift inference from the combination of galaxy colours and clustering in a hierarchical Bayesian model,Monthly Notices of the Royal Astronomical Society483(2019) 2801 [1807.11873]

work page Pith review arXiv 2019
[37]

A. E. Firth, O. Lahav and R. S. Somerville,Estimating photometric redshifts with artificial neural networks,Monthly Notices of the Royal Astronomical Society339(2003) 1195 [astro-ph/0203250]

work page arXiv 2003
[38]

A. A. Collister and O. Lahav,ANNz: Estimating Photometric Redshifts Using Artificial Neural Networks,The Publications of the Astronomical Society of the Pacific116(2004) 345 [astro-ph/0311058]

work page arXiv 2004
[39]

W. A. Baum,Photoelectric Magnitudes and Red-Shifts, inProblems of Extra-Galactic Research(G. C. McVittie, ed.), vol. 15 ofIAU Symposium, p. 390, Jan., 1962

1962
[40]

A. J. Connolly, I. Csabai, A. S. Szalay, D. C. Koo, R. G. Kron and J. A. Munn,Slicing Through Multicolor Space: Galaxy Redshifts from Broadband Photometry,The Astronomical Journal110(1995) 2655 [astro-ph/9508100]

work page arXiv 1995
[41]

R. J. Brunner, A. J. Connolly, A. S. Szalay and M. A. Bershady,Toward More Precise Photometric Redshifts: Calibration Via CCD Photometry,The Astrophysical Journal482 (1997) L21 [astro-ph/9703058]

work page arXiv 1997
[42]

Y . Wang, N. Bahcall and E. L. Turner,A Catalog of Color-based Redshift Estimates for Z <∼4 Galaxies in the Hubble Deep Field,The Astronomical Journal116(1998) 2081 [astro-ph/9804195]

work page arXiv 1998
[43]

Tagliaferri, G

R. Tagliaferri, G. Longo, S. Andreon, S. Capozziello, C. Donalek and G. Giordano,Neural Networks for Photometric Redshifts Evaluation, inLecture Notes in Computer Science, vol. 2859, pp. 226–234. 2003. DOI

2003
[44]

Collister, O

A. Collister, O. Lahav, C. Blake, R. Cannon, S. Croom, M. Drinkwater et al.,MegaZ-LRG: a photometric redshift catalogue of one million SDSS luminous red galaxies,Monthly Notices of the Royal Astronomical Society375(2007) 68 [astro-ph/0607630]

work page arXiv 2007
[45]

Gruen, S

D. Gruen, S. Seitz, J. Koppenhoefer and A. Riffeser,Bias-free Shear Estimation Using Artificial Neural Networks,The Astrophysical Journal720(2010) 639 [1002.0838]

work page arXiv 2010
[46]

A. J. Ross, S. Ho, A. J. Cuesta, R. Tojeiro, W. J. Percival, D. Wake et al.,Ameliorating systematic uncertainties in the angular clustering of galaxies: a study using the SDSS-III, Monthly Notices of the Royal Astronomical Society417(2011) 1350 [1105.2320]

work page arXiv 2011
[47]

M. T. Soumagnac, F. B. Abdalla, O. Lahav, D. Kirk, I. Sevilla, E. Bertin et al.,Star/galaxy separation at faint magnitudes: application to a simulated Dark Energy Survey,Monthly Notices of the Royal Astronomical Society450(2015) 666 [1306.5236]

work page arXiv 2015
[48]

I. A. Almosallam, M. J. Jarvis and S. J. Roberts,GPZ: non-stationary sparse Gaussian processes for heteroscedastic uncertainty estimation in photometric redshifts,Monthly Notices of the Royal Astronomical Society462(2016) 726 [1604.03593]. 24 Luca Tortorelli and Daniel Gr ¨un

work page arXiv 2016
[49]

K. J. Duncan,All-purpose, all-sky photometric redshifts for the Legacy Imaging Surveys Data Release 8,Monthly Notices of the Royal Astronomical Society512(2022) 3662 [2203.01949]

work page arXiv 2022
[50]

D’Isanto,Uncertain Photometric Redshifts with Deep Learning Methods, in Astroinformatics(M

A. D’Isanto,Uncertain Photometric Redshifts with Deep Learning Methods, in Astroinformatics(M. Brescia, S. G. Djorgovski, E. D. Feigelson, G. Longo and S. Cavuoti, eds.), vol. 325 ofIAU Symposium, pp. 209–212, June, 2017,1703.01979, DOI

work page arXiv 2017
[51]

M. M. Rau, S. Seitz, F. Brimioulle, E. Frank, O. Friedrich, D. Gruen et al.,Accurate photometric redshift probability density estimation - method comparison and application, Monthly Notices of the Royal Astronomical Society452(2015) 3710 [1503.08215]

work page arXiv 2015
[52]

Sadeh, F

I. Sadeh, F. B. Abdalla and O. Lahav,ANNz2: Photometric Redshift and Probability Distribution Function Estimation using Machine Learning,The Publications of the Astronomical Society of the Pacific128(2016) 104502 [1507.00490]

work page arXiv 2016
[53]

Amaro, S

V . Amaro, S. Cavuoti, M. Brescia, C. Vellucci, C. Tortora and G. Longo,METAPHOR: Probability density estimation for machine learning based photometric redshifts, in Astroinformatics(M. Brescia, S. G. Djorgovski, E. D. Feigelson, G. Longo and S. Cavuoti, eds.), vol. 325 ofIAU Symposium, pp. 197–200, June, 2017,1703.02292, DOI

work page arXiv 2017
[54]

Cavuoti, V

S. Cavuoti, V . Amaro, M. Brescia, C. Vellucci, C. Tortora and G. Longo,METAPHOR: a machine-learning-based method for the probability density estimation of photometric redshifts,Monthly Notices of the Royal Astronomical Society465(2017) 1959 [1611.02162]

work page arXiv 2017
[55]

J. F. Crenshaw, J. B. Kalmbach, A. Gagliano, Z. Yan, A. J. Connolly, A. I. Malz et al., Probabilistic Forward Modeling of Galaxy Catalogs with Normalizing Flows,The Astronomical Journal168(2024) 80 [2405.04740]

work page arXiv 2024
[56]

Y . Ren, K. C. Chan, L. Zhang, Y . Li, H. Zhang, R. Song et al.,Photo-z Estimation with Normalizing Flow,The Astrophysical Journal997(2026) 65 [2510.10032]

work page arXiv 2026
[57]

M. Lima, C. E. Cunha, H. Oyaizu, J. Frieman, H. Lin and E. S. Sheldon,Estimating the redshift distribution of photometric galaxy samples,Monthly Notices of the Royal Astronomical Society390(2008) 118 [0801.3822]

work page arXiv 2008
[58]

N. M. Ball, R. J. Brunner, A. D. Myers, N. E. Strand, S. L. Alberts and D. Tcheng,Robust Machine Learning Applied to Astronomical Data Sets. III. Probabilistic Photometric Redshifts for Galaxies and Quasars in the SDSS and GALEX,The Astrophysical Journal 683(2008) 12 [0804.3413]

work page arXiv 2008
[59]

C. E. Cunha, M. Lima, H. Oyaizu, J. Frieman and H. Lin,Estimating the redshift distribution of photometric galaxy samples - II. Applications and tests of a new method, Monthly Notices of the Royal Astronomical Society396(2009) 2379 [0810.2991]

work page arXiv 2009
[60]

Redshift distributions of galaxies in the DES Science Verification shear catalogue and implications for weak lensing

C. Bonnett, M. A. Troxel, W. Hartley, A. Amara, B. Leistedt, M. R. Becker et al.,Redshift distributions of galaxies in the Dark Energy Survey Science Verification shear catalogue and implications for weak lensing,Physical Review D94(2016) 042005 [1507.05909]

work page Pith review arXiv 2016
[61]

KiDS-450: Cosmological parameter constraints from tomographic weak gravitational lensing

H. Hildebrandt, M. Viola, C. Heymans, S. Joudaki, K. Kuijken, C. Blake et al.,KiDS-450: cosmological parameter constraints from tomographic weak gravitational lensing,Monthly Notices of the Royal Astronomical Society465(2017) 1454 [1606.05338]

work page Pith review arXiv 2017
[62]

Tanaka, J

M. Tanaka, J. Coupon, B.-C. Hsieh, S. Mineo, A. J. Nishizawa, J. Speagle et al., Photometric redshifts for Hyper Suprime-Cam Subaru Strategic Program Data Release 1, Publications of the Astronomical Society of Japan70(2018) S9 [1704.05988]

work page arXiv 2018
[63]

Hoyle, D

B. Hoyle, D. Gruen, G. M. Bernstein, M. M. Rau, J. De Vicente, W. G. Hartley et al.,Dark Energy Survey Year 1 Results: redshift distributions of the weak-lensing source galaxies, Monthly Notices of the Royal Astronomical Society478(2018) 592 [1708.01532]

work page arXiv 2018
[64]

DNF - Galaxy photometric redshift by Directional Neighbourhood Fitting

J. De Vicente, E. S ´anchez and I. Sevilla-Noarbe,DNF - Galaxy photometric redshift by Directional Neighbourhood Fitting,Monthly Notices of the Royal Astronomical Society459 (2016) 3078 [1511.07623]

work page Pith review arXiv 2016
[65]

Porredon, M

A. Porredon, M. Crocce, P. Fosalba, J. Elvin-Poole, A. Carnero Rosell, R. Cawthon et al., Dark Energy Survey Year 3 results: Optimizing the lens sample in a combined galaxy clustering and galaxy-galaxy lensing analysis,Physical Review D103(2021) 043503 [2011.03411]. 1 Photometric Redshifts 25

work page arXiv 2021
[66]

Weaverdyck, M

N. Weaverdyck, M. Rodr ´ıguez-Monroy, J. Elvin-Poole, I. Sevilla-Noarbe, A. Porredon, S. Avila et al.,Dark Energy Survey Year 6 Results: MagLim++ Lens Sample Selection and Measurements of Galaxy Clustering,arXiv e-prints(2026) arXiv:2601.14484 [2601.14484]

work page arXiv 2026
[67]

Carliles, T

S. Carliles, T. Budav ´ari, S. Heinis, C. Priebe and A. Szalay,Photometric Redshift Estimation on SDSS Data Using Random Forests, inAstronomical Data Analysis Software and Systems XVII(R. W. Argyle, P. S. Bunclark and J. R. Lewis, eds.), vol. 394 of Astronomical Society of the Pacific Conference Series, p. 521, Aug., 2008,0711.2477, DOI

work page arXiv 2008
[68]

D. W. Gerdes, A. J. Sypniewski, T. A. McKay, J. Hao, M. R. Weis, R. H. Wechsler et al., ArborZ: Photometric Redshifts Using Boosted Decision Trees,The Astrophysical Journal 715(2010) 823 [0908.4085]

work page arXiv 2010
[69]

Carrasco Kind and R

M. Carrasco Kind and R. J. Brunner,TPZ: photometric redshift PDFs and ancillary information by using prediction trees and random forests,Monthly Notices of the Royal Astronomical Society432(2013) 1483 [1303.7269]

work page arXiv 2013
[70]

Gruen, S

D. Gruen, S. Seitz, F. Brimioulle, R. Kosyra, J. Koppenhoefer, C.-H. Lee et al.,Weak lensing analysis of SZ-selected clusters of galaxies from the SPT and Planck surveys, Monthly Notices of the Royal Astronomical Society442(2014) 1507 [1310.6744]

work page arXiv 2014
[71]

Wadadekar,Estimating Photometric Redshifts Using Support Vector Machines,The Publications of the Astronomical Society of the Pacific117(2005) 79 [astro-ph/0412005]

Y . Wadadekar,Estimating Photometric Redshifts Using Support Vector Machines,The Publications of the Astronomical Society of the Pacific117(2005) 79 [astro-ph/0412005]

work page arXiv 2005
[72]

Jones and J

E. Jones and J. Singal,Analysis of a custom support vector machine for photometric redshift estimation and the inclusion of galaxy shape information,Astronomy & Astrophysics600 (2017) A113 [1607.00044]

work page arXiv 2017
[73]

Mapping the Galaxy Color-Redshift Relation: Optimal Photometric Redshift Calibration Strategies for Cosmology Surveys

D. Masters, P. Capak, D. Stern, O. Ilbert, M. Salvato, S. Schmidt et al.,Mapping the Galaxy Color-Redshift Relation: Optimal Photometric Redshift Calibration Strategies for Cosmology Surveys,The Astrophysical Journal813(2015) 53 [1509.03318]

work page Pith review arXiv 2015
[74]

D. C. Masters, D. K. Stern, J. G. Cohen, P. L. Capak, J. D. Rhodes, F. J. Castander et al., The Complete Calibration of the Color-Redshift Relation (C3R2) Survey: Survey Overview and Data Release 1,The Astrophysical Journal841(2017) 111 [1704.06665]

work page arXiv 2017
[75]

A. H. Wright, H. Hildebrandt, J. L. van den Busch, C. Heymans, B. Joachimi, A. Kannawadi et al.,KiDS+VIKING-450: Improved cosmological parameter constraints from redshift calibration with self-organising maps,Astronomy & Astrophysics640(2020) L14 [2005.04207]

work page arXiv 2020
[76]

Myles, A

J. Myles, A. Alarcon, A. Amon, C. S ´anchez, S. Everett, J. DeRose et al.,Dark Energy Survey Year 3 results: redshift calibration of the weak lensing source galaxies,Monthly Notices of the Royal Astronomical Society505(2021) 4249 [2012.08566]

work page arXiv 2021
[77]

Davidzon, K

I. Davidzon, K. Jegatheesan, O. Ilbert, S. de la Torre, S. K. Leslie, C. Laigle et al., COSMOS2020: Manifold learning to estimate physical parameters in large galaxy surveys, Astronomy & Astrophysics665(2022) A34 [2206.06373]

work page arXiv 2022
[78]

Teimoorinia, F

H. Teimoorinia, F. Archinuk, J. Woo, S. Shishehchi and A. F. L. Bluck,Mapping the Diversity of Galaxy Spectra with Deep Unsupervised Machine Learning,The Astronomical Journal163(2022) 71 [2112.03425]

work page arXiv 2022
[79]

B. W. Holwerda, D. Smith, L. Porter, C. Henry, R. Porter-Temple, K. Cook et al.,Galaxy and mass assembly (GAMA): Self-Organizing Map application on nearby galaxies,Monthly Notices of the Royal Astronomical Society513(2022) 1972 [2203.15611]

work page arXiv 2022
[80]

Abedini, G

F. Abedini, G. Gozaliasl, A. H. Zonoozi, A. Kalantari, M. Korpi-Lagg, O. Ilbert et al., COSMOS-Web: Estimating Physical Parameters of Galaxies Using Self-Organizing Maps, Monthly Notices of the Royal Astronomical Society(2026) [2506.04138]

work page arXiv 2026
[81]

Ashmead, J

F. Ashmead, J. A. Newman, B. H. Andrews, R. Bezanson, B. Dey, D. C. Masters et al., Optimizing Photometric Redshift Training Sets I: Efficient Compression of the Galaxy Color-Redshift Relation with UMAP,arXiv e-prints(2025) arXiv:2512.09032 [2512.09032]. 26 Luca Tortorelli and Daniel Gr ¨un

work page arXiv 2025

Showing first 80 references.