Improving Generalization and Uncertainty Quantification of Photometric Redshift Models

• URL: http://arxiv.org/abs/2601.17222v1
• Date: Fri, 23 Jan 2026 23:19:47 GMT
• Title: Improving Generalization and Uncertainty Quantification of Photometric Redshift Models
• Authors: Jonathan Soriano, Tuan Do, Srinath Saikrishnan, Vikram Seenivasan, Bernie Boscoe, Jack Singal, Evan Jones,
• Abstract summary: We train machine learning models for photometric redshift estimation on a broader range of galaxy types.<n>We find that a NN trained on a composite dataset predicts photo-$z$'s that are 4.5 times less biased within the redshift range.<n>We also find that BNNs produce reliable uncertainty estimates, but are sensitive to the different ground truths.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate redshift estimates are a vital component in understanding galaxy evolution and precision cosmology. In this paper, we explore approaches to increase the applicability of machine learning models for photometric redshift estimation on a broader range of galaxy types. Typical models are trained with ground-truth redshifts from spectroscopy. We test the utility and effectiveness of two approaches for combining spectroscopic redshifts and redshifts derived from multiband ($\sim$35 filters) photometry, which sample different types of galaxies compared to spectroscopic surveys. The two approaches are (1) training on a composite dataset and (2) transfer learning from one dataset to another. We compile photometric redshifts from the COSMOS2020 catalog (TransferZ) to complement an established spectroscopic redshift dataset (GalaxiesML). We used two architectures, deterministic neural networks (NN) and Bayesian neural networks (BNN), to examine and evaluate their performance with respect to the Legacy Survey of Space and Time (LSST) photo-$z$ science requirements. We also use split conformal prediction for calibrating uncertainty estimates and producing prediction intervals for the BNN and NN, respectively. We find that a NN trained on a composite dataset predicts photo-$z$'s that are 4.5 times less biased within the redshift range $0.3<z<1.5$, 1.1 times less scattered, and has a 1.4 times lower outlier rate than a model trained on only spectroscopic ground truths. We also find that BNNs produce reliable uncertainty estimates, but are sensitive to the different ground truths. This investigation leverages different sources of ground truths to develop models that can accurately predict photo-$z$'s for a broader population of galaxies crucial for surveys such as Euclid and LSST.

Related papers

• Mantis Shrimp: Exploring Photometric Band Utilization in Computer Vision Networks for Photometric Redshift Estimation [0.30924355683504173]
  We present a model for photometric redshift estimation that fuses ultra-violet (GALEX), optical (PanSTARRS), and infrared (UnWISE) imagery.<n>Mantis Shrimp estimates the conditional density estimate of redshift using cutout images.<n>We study how the models learn to use information across bands, finding evidence that our models successfully incorporates information from all surveys.
  arXiv  Detail & Related papers  (2025-01-15T19:46:23Z)
• Using different sources of ground truths and transfer learning to improve the generalization of photometric redshift estimation [0.0]
  We explore methods to improve galaxy redshift predictions by combining different ground truths.<n>We first train a base neural network on TransferZ and then refine it using transfer learning on a dataset of galaxies with more precise spectroscopic redshifts (GalaxiesML)<n>Both methods reduce bias by $sim$ 5x, RMS error by $sim$ 1.5x, and catastrophic outlier rates by 1.3x on GalaxiesML, compared to a baseline trained only on TransferZ data.
  arXiv  Detail & Related papers  (2024-11-27T04:55:37Z)
• GalaxiesML: a dataset of galaxy images, photometry, redshifts, and structural parameters for machine learning [1.0279580671257864]
  We present a dataset built for machine learning applications consisting of galaxy photometry, images, spectroscopic redshifts, and structural properties. This dataset comprises 286,401 galaxy images and photometry from the Hyper-Suprime-Cam Survey PDR2 in five imaging filters. We make this dataset public to help spur development of machine learning methods for the next generation of surveys such as Euclid and LSST.
  arXiv  Detail & Related papers  (2024-09-30T22:46:44Z)
• Deep Learning Based Speckle Filtering for Polarimetric SAR Images. Application to Sentinel-1 [51.404644401997736]
  We propose a complete framework to remove speckle in polarimetric SAR images using a convolutional neural network. Experiments show that the proposed approach offers exceptional results in both speckle reduction and resolution preservation.
  arXiv  Detail & Related papers  (2024-08-28T10:07:17Z)
• Spectral Image Data Fusion for Multisource Data Augmentation [44.99833362998488]
  Multispectral and hyperspectral images are increasingly popular in different research fields, such as remote sensing, astronomical imaging, or precision agriculture. The amount of free data available to perform machine learning tasks is relatively small. Artificial intelligence models developed in the area of spectral imaging require input images with a fixed spectral signature.
  arXiv  Detail & Related papers  (2024-04-05T13:40:18Z)
• Streamlined Lensed Quasar Identification in Multiband Images via Ensemble Networks [34.82692226532414]
  Quasars experiencing strong lensing offer unique viewpoints on subjects related to cosmic expansion rate, dark matter, and quasar host galaxies. We have developed a novel approach by ensembling cutting-edge convolutional networks (CNNs) trained on realistic galaxy-quasar lens simulations. We retrieve approximately 60 million sources as parent samples and reduce this to 892,609 after employing a photometry preselection to discover quasars with Einstein radii of $theta_mathrmE5$ arcsec.
  arXiv  Detail & Related papers  (2023-07-03T15:09:10Z)
• Photo-zSNthesis: Converting Type Ia Supernova Lightcurves to Redshift Estimates via Deep Learning [0.0]
  Photo-zSNthesis is a convolutional neural network-based method for predicting full redshift probability distributions. We show a 61x improvement in prediction bias Delta z> on PLAsTiCC simulations and 5x improvement on real SDSS data.
  arXiv  Detail & Related papers  (2023-05-19T17:59:00Z)
• Cosmology from Galaxy Redshift Surveys with PointNet [65.89809800010927]
  In cosmology, galaxy redshift surveys resemble such a permutation invariant collection of positions in space. We employ a textitPointNet-like neural network to regress the values of the cosmological parameters directly from point cloud data. Our implementation of PointNets can analyse inputs of $mathcalO(104) - mathcalO(105)$ galaxies at a time, which improves upon earlier work for this application by roughly two orders of magnitude.
  arXiv  Detail & Related papers  (2022-11-22T15:35:05Z)
• Understanding of the properties of neural network approaches for transient light curve approximations [37.91290708320157]
  This paper presents a search for the best-performing methods to approximate the observed light curves over time and wavelength. Test datasets include simulated PLAsTiCC and real Zwicky Transient Facility Bright Transient Survey light curves of transients.
  arXiv  Detail & Related papers  (2022-09-15T18:00:08Z)
• Inferring Structural Parameters of Low-Surface-Brightness-Galaxies with Uncertainty Quantification using Bayesian Neural Networks [70.80563014913676]
  We show that a Bayesian Neural Network (BNN) can be used for the inference, with uncertainty, of such parameters from simulated low-surface-brightness galaxy images. Compared to traditional profile-fitting methods, we show that the uncertainties obtained using BNNs are comparable in magnitude, well-calibrated, and the point estimates of the parameters are closer to the true values.
  arXiv  Detail & Related papers  (2022-07-07T17:55:26Z)
• Learning Enriched Illuminants for Cross and Single Sensor Color Constancy [182.4997117953705]
  We propose cross-sensor self-supervised training to train the network. We train the network by randomly sampling the artificial illuminants in a sensor-independent manner. Experiments show that our cross-sensor model and single-sensor model outperform other state-of-the-art methods by a large margin.
  arXiv  Detail & Related papers  (2022-03-21T15:45:35Z)
• Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods [0.0]
  We investigate two major forms of biases, i.e., class-dependent residuals and mode collapse, in a case study of estimating photometric redshifts. We propose a set of consecutive steps for resolving the two biases based on CNN models. Experiments show that our methods possess a better capability in controlling biases compared to benchmark methods.
  arXiv  Detail & Related papers  (2022-02-21T02:59:33Z)
• DeepShadows: Separating Low Surface Brightness Galaxies from Artifacts using Deep Learning [70.80563014913676]
  We investigate the use of convolutional neural networks (CNNs) for the problem of separating low-surface-brightness galaxies from artifacts in survey images. We show that CNNs offer a very promising path in the quest to study the low-surface-brightness universe.
  arXiv  Detail & Related papers  (2020-11-24T22:51:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.