Improving machine learning-derived photometric redshifts and physical property estimates using unlabelled observations
arXiv:2212.02537 · doi:10.1093/mnras/stac3596
Abstract
In the era of huge astronomical surveys, machine learning offers promising solutions for the efficient estimation of galaxy properties. The traditional, `supervised' paradigm for the application of machine learning involves training a model on labelled data, and using this model to predict the labels of previously unlabelled data. The semi-supervised `pseudo-labelling' technique offers an alternative paradigm, allowing the model training algorithm to learn from both labelled data and as-yet unlabelled data. We test the pseudo-labelling method on the problems of estimating redshift, stellar mass, and star formation rate, using COSMOS2015 broad band photometry and one of several publicly available machine learning algorithms, and we obtain significant improvements compared to purely supervised learning. We find that the gradient-boosting tree methods CatBoost, XGBoost, and LightGBM benefit the most, with reductions of up to ~15% in metrics of absolute error. We also find similar improvements in the photometric redshift catastrophic outlier fraction. We argue that the pseudo-labellng technique will be useful for the estimation of redshift and physical properties of galaxies in upcoming large imaging surveys such as Euclid and LSST, which will provide photometric data for billions of sources.
arXiv comment10 pages, 6 figures, accepted for publication in MNRAS
References in corpus (33)
- Array Programming with NumPy
- LSST: from Science Drivers to Reference Design and Anticipated Data Products
- Accurate photometric redshifts for the CFHT Legacy Survey calibrated using the VIMOS VLT Deep Survey
- A simple model to interpret the ultraviolet, optical and infrared emission from galaxies
- The COSMOS2015 Catalog: Exploring the 1<z<6 Universe with half a million galaxies
- Measuring and Modelling the Redshift Evolution of Clustering: the Hubble Deep Field North
- Analysis of galaxy SEDs from far-UV to far-IR with CIGALE: Studying a SINGS test sample
- Inferring the star-formation histories of massive quiescent galaxies with BAGPIPES: Evidence for multiple quenching mechanisms
- Rotation-invariant convolutional neural networks for galaxy morphology prediction
- Stellar Population Inference with Prospector
- ANNz: estimating photometric redshifts using artificial neural networks
- Improving galaxy morphologies for SDSS with Deep Learning
- A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning
- Star-Forming Galaxies at Cosmic Noon
- Photometric redshifts from SDSS images using a Convolutional Neural Network
- Euclid preparation: X. The Euclid photometric-redshift challenge
- Deep learning for galaxy surface brightness profile fitting
- Photometric redshifts for Quasars in multi band Surveys
- Fitting Analysis using Differential Evolution Optimization (FADO): Spectral population synthesis through genetic optimization under self-consistency boundary conditions
- Identifying galaxies, quasars, and stars with machine learning: A new catalogue of classifications for 111 million SDSS sources without spectra
- Star formation rates and stellar masses from machine learning
- Photometric classification of emission line galaxies with Machine Learning methods
- Machine learning Applied to Star-Galaxy-QSO Classification and Stellar Effective Temperature Regression
- CPz: Classification-aided photometric-redshift estimation
- A machine learning approach to galaxy properties: joint redshift-stellar mass probability distributions with Random Forest
- A cooperative approach among methods for photometric redshifts estimation: an application to KiDS data
- Attention-gating for improved radio galaxy classification
- Star Formation Rates for photometric samples of galaxies using machine learning methods
- Improving the reliability of photometric redshift with machine learning
- Stacking for machine learning redshifts applied to SDSS galaxies
- The Probabilistic Random Forest applied to the selection of quasar candidates in the QUBRICS Survey
- Comparison of Observed Galaxy Properties with Semianalytic Model Predictions using Machine Learning
- Quasar photometric redshifts from incomplete data using Deep Learning
Cited by in corpus (5)
- Euclid preparation: XXII. Selection of Quiescent Galaxies from Mock Photometry using Machine Learning
- Identifying type II quasars at intermediate redshift with few-shot learning photometric classification
- Euclid preparation. Estimating galaxy physical properties using CatBoost chained regressors with attention
- ULISSE: Determination of star-formation rate and stellar mass based on the one-shot galaxy imaging technique
- A gradient boosting and broadband approach to finding Lyman-α emitting galaxies beyond narrowband surveys