Civita Vellucci

METAPHOR: a machine-learning-based method for the probability density estimation of photometric redshifts

A variety of fundamental astrophysical science topics require the determination of very accurate photometric redshifts (photo-z). A wide plethora of methods have been developed, based either on template models fitting or on empirical explorations of the photometric parameter space. Machine-learning-based techniques are not explicitly dependent on the physical priors and able to produce accurate photo-z estimations within the photometric ranges derived from the spectroscopic training set. These estimates, however, are not easy to characterize in terms of a photo-z probability density function (PDF), due to the fact that the analytical relation mapping the photometric parameters on to the redshift space is virtually unknown. We present METAPHOR (Machine-learning Estimation Tool for Accurate PHOtometric Redshifts), a method designed to provide a reliable PDF of the error distribution for empirical techniques. The method is implemented as a modular workflow, whose internal engine for photo-z estimation makes use of the MLPQNA neural network (Multi Layer Perceptron with Quasi Newton learning rule), with the possibility to easily replace the specific machine-learning model chosen to predict photo-z. We present a summary of results on SDSS-DR9 galaxy data, used also to perform a direct comparison with PDFs obtained by the Le Phare spectral energy distribution template fitting. We show that METAPHOR is capable to estimate the precision and reliability of photometric redshifts obtained with three different self-adaptive techniques, i.e. MLPQNA, Random Forest and the standard K-Nearest Neighbors models.

A cooperative approach among methods for photometric redshifts estimation: an application to KiDS data

Photometric redshifts (photo-z) are fundamental in galaxy surveys to address different topics, from gravitational lensing and dark matter distribution to galaxy evolution. The Kilo Degree Survey (KiDS), i.e. the European Southern Observatory (ESO) public survey on the VLT Survey Telescope (VST), provides the unprecedented opportunity to exploit a large galaxy data set with an exceptional image quality and depth in the optical wavebands. Using a KiDS subset of about 25000 galaxies with measured spectroscopic redshifts, we have derived photo-z using (i) three different empirical methods based on supervised machine learning; (ii) the Bayesian photometric redshift model (or BPZ); and (iii) a classical spectral energy distribution (SED) template fitting procedure (le phare). We confirm that, in the regions of the photometric parameter space properly sampled by the spectroscopic templates, machine learning methods provide better redshift estimates, with a lower scatter and a smaller fraction of outliers. SED fitting techniques, however, provide useful information on the galaxy spectral type, which can be effectively used to constrain systematic errors and to better characterize potential catastrophic outliers. Such classification is then used to specialize the training of regression machine learning models, by demonstrating that a hybrid approach, involving SED fitting and machine learning in a single collaborative framework, can be effectively used to improve the accuracy of photo-z estimates.

Photometric redshifts for the Kilo-Degree Survey: Machine-learning analysis with artificial neural networks

We present a machine-learning photometric redshift analysis of the Kilo-Degree Survey Data Release 3, using two neural-network based techniques: ANNz2 and MLPQNA. Despite limited coverage of spectroscopic training sets, these ML codes provide photo-zs of quality comparable to, if not better than, those from the BPZ code, at least up to zphot<0.9 and r<23.5. At the bright end of r<20, where very complete spectroscopic data overlapping with KiDS are available, the performance of the ML photo-zs clearly surpasses that of BPZ, currently the primary photo-z method for KiDS. Using the Galaxy And Mass Assembly (GAMA) spectroscopic survey as calibration, we furthermore study how photo-zs improve for bright sources when photometric parameters additional to magnitudes are included in the photo-z derivation, as well as when VIKING and WISE infrared bands are added. While the fiducial four-band ugri setup gives a photo-z bias

Cooperative photometric redshift estimation

\delta z=-2e-4

Data Deluge in Astrophysics: Photometric Redshifts as a Template Use Case.

and scatter

Probability density estimation of photometric redshifts based on machine learning

\sigma_z<0.022

METAPHOR: Probability density estimation for machine learning based photometric redshifts

at mean z = 0.23, combining magnitudes, colours, and galaxy sizes reduces the scatter by ~7% and the bias by an order of magnitude. Once the ugri and IR magnitudes are joined into 12-band photometry spanning up to 12

The third data release of the Kilo-Degree Survey and associated data products

\mu

Statistical analysis of probability density functions for photometric redshifts through the KiDS-ESO-DR3 galaxies.

, the scatter decreases by more than 10% over the fiducial case. Finally, using the 12 bands together with optical colours and linear sizes gives

Evolution of galaxy size–stellar mass relation from the Kilo-Degree Survey

\delta z<4e-5