Photometric redshifts from SDSS images using a convolutional neural network

Abstract

We developed a Deep Convolutional Neural Network (CNN), used as a classifier, to estimate photometric redshifts and associated probability distribution functions (PDF) for galaxies in the Main Galaxy Sample of the Sloan Digital Sky Survey at z < 0.4. Our method exploits all the information present in the images without any feature extraction. The input data consist of 64×64 pixel ugriz images centered on the spectroscopic targets, plus the galactic reddening value on the line-of-sight. For training sets of 100k objects or more (≥ 20% of the database), we reach a dispersion σ MAD < 0.01, significantly lower than the current best one obtained from another machine learning technique on the same sample. The bias is lower than 10 −4 , independent of photometric redshift. The PDFs are shown to have very good predictive power. We also find that the CNN redshifts are unbiased with respect to galaxy inclination, and that σ MAD decreases with the signal-to-noise ratio (SNR), achieving values below 0.007 for SNR > 100, as in the deep stacked region of Stripe 82. We argue that for most galaxies the precision is limited by the SNR of SDSS images rather than by the method. The success of this experiment at low redshift opens promising perspectives for upcoming surveys.

The impact of the connectivity of the cosmic web on the physical properties of galaxies at its nodes

“…Future large-field photometric surveys, such as Euclid (Laureijs et al 2011), HSC (Aihara et al 2018) and LSST (LSST Dark Energy Science Collaboration 2012) will be able to confirm and extend these results by probing a wider group mass range and a larger variety of environment (though in 2D) while relying on state-of-the art photometric redshift extraction techniques (e.g. Davidzon et al 2019;Pasquet et al 2019).…”

Machine-Learning Methods for Computational Science and Engineering

“…While ML methods such as ANN have been used for almost 30 years [226], more recent works focus on CNNs, due to their ability to process and analyze images in a relatively computationally efficient way. CNNs have been used to understand the morphology of galaxies [227][228][229], predict photometric redshifts [230,231], detect galaxy clusters [232], identify gravitational lenses [233][234][235][236] and reconstruction of images [237] Video classification is yet another field that keeps improving along with advances in ML. Karpathy et al [238] have used CNNs to classify sports-related videos found on YouTube into their corresponding sports.…”

Galaxy formation and evolution science in the era of the Large Synoptic Survey Telescope

“…The most likely sources for the human classifications for training are citizen science efforts such as Galaxy Zoo or efforts involving the classification of more restricted datasets by professional astronomers 69 . The promise and efficiency of deep learning and other machine learning techniques lend themselves to other applications, such as photometric redshift determinations [178][179][180] or more even basic steps in the photometric pipeline such as object identification, deblending and segmentation. 62,63 .…”