Deep-CEE I: fishing for galaxy clusters with deep neural nets

Abstract

We introduce Deep-CEE (Deep Learning for Galaxy Cluster Extraction and Evaluation), a proof of concept for a novel deep learning technique, applied directly to wide-field colour imaging to search for galaxy clusters, without the need for photometric catalogues. This technique is complementary to traditional methods and could also be used in combination with them to confirm galaxy cluster candidates. We use a state-of-the-art probabilistic algorithm, adapted to localise and classify galaxy clusters from other astronomical objects in SDSS imaging. As there is an abundance of labelled data for galaxy clusters from previous classifications in publicly available catalogues, we do not need to rely on simulated data. This means we keep our training data as realistic as possible, which is advantageous when training a deep learning algorithm. Ultimately, we will apply our model to surveys such as LSST and Euclid to probe wider and deeper into unexplored regions of the Universe. This will produce large samples of both high redshift and low mass clusters, which can be utilised to constrain both environment-driven galaxy evolution and cosmology.

A data-driven computational scheme for the nonlinear mechanical properties of cellular mechanical metamaterials under large deformation

“…Neural networks have been demonstrated to be powerful function approximators for solving challenging engineering tasks, such as language modeling, 56 image classification, 57 and machine translation. 58 More recently, there has been a growing interest in applying neural networks to complex problems in natural sciences, e.g., physics, [59][60][61] chemistry, 62 astronomy, 63 biomedicine, 64 and materials science. [65][66][67][68][69] In the present work, we extend previous works on NN-based computational homogenization methods 53,54 to model the nonlinear mechanical behavior of cellular mechanical metamaterials under large deformation.…”

Z-Sequence: photometric redshift predictions for galaxy clusters with sequential random k-nearest neighbours

“…This is beneficial for photometric redshift estimation since Z-Sequence can be adapted to any imaging survey and trained on galaxy photometry data from known cluster positions in existing cluster catalogues. To prepare for upcoming surveys, we intend to run Z-Sequence as a complementary tool to our own DEEP-CEE (Chan & Stott 2019) cluster finder to examine the entirety of the SDSS sky coverage in a preliminary data pipeline, where clusters detected directly from the astronomical images would be accompanied with estimated photometric redshifts.…”

“…Secondly, it does not depend on galaxy photometric redshift catalogues. Thirdly, this approach can be combined with cluster finders that do not naturally predict redshift, such as DEEP-CEE (Chan & Stott 2019), since Z-Sequence only requires input astronomical coordinates and a photometry catalogue to predict photometric redshift of clusters.…”

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.…”