Improving galaxy morphology with machine learning

Barchi, Paulo Henrique; Costa, F. da; Sautter, Rubens; Rosa, Renata Lopes; Carvalho, R. R. de

doi:10.6062/jcis.2016.07.03.0114

Cited by 8 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The huge amount of photometric astrophysical data available and the highly increasing advancements on hardware and methods to perform automatic classifications has been leveraging related publications (Law et al, 2007;Freeman et al, 2013;Khalifa et al, 2017;Huertas-Company et al, 2018;Barchi et al, 2016;Dieleman et al, 2015;Khan et al, 2018;Huertas-Company et al, 2015;Domínguez Sánchez et al, 2018). Highlight to Domínguez Sánchez et al (2018) who use questions and answers from Galaxy Zoo 2 for replicating the answers from the users, and provide morphology classification by T-Type in their final catalog.…”

Section: Introductionmentioning

confidence: 99%

Machine and Deep Learning applied to galaxy morphology - A comparative study

Barchi

Carvalho

Rosa

et al. 2020

Astronomy and Computing

View full text Add to dashboard Cite

Morphological classification is a key piece of information to define samples of galaxies aiming to study the large-scale structure of the universe. In essence, the challenge is to build up a robust methodology to perform a reliable morphological estimate from galaxy images. Here, we investigate how to substantially improve the galaxy classification within large datasets by mimicking human classification. We combine accurate visual classifications from the Galaxy Zoo project with machine and deep learning methodologies. We propose two distinct approaches for galaxy morphology: one based on non-parametric morphology and traditional machine learning algorithms; and another based on Deep Learning. To measure the input features for the traditional machine learning methodology, we have developed a system called CyMorph, with a novel non-parametric approach to study galaxy morphology. The main datasets employed comes from the Sloan Digital Sky Survey Data Release 7 (SDSS-DR7). We also discuss the class imbalance problem considering three classes. Performance of each model is mainly measured by Overall Accuracy (OA). A spectroscopic validation with astrophysical parameters is also provided for Decision Tree models to assess the quality of our morphological classification. In all of our samples, both Deep and Traditional Machine Learning approaches have over 94.5% OA to classify galaxies in two classes (elliptical and spiral). We compare our classification with state-of-the-art morphological classification from literature. Considering only two classes separation, we achieve 99% of overall accuracy in average when using our deep learning models, and 82% when using three classes. We provide a catalog with 670,560 galaxies containing our best results, including morphological metrics and classification.ETGs have T-Type ≤ 0 and LTGs have T-Type > 0 (de Vaucouleurs, 1963). T-Type considers ellipticity and spiral arms strength but does not reflect the presence or absence of the bar feature in spirals.Morphology reveals structural, intrinsic and environmental properties of galaxies. In the local universe, ETGs are mostly situated in the center of galaxy clusters, have a larger mass, less gas, higher velocity dispersion, and older stellar populations than LTGs, which are rich star-forming systems (Roberts and Haynes, 1994;Blanton and Moustakas, 2009;Pozzetti et al., 2010). By mapping where the ETGs are, it is possible to map the large-scale structure of the universe. Therefore, galaxy morphology is of paramount importance for extragalactic research as it relates to stellar properties and key aspects of the evolution and structure of the universe.Astronomy has become an extremely data-rich field of knowledge with the advance of new technologies in recent decades. Nowadays it is impossible to rely on human classification given the huge flow of data attained by current research

show abstract

Section: Introductionmentioning

confidence: 99%

Machine and Deep Learning applied to galaxy morphology - A comparative study

Barchi

Carvalho

Rosa

et al. 2020

Astronomy and Computing

View full text Add to dashboard Cite

show abstract

“…I. Perren et al [14] pre-sented the Automated Star Cluster Analysis package (ASteCA), a set of tools designed to fully automate the conventional tests used to establish the basic properties of stellar clusters. P. H. Barchi et al [7] have used both supervised and unsupervised machine learning algorithms to improve the classifications of galaxies into spiral and elliptical with morphological parameters.Selim et al [17] introduced a novel technique in which 2D and 3D Kmeans, as well as normal distribution features, were employed to predict the most likely galaxies of Virgo clusters and the Virgo center.Sen et al [18] have described a number of machine learning and big data tools that can be used to handle and process massive amounts of astronomical data in their review paper.Snigdha et al [19] proposed a neural network model for interpreting redshift data of celestial objects, and two different ways to train the model were proposed: one utilizing Lipschitz-based adaptive learning rate in a single node/machine, and the other using a multinode clustered environment.…”

Section: Related Workmentioning

confidence: 99%

Experimental investigation to identify galaxy clusters using sparse matrix clustering algorithm

Rai

Sen

Chakraborty

2022

Preprint

View full text Add to dashboard Cite

Recent advances in astronomy have shifted observational astronomy toward data-driven astronomy, with an exponential increase in data associated with celestial objects. If we can handle this massive amount of quickly changing data, we will be able to detect galaxy clusters, revealing a wealth of vital information about the evolution of the universe. In this paper, we have proposed a novel clustering technique that can handle massive amounts of rapidly changing data in real time. In this clustering technique, we have used 3D sparse matrix where each cell of the 3D matrix can be used to locate/identify a neighbor against the central galactic coordinate. In our investigation, we also used HDF5 to store and organize the discovered galaxy clusters so that we didn’t have to re-run our algorithm every time a new coordinate was encountered. Following preparation, the astronomical data containing the galactic coordinates RA, DEC, and radial distance obtained from redshift is input into our developed algorithm to identify, store, and depict the galaxy clusters.

show abstract

“…Most recently, deep learning has been used to process galaxy images, particularly for the classification of galaxy morphologies (Dieleman et al 2015, Barchi et al 2017, Domínguez Sánchez et al 2018, Khalifa et al 2018. Techniques seek the recovery of galaxy features in noisy images with generative adversarial networks (Schawinski et al 2017), the search for strong lensing effects with deep learning networks (Lanusse et al 2018), and for deblending galaxies (Figure 6, Reiman & Göhre 2019).…”

Section: Photometry Of Blended Galaxiesmentioning

confidence: 99%

21st Century Statistical and Computational Challenges in Astrophysics

Feigelson,

de Souza,

Ishida

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

Improving galaxy morphology with machine learning

Cited by 8 publications

References 20 publications

Machine and Deep Learning applied to galaxy morphology - A comparative study

Machine and Deep Learning applied to galaxy morphology - A comparative study

Experimental investigation to identify galaxy clusters using sparse matrix clustering algorithm

21st Century Statistical and Computational Challenges in Astrophysics

Contact Info

Product

Resources

About