Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMachine Learning Applied to STAR-GALAXY-QSO Classification of The Javalambre-Photometric Local Universe Survey
133
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
In modern astronomy, machine learning as an raising realm for data analysis, has proved to be efficient and effective to mine the big data from the newest telescopes. By using support vector machine (SVM), we construct a supervised machine learning algorithm, to classify the objects in the Javalambre-Photometric Local Universe Survey (J-Plus). The sample is featured with 12-waveband, and magnitudes is labeled with spectrum-based catalogs, including Sloan Digital Sky Survey spectroscopic data, Large Sky Area Multi-Object Fiber Spectroscopic Telescope, and VERONCAT - Veron Catalog of Quasars & AGN. The performance of the classifier is presented with the applications of blind test validations based on RAdial Velocity Extension, Kepler Input Catalog, 2 MASS Redshift Survey, and UV-bright Quasar Survey. The accuracies of the classifier are 96.5% in blind test and 97.0% in training cross validation. The F_1-scores are 95.0% for STAR, 92.9% for GALAXY and 87.0% for QSO. In the classification for J-Plus catalog, we develop a new method to constrain the potential extrapolation.
rate research
Read More
J-PLUS is an ongoing 12-band photometric optical survey, observing thousands of square degrees of the Northern hemisphere from the dedicated JAST/T80 telescope at the Observatorio Astrofisico de Javalambre. T80Cam is a 2 sq.deg field-of-view camera mounted on this 83cm-diameter telescope, and is equipped with a unique system of filters spanning the entire optical range. This filter system is a combination of broad, medium and narrow-band filters, optimally designed to extract the rest-frame spectral features (the 3700-4000AA Balmer break region, H$delta$, Ca H+K, the G-band, the Mgb and Ca triplets) that are key to both characterize stellar types and to deliver a low-resolution photo-spectrum for each pixel of the sky observed. With a typical depth of AB $sim 21.25$ mag per band, this filter set thus allows for an indiscriminate and accurate characterization of the stellar population in our Galaxy, it provides an unprecedented 2D photo-spectral information for all resolved galaxies in the local universe, as well as accurate photo-z estimates ($Delta,zsim 0.01-0.03$) for moderately bright (up to $rsim 20$ mag) extragalactic sources. While some narrow band filters are designed for the study of particular emission features ([OII]/$lambda$3727, H$alpha$/$lambda$6563) up to $z < 0.015$, they also provide well-defined windows for the analysis of other emission lines at higher redshifts. As a result, J-PLUS has the potential to contribute to a wide range of fields in Astrophysics, both in the nearby universe (Milky Way, 2D IFU-like studies, stellar populations of nearby and moderate redshift galaxies, clusters of galaxies) and at high redshifts (ELGs at $zapprox 0.77, 2.2$ and $4.4$, QSOs, etc). With this paper, we release $sim 36$ sq.deg of J-PLUS data, containing about $1.5times 10^5$ stars and $10^5$ galaxies at $r<21$ mag.
Future astrophysical surveys such as J-PAS will produce very large datasets, which will require the deployment of accurate and efficient Machine Learning (ML) methods. In this work, we analyze the miniJPAS survey, which observed about 1 deg2 of the AEGIS field with 56 narrow-band filters and 4 ugri broad-band filters. We discuss the classification of miniJPAS sources into extended (galaxies) and point-like (e.g. stars) objects, a necessary step for the subsequent scientific analyses. We aim at developing an ML classifier that is complementary to traditional tools based on explicit modeling. In order to train and test our classifiers, we crossmatched the miniJPAS dataset with SDSS and HSC-SSP data. We trained and tested 6 different ML algorithms on the two crossmatched catalogs. As input for the ML algorithms we use the magnitudes from the 60 filters together with their errors, with and without the morphological parameters. We also use the mean PSF in the r detection band for each pointing. We find that the RF and ERT algorithms perform best in all scenarios. When analyzing the full magnitude range of 15<r<23.5 we find AUC=0.957 with RF when using only photometric information, and AUC=0.986 with ERT when using photometric and morphological information. Regarding feature importance, when using morphological parameters, FWHM is the most important feature. When using photometric information only, we observe that broad bands are not necessarily more important than narrow bands, and errors are as important as the measurements. ML algorithms can compete with traditional star/galaxy classifiers, outperforming the latter at fainter magnitudes (r>21). We use our best classifiers, with and without morphology, in order to produce a value added catalog available at https://j-pas.org/datareleases .
Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques fitting parametric models to curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k-nearest neighbors, support vector machines, artificial neural networks and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieves an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.
The advancement of technology has resulted in a rapid increase in supernova (SN) discoveries. The Subaru/Hyper Suprime-Cam (HSC) transient survey, conducted from fall 2016 through spring 2017, yielded 1824 SN candidates. This gave rise to the need for fast type classification for spectroscopic follow-up and prompted us to develop a machine learning algorithm using a deep neural network (DNN) with highway layers. This machine is trained by actual observed cadence and filter combinations such that we can directly input the observed data array into the machine without any interpretation. We tested our model with a dataset from the LSST classification challenge (Deep Drilling Field). Our classifier scores an area under the curve (AUC) of 0.996 for binary classification (SN Ia or non-SN Ia) and 95.3% accuracy for three-class classification (SN Ia, SN Ibc, or SN II). Application of our binary classification to HSC transient data yields an AUC score of 0.925. With two weeks of HSC data since the first detection, this classifier achieves 78.1% accuracy for binary classification, and the accuracy increases to 84.2% with the full dataset. This paper discusses the potential use of machine learning for SN type classification purposes.
From the approximately $sim$3,500 planetary nebulae (PNe) discovered in our Galaxy, only 14 are known to be members of the Galactic halo. Nevertheless, a systematic search for halo PNe has never been performed. In this study, we present new photometric diagnostic tools to identify compact PNe in the Galactic halo by making use of the novel 12-filter system projects, J-PLUS (Javalambre Photometric Local Universe Survey) and S-PLUS (Southern-Photometric Local Universe Survey). We reconstructed the IPHAS (Isaac Newton Telescope (INT) Photometric H${alpha}$ Survey of the Northern Galactic Plane) diagnostic diagram and propose four new ones using i) the J-PLUS and S-PLUS synthetic photometry for a grid of photo-ionisation models of halo PNe, ii) several observed halo PNe, as well as iii) a number of other emission-line objects that resemble PNe. All colour-colour diagnostic diagrams are validated using two known halo PNe observed by J-PLUS during the scientific verification phase and the first data release (DR1) of S-PLUS and the DR1 of J-PLUS. By applying our criteria to the DR1s ($sim$1,190 deg$^2$), we identified one PN candidate. However, optical follow-up spectroscopy proved it to be a H II region belonging to the UGC 5272 galaxy. Here, we also discuss the PN and two H II galaxies recovered by these selection criteria. Finally, the cross-matching with the most updated PNe catalogue (HASH) helped us to highlight the potential of these surveys, since we recover all the known PNe in the observed area. The tools here proposed to identify PNe and separate them from their emission-line contaminants proved to be very efficient thanks to the combination of many colours, even when applied -like in the present work- to an automatic photometric search that is limited to compact PNe.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
