اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدTransfer learning for galaxy morphology from one survey to another
74
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Deep Learning (DL) algorithms for morphological classification of galaxies have proven very successful, mimicking (or even improving) visual classifications. However, these algorithms rely on large training samples of labelled galaxies (typically thousands of them). A key question for using DL classifications in future Big Data surveys is how much of the knowledge acquired from an existing survey can be exported to a new dataset, i.e. if the features learned by the machines are meaningful for different data. We test the performance of DL models, trained with Sloan Digital Sky Survey (SDSS) data, on Dark Energy survey (DES) using images for a sample of $sim$5000 galaxies with a similar redshift distribution to SDSS. Applying the models directly to DES data provides a reasonable global accuracy ($sim$ 90%), but small completeness and purity values. A fast domain adaptation step, consisting in a further training with a small DES sample of galaxies ($sim$500-300), is enough for obtaining an accuracy > 95% and a significant improvement in the completeness and purity values. This demonstrates that, once trained with a particular dataset, machines can quickly adapt to new instrument characteristics (e.g., PSF, seeing, depth), reducing by almost one order of magnitude the necessary training sample for morphological classification. Redshift evolution effects or significant depth differences are not taken into account in this study.
قيم البحث
اقرأ أيضاً
We present the first nonparametric morphological analysis of a set of spiral galaxies from UV to submm wavelengths. Our study is based on high-quality multi-wavelength imaging for nine well-resolved spiral galaxies from the DustPedia database, combin
ed with nonparametric morphology indicators calculated in a consistent way using the {tt{StatMorph}} package. We measure the half-light radius, the concentration index, the asymmetry index, the smoothness index, the Gini coefficient and the $M_{20}$ indicator in various wavebands from UV to submm wavelengths, as well as in stellar mass, dust mass and star formation rate maps. We find that the interstellar dust in galaxies is distributed in a more extended, less centrally concentrated, more asymmetric, and more clumpy way than the stars. This is particularly evident when comparing morphological indicators based on the stellar mass and dust mass maps. This should serve as a warning sign against treating the dust in galaxies as a simple smooth component. We argue that the nonparametric galaxy morphology of galaxies from UV to submm wavelengths is an interesting test for cosmological hydrodynamics simulations.
We present Galaxy Zoo DECaLS: detailed visual morphological classifications for Dark Energy Camera Legacy Survey images of galaxies within the SDSS DR8 footprint. Deeper DECaLS images (r=23.6 vs. r=22.2 from SDSS) reveal spiral arms, weak bars, and t
idal features not previously visible in SDSS imaging. To best exploit the greater depth of DECaLS images, volunteers select from a new set of answers designed to improve our sensitivity to mergers and bars. Galaxy Zoo volunteers provide 7.5 million individual classifications over 314,000 galaxies. 140,000 galaxies receive at least 30 classifications, sufficient to accurately measure detailed morphology like bars, and the remainder receive approximately 5. All classifications are used to train an ensemble of Bayesian convolutional neural networks (a state-of-the-art deep learning method) to predict posteriors for the detailed morphology of all 314,000 galaxies. When measured against confident volunteer classifications, the networks are approximately 99% accurate on every question. Morphology is a fundamental feature of every galaxy; our human and machine classifications are an accurate and detailed resource for understanding how galaxies evolve.
We report the quadruple nature of the source WISE 025942.9-163543 as observed in the VST-ATLAS survey. Spectra of the two brightest images show quasar emission lines at z=2.16. The system was discovered by splitting ATLAS cutouts of WISE sources with
W1-W2 > 0.7, when possible, into three components. Followup Magellan images were used to obtain astrometry and g and i photometry, with i=18.78 and 19.73, respectively, for the brightest and faintest components. Absorption lines are observed at z=0.905 but there is little evidence for a lensing galaxy after PSF fitting and subtraction. Saha and Williams (2003) would classify ATLAS 0259-1635 as a short-axis quad. The larger and smaller diameters are 1.57 and 1.32 arcseconds, respectively. Modeling the lensing galaxy as a singular isothermal sphere with external shear, the largest and smallest predicted magnifications are 10.8 and 6.4 respectively.
In this paper we introduce the textsc{Deepz} deep learning photometric redshift (photo-$z$) code. As a test case, we apply the code to the PAU survey (PAUS) data in the COSMOS field. textsc{Deepz} reduces the $sigma_{68}$ scatter statistic by 50% at
$i_{rm AB}=22.5$ compared to existing algorithms. This improvement is achieved through various methods, including transfer learning from simulations where the training set consists of simulations as well as observations, which reduces the need for training data. The redshift probability distribution is estimated with a mixture density network (MDN), which produces accurate redshift distributions. Our code includes an autoencoder to reduce noise and extract features from the galaxy SEDs. It also benefits from combining multiple networks, which lowers the photo-$z$ scatter by 10 percent. Furthermore, training with randomly constructed coadded fluxes adds information about individual exposures, reducing the impact of photometric outliers. In addition to opening up the route for higher redshift precision with narrow bands, these machine learning techniques can also be valuable for broad-band surveys.
Establishing accurate morphological measurements of galaxies in a reasonable amount of time for future big-data surveys such as EUCLID, the Large Synoptic Survey Telescope or the Wide Field Infrared Survey Telescope is a challenge. Because of its hig
h level of abstraction with little human intervention, deep learning appears to be a promising approach. Deep learning is a rapidly growing discipline that models high-level patterns in data as complex multilayered networks. In this work we test the ability of deep convolutional networks to provide parametric properties of Hubble Space Telescope like galaxies (half-light radii, Sersic indices, total flux etc..). We simulate a set of galaxies including point spread function and realistic noise from the CANDELS survey and try to recover the main galaxy parameters using deep-learning. We com- pare the results with the ones obtained with the commonly used profile fitting based software GALFIT. This way showing that with our method we obtain results at least equally good as the ones obtained with GALFIT but, once trained, with a factor 5 hundred time faster.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
