Sky Mining - Application to Photomorphic Redshift Estimation.

摘要

The field of astronomy has evolved from the ancient craft of observing the sky. In it's present form, astronomers explore the cosmos not just by observing through the tiny visible window used by our eyes, but also by exploiting the electromagnetic spectrum from radio waves to gamma rays. The domain is undoubtedly at the forefront of data-driven science. The data growth rate is expected to be around 50%--100% per year. This data explosion is attributed largely to the large-scale wide and deep surveys of the different regions of the sky at multiple wavelengths (both ground and space-based surveys).;This dissertation describes the application of machine learning methods to the estimation of galaxy redshifts leveraging such a survey data. Galaxy is a large system of stars held together by mutual gravitation and isolated from similar systems by vast regions of space. Our view of the universe is closely tied to our understanding of galaxy formation. Thus, a better understanding of the relative location of the multitudes of galaxies is crucial. The position of each galaxy can be characterized using three coordinates. Right Ascension (ra) and Declination (dec) are the two coordinates that locate the galaxy in two dimensions on the plane of the sky. It is relatively straightforward to measure them. In contrast, fixing the third coordinate that is the galaxy's distance from the observer along the line of sight (redshift 'z') is considerably more challenging.;"Spectroscopic redshift" method gives us accurate and precise measurements of z. However, it is extremely time-intensive and unusable for faint objects. Additionally, the rate at which objects are being identified via photometric surveys far exceeds the rate at which the spectroscopic redshift measurements can keep pace in determining their distance. As the surveys go deeper into the sky, the proportion of faint objects being identified also continues to increase. In order to tackle both these drawbacks increasing in severity every day, alternative method "Photometric redshift" has been studied in the past. It uses the brightness of the object viewed through various standard filters, each of which lets through a relatively broad spectrum of colors. However, these methods are bound by the degeneracy problem (objects with different color profiles have the same redshift) which leads to low predictive accuracy.;As part of our study, we are looking beyond color attributes to identify other measured attributes as degeneracy resolvers as well as generate estimators that are highly accurate; termed as "Photomorphic redshift" estimators. The present study investigates the photometric information of the objects such as color and magnitude (= observed flux) and morphology attributes such as shape, size, orientation and concentration in the different wavelengths. The specific type of magnitude used in this study are the PSF, Fiber and Petrosian magnitude. The morphology attributes are the ratio of Fiber to Petrosian magnitude, concentration index and Petrosian radius. All these attributes are in the five bands ugriz of the Sloan Digital Sky Survey (SDSS).;Machine learning techniques based on Naive Bayes (NB), Bayesian Network (BN) and Generalized Linear Model (GLM) are researched to better understand their applicability, advantages and resulting predictive performance in terms of efficiency and accuracy. Note: The SDSS Data Release (DR) 10 data was used in the executed experiments (total of 700,777 galaxies with forty-five attributes associated with each galaxy).;The significant findings of the present work are as follows: 1. Magnitude and morphology attributes have been found to be successful degeneracy resolvers. 2. Magnitude and morphology attributes have been found to be better redshift estimators than color attributes alone. 3. Naive Bayes, Bayesian Network and GLM have been found to be viable redshift estimation methods. Attribute selection is an important factor in computational performance. 4. In addition to the redshift estimate, the likelihood distribution of the estimate is even more useful, and my Bayesian Network models provide that information. This is particularly useful in ensemble methods as well as the kernel for mass distribution in the universe. 5. The generated Bayesian Network models can be applied to any of the variables, not just limited to redshift. Example applications include quality analysis and missing value imputation. Different types of Bayesian Network learning algorithms---constraint-based, score-based and hybrid---were investigated in detail.