Data Mining and Machine Learning in Astronomy

We review the current state of data mining and machine learning in astronomy. Data Mining can have a somewhat mixed connotation from the point of view of a researcher in this field. If used correctly, it can be a powerful approach, holding the potential to fully exploit the exponentially increasing amount of available data, promising great scientific advance. However, if misused, it can be little more than the black-box application of complex computing algorithms that may give little physical insight, and provide questionable results. Here, we give an overview of the entire data mining process, from data collection through to the interpretation of results. We cover common machine learning algorithms, such as artificial neural networks and support vector machines, applications from a broad range of astronomy, emphasizing those where data mining techniques directly resulted in improved science, and important current and future directions, including probability density functions, parallel algorithms, petascale computing, and the time domain. We conclude that, so long as one carefully selects an appropriate algorithm, and is guided by the astronomical problem at hand, data mining can be very much the powerful tool, and not the questionable black box.

A Cross-Correlation Analysis of Mg II Absorption Line Systems and Luminous Red Galaxies from the SDSS DR5

We analyze the cross-correlation of 2,705 unambiguously intervening Mg II (2796,2803A) quasar absorption line systems with 1,495,604 luminous red galaxies (LRGs) from the Fifth Data Release of the Sloan Digital Sky Survey within the redshift range 0.36<=z<=0.8. We confirm with high precision a previously reported weak anti-correlation of equivalent width and dark matter halo mass, measuring the average masses to be log M_h(M_[solar]h^-1)=11.29 [+0.36,-0.62] and log M_h(M_[solar]h^-1)=12.70 [+0.53,-1.16] for systems with W[2796A]>=1.4A and 0.8A<=W[2796A]<1.4A, respectively. Additionally, we investigate the significance of a number of potential sources of bias inherent in absorber-LRG cross-correlation measurements, including absorber velocity distributions and the weak lensing of background quasars, which we determine is capable of producing a 20-30% bias in angular cross-correlation measurements on scales less than 2. We measure the Mg II - LRG cross-correlation for 719 absorption systems with v<60,000 km s^-1 in the quasar rest frame and find that these associated absorbers typically reside in dark matter haloes that are ~10-100 times more massive than those hosting unambiguously intervening Mg II absorbers. Furthermore, we find evidence for evolution of the redshift number density, dN/dz, with 2-sigma significance for the strongest (W>2.0A) absorbers in the DR5 sample. This width-dependent dN/dz evolution does not significantly affect the recovered equivalent width-halo mass anti-correlation and adds to existing evidence that the strongest Mg II absorption systems are correlated with an evolving population of field galaxies at z<0.8, while the non-evolving dN/dz of the weakest absorbers more closely resembles that of the LRG population.

Robust Machine Learning Applied to Terascale Astronomical Datasets

We present recent results from the LCDM (Laboratory for Cosmological Data Mining; http://lcdm.astro.uiuc.edu) collaboration between UIUC Astronomy and NCSA to deploy supercomputing cluster resources and machine learning algorithms for the mining of terascale astronomical datasets. This is a novel application in the field of astronomy, because we are using such resources for data mining, and not just performing simulations. Via a modified implementation of the NCSA cyberenvironment Data-to-Knowledge, we are able to provide improved classifications for over 100 million stars and galaxies in the Sloan Digital Sky Survey, improved distance measures, and a full exploitation of the simple but powerful k-nearest neighbor algorithm. A driving principle of this work is that our methods should be extensible from current terascale datasets to upcoming petascale datasets and beyond. We discuss issues encountered to-date, and further issues for the transition to petascale. In particular, disk I/O will become a major limiting factor unless the necessary infrastructure is implemented.

Robust Machine Learning Applied to Astronomical Datasets III: Probabilistic Photometric Redshifts for Galaxies and Quasars in the SDSS and GALEX

We apply machine learning in the form of a nearest neighbor instance-based algorithm (NN) to generate full photometric redshift probability density functions (PDFs) for objects in the Fifth Data Release of the Sloan Digital Sky Survey (SDSS DR5). We use a conceptually simple but novel application of NN to generate the PDFs - perturbing the object colors by their measurement error - and using the resulting instances of nearest neighbor distributions to generate numerous individual redshifts. When the redshifts are compared to existing SDSS spectroscopic data, we find that the mean value of each PDF has a dispersion between the photometric and spectroscopic redshift consistent with other machine learning techniques, being sigma = 0.0207 +/- 0.0001 for main sample galaxies to r < 17.77 mag, sigma = 0.0243 +/- 0.0002 for luminous red galaxies to r < ~19.2 mag, and sigma = 0.343 +/- 0.005 for quasars to i < 20.3 mag. The PDFs allow the selection of subsets with improved statistics. For quasars, the improvement is dramatic: for those with a single peak in their probability distribution, the dispersion is reduced from 0.343 to sigma = 0.117 +/- 0.010, and the photometric redshift is within 0.3 of the spectroscopic redshift for 99.3 +/- 0.1% of the objects. Thus, for this optical quasar sample, we can virtually eliminate catastrophic photometric redshift estimates. In addition to the SDSS sample, we incorporate ultraviolet photometry from the Third Data Release of the Galaxy Evolution Explorer All-Sky Imaging Survey (GALEX AIS GR3) to create PDFs for objects seen in both surveys. For quasars, the increased coverage of the observed frame UV of the SED results in significant improvement over the full SDSS sample, with sigma = 0.234 +/- 0.010. We demonstrate that this improvement is genuine. [Abridged]

Robust Machine Learning Applied to Terascale Astronomical Datasets

We present recent results from the Laboratory for Cosmological Data Mining (http://lcdm.astro.uiuc.edu) at the National Center for Supercomputing Applications (NCSA) to provide robust classifications and photometric redshifts for objects in the terascale-class Sloan Digital Sky Survey (SDSS). Through a combination of machine learning in the form of decision trees, k-nearest neighbor, and genetic algorithms, the use of supercomputing resources at NCSA, and the cyberenvironment Data-to-Knowledge, we are able to provide improved classifications for over 100 million objects in the SDSS, improved photometric redshifts, and a full exploitation of the powerful k-nearest neighbor algorithm. This work is the first to apply the full power of these algorithms to contemporary terascale astronomical datasets, and the improvement over existing results is demonstrable. We discuss issues that we have encountered in dealing with data on the terascale, and possible solutions that can be implemented to deal with upcoming petascale datasets.