Diego Ordóñez

HSC: A multi-resolution clustering strategy in Self-Organizing Maps applied to astronomical observations

This work presents a strategy for the classification of astronomical objects based on spectrophotometric data and the use of unsupervised neural networks and statistical classification algorithms. Our strategy constitutes an essential part of the preparation phase of the automatic classification and parameterization algorithms for the data that are to be collected by the Gaia satellite of the European Space Agency (ESA), whose launch is foreseen for the spring of 2012. The proposed algorithm is based on a hierarchical structure of neural networks composed of various tree-structured SOM networks. The classification of possible astronomical objects (stars, galaxies, quasars, multiple objects, etc.) basically consists in the iterative segmentation of the inputs space and the ensuing generation of initial classifications and increase in classification precision by means of a refining process. Apart from providing a classification, our technique also measures the quality and precision of the classifications and segments the objects for which it cannot determine whether or not they belong to a pre-established class of astronomical objects (outliers).

Parameterization of RVS synthetic stellar spectra for the ESA Gaia mission: Study of the optimal domain for ANN training

One of the upcoming cornerstone missions of the European Space Agency (ESA) is Gaia, a spacecraft that will be launched in 2011 and will carry out a stereoscopic census of our Galaxy and its environment by measuring with unprecedented exactitude the astrometry (distance and movements), the photometric distribution from ultraviolet to the infrared of its components, and, in the case of the brightest objects (mainly stars), the spectrum with intermediate resolution in the region of the infrared CaII triplet, with a spectrograph known as Radial Velocity Spectrometer (RVS). Stars are the basic constituents of our Galaxy, and they can be characterized if we can estimate their principal atmospheric parameters: effective temperature, gravity, metal content (general abundance of elements other than H and He), and their abundance of alpha elements (elements with Z>22, [@a/Fe]), which provide information on the physical environment in which the star was born. This work presents our results for the parameterization of stellar spectra with simulated data (synthetic spectra) in the spectral region of the RVS and with the application of Artificial Intelligence Techniques based on ANNs. Our work has two main purposes: to determine the optimal domain for the ANNs performance, and to develop an adequate noise detection and filtering algorithm.

Distributed Genetic Algorithm for Feature Selection in Gaia RVS Spectra: Application to ANN Parameterization

This work presents an algorithm that was developed to select the most relevant areas of a stellar spectrum to extract its basic atmospheric parameters. We consider synthetic spectra obtained from models of stellar atmospheres in the spectral region of the radial velocity spectrograph instrument of the European Space Agency’s Gaia space mission. The algorithm that demarcates the areas of the spectra sensitive to each atmospheric parameter (effective temperature and gravity, metallicity, and abundance of alpha elements) is a genetic algorithm, and the parameterization takes place through the learning of artificial neural networks. Due to the high computational cost of processing, we present a distributed implementation in both multiprocessor and multicomputer environments.

Genetic Algorithms Applied to Spectral Index Extraction

Within the scope of computational astropysics, this work presents an experimental study on the application of genetic algorithms to the automated extraction of relevant information from stellar spectra. The input data are a dataset obtained through the collaboration of our research group with the Gaia project of the European Space Agency. The results show that predictions based on spectral indices, which in turn were extracted by means of genetic algorithms, have accuracy levels that are very similar to those obtained through wavelength information. Working with a reduced dataset also implies the reduction of complexity and increased performance.

A comparative study of stellar spectra analysis with neural networks in transformed domains

The main purpose of the GAIA mission of the European Space Agency (ESA) is to carry out a stereoscopic census of our galaxy and its environment. This task is based on measurements that will provide with unprecedented exactitude information on the astrometry (distance, movements, and spectral energy distribution) of approximately 1% of the objects in the milky way (109 objects). In the case of the brightest objects, essentially stars, spectra with intermediate resolution in the region of the infrared CaII triplet will be measured with a dedicated spectrograph, RVS (Radial Velocity Spectrometer). Stars can be characterized on the basis of their principal atmospheric parameters: effective temperature, gravity, metal content (general abundance of elements other than H and He), and their abundance of alpha elements (elements with Z>22, α), which provide information on the physical environment in which the star was born. The goal of the present work is to study spectral parameterization by means of ANN: it determines the optimal domain for the ANNs performance, and proposes an adequate noise detection and filtering algorithm by considering simulated data (synthetic spectra) in the spectral region of the RVS.

A User-Friendly Framework for Multilanguage ANN Generation: Real Case Applications

This article presents a framework, developed in JAVA, that facilitates the design and implementation of artificial neural networks and provides automatic multilanguage code generation (ANSI C and JAVA). The framework consists of three systems: a library, in which we factorize network-related functionalities, and two tools, an interpreter and a Web application, that provide ANN-related features. The functioning of this tool was tested by applying it to two problems in two different fields.