Aprendizagem de máquina aplicada a métodos de classificação de supernovas
Nenhuma Miniatura disponível
Data
2018-09-06
Autores
Silva, Rodrigo Duarte
Título da Revista
ISSN da Revista
Título de Volume
Editor
Universidade Federal do Espírito Santo
Resumo
Future observational research with investments, telescopes and technologies never before seen, are being proposed in an attempt to unravel the mysteries of the Universe. In our work, we provide an overview of this scenario, with special attention to the classification of supernovae that will be done by LSST (Large Synoptic Survey Telescope) from 2022. Initially, we introduce the physics that involve the Supernova event and its observation, with the objective of treating the problem of photometric classification of supernovae. We provide important references in the use of different machine learning and neural networks for this purpose. We include results from the use of some of the computational methods and the theory behind them, highlighting their potentialities and vunerabilities. Machine learning methods may involve supervision or not. We aim to describe the application of these powerful tools in the analysis of observational data and verify unexpected results.
Descrição
Palavras-chave
Machine learning , Universe , Aprendizagem de máquina , Supernova , Universo
Citação
SILVA, Rodrigo Duarte. Aprendizagem de máquina aplicada a métodos de classificação de supernovas. 2018. Dissertação (Mestrado em Física) – Programa de Pós-Graduação em Física, Universidade Federal do Espírito Santo, Vitória, 2018.