Aprendizagem de máquina aplicada a métodos de classificação de supernovas

• Ano de defesa: 2018
• Autor(a) principal: Silva, Rodrigo Duarte
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Espírito Santo; BR; Mestrado em Física; Centro de Ciências Exatas; UFES; Programa de Pós-Graduação em Física
• Palavras-chave em Português: Machine learning; Universe; Aprendizagem de máquina; Supernova; Universo; Física; 53
• Link de acesso: http://repositorio.ufes.br/handle/10/10543

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.