Previsão de níveis de precipitação usando redes neurais artificiais

Detalhes bibliográficos
Ano de defesa: 2018
Autor(a) principal: Briones Estébanez, Katiusca Magdalena
Orientador(a): Não Informado pela instituição
Banca de defesa: Não Informado pela instituição
Tipo de documento: Tese
Tipo de acesso: Acesso aberto
Idioma: por
Instituição de defesa: Universidade Federal do Rio de Janeiro
Brasil
Instituto Alberto Luiz Coimbra de Pós-Graduação e Pesquisa de Engenharia
Programa de Pós-Graduação em Engenharia Civil
UFRJ
Programa de Pós-Graduação: Não Informado pela instituição
Departamento: Não Informado pela instituição
País: Não Informado pela instituição
Palavras-chave em Português:
Link de acesso: http://hdl.handle.net/11422/13419
Resumo: The planning of various human activities, such as agriculture, construction, transportation, tourism, leisure, among others, are delimited to a greater or lesser extent by the climatic conditions, especially rainfall amounts and temperature values. Climate forecast, i.e. forecast for months ahead, are negatively impacted by the dynamics of the atmosphere-earth-ocean system, causing various levels of uncertainties. Currently, many traditional and modern methods support the forecast of climate conditions; however, the necessary accuracy is not reached. Thus, in this thesis were analyzed how the artificial neural networks could contribute in the rainfall forecast. Artificial neural networks are a method of the artificial intelligence area that has had an accelerated development in recent decades, where a considerable number of applications with satisfactory results have positioned these networks as the state of the art in several areas of knowledge. Precipitation levels from three cities of Ecuador were forecasted using as predictors atmospheric and oceanic variables. The results obtained show that the artificial neural networks were able to predict the rain a month ahead with accuracy for Guayaquil of 89%, Portoviejo of 100% and Esmeraldas of 74%, results considered satisfactory and encouraging for the use of artificial intelligence techniques in the operational climatic forecast.