PEDROAMARALMEDEIROS
4 resultados
Resultados de Busca
Agora exibindo 1 - 4 de 4
Resumo IPEN-doc 29276 Desenvolvimento de um modelo em python de predição em rede neural para dados de LIDAR e CRDS2022 - MEDEIROS, PEDRO A.; LANDULFO, EDUARDOResumo IPEN-doc 28968 Limits of a prediction model using RNN with four layers LSTM for CRDS data2021 - MEDEIROS, PEDRO A.; MARQUES, MARCIA; LANDULFO, EDUARDOPrediction models can be very useful when dealing with ciclic temporal sequence of data. For ciclic sequences that have caotic behavior, like atmospherics measures, the Recurrent Neural Network(RNN) is a potential option to create acurate prediction models.This type of neural network is effective in dealing with temporal sequences because it uses its internal state as a memory to process certain data intervals. In building the model, it is necessary to use layers with neurons to discern a trend that the data sequence takes, for this, in the RNN model it is possible to use the long short-term memory (LSTM) architecture to more easily predict unusual behaviors in the data stream, since its use facilitates the recognition of long-term sequences in the analyzed sequence. This type of architecture can be added in layers to increase model efficiency. For the training and testing of the model, data obtained by the Metroclima project with a Cavity Ring Down Spectroscopy (CRDS) at the UNICID station located in São Paulo were used, with the data ranging from 2019 to 2021. In this process, four LSTM layers will be used to create a prediction model that will be tested to its limit on the effectiveness of predicting atmospheric data of this type.Resumo IPEN-doc 28966 Measurement of greenhouses gases in the city of Sao Paulo2021 - SILVA, THAIS A. da; OLIVEIRA, CARLOS E.S. de; CRUZ, DANILO D.; MEDEIROS, ILCA M.M.A.; MEDEIROS, JOSE A.G. de; OLIVEIRA, LUCAS P.; MARQUES, MARCIA T.A.; MEDEIROS, PEDRO A.; ANDRADE, MARIA F.; LANDULFO, EDUARDOThe gases that most contribute to the greenhouse effect are carbon dioxide (CO2), methane (CH4) and nitrous oxide (N2O). When those gases have been in the atmosphere for a long time, its effects become almost irreversible with the radiative forcing of years, until natural processes manage to remove the quantities already emitted. Methane is a radiative agent and happens significantly in the southern hemisphere. Methane is a major source of water vapor. When the concentration of water vapor in the stratosphere increases, it contributes to intensifying the greenhouse effect. The large part of carbon dioxide and methane absorbed by the ocean, atmosphere and biosphere, contributes to the global carbon cycle, bringing a stable carbon rate in the air. Forest fires are often responsible for releasing carbon dioxide and methane. It is important to consider the role of photosynthesis in the balance between anthropogenic process, climate change and air quality. Therefore, forest preservation and reforestation projects are fundamental against climate change. The main purpose of Metroclima Project is to assess the sources of greenhouse gases and short-lived pollutants in Sao Paulo and neighboring cities, in the Southeast of Brazil. Currently, the GHG measurement network has four stations (IAG Station, Pico do Jaragua, UNICID and ICESP) extended across the City of Sao Paulo, measuring carbon dioxide and methane concentrations continuously using Cavity Ring Down Spectroscopy (CRDS) instruments. In specific, the goal of this study is related to assessment of methane concentration variability and identification of potential sources near UNICID Station – an urban site; using the CRDS Picarro G2401 system. The data analysis acquired during 2020 and 2021 will be shown. Our results comprise a valuable contribution to the knowledge about methane concentrations in the city and guide public decision based on scientific evidence.Resumo IPEN-doc 28389 Metodologia de tratamento de dados LIDAR com python e estruturação da obtenção de dados2021 - MEDEIROS, PEDRO A.; LANDULFO, EDUARDO