This work presents the SEEG platform, a 46-year long dataset of greenhouse gas emissions (GHG) in Brazil (1970–2015) providing more than 2 million data records for the Agriculture, Energy, Industry, Waste and Land Use Change Sectors at national and subnational levels. The SEEG dataset was developed by the Climate Observatory, a Brazilian civil society initiative, based on the IPCC guidelines and Brazilian National Inventories embedded with country specific emission factors and processes, raw data from multiple official and non-official sources, and organized together with social and economic indicators. Once completed, the SEEG dataset was converted into a spreadsheet format and shared via web-platform that, by means of simple queries, allows users to search data by emission sources and country and state activities. Because of its effectiveness in producing and making available data on a consistent and accessible basis, SEEG may significantly increase the capacity of civil society, scientists and stakeholders to understand and anticipate trends related to GHG emissions as well as its implications to public policies in Brazil.
Forecasting photovoltaic electricity generation is one of the key components to reducing the impacts of solar power natural variability, nurturing the penetration of renewable energy sources. Machine learning is a well-known method that relies on the principle that systems can learn from previously measured data, detecting patterns which are then used to predict future values of a target variable. These algorithms have been used successfully to predict incident solar irradiation, but the results depend on the specificities of the studied location due to the natural variability of the meteorological parameters. This paper presents an extensive comparison of the three ML algorithms most used worldwide for forecasting solar radiation, Support Vector Machine (SVM), Artificial Neural Network (ANN), and Extreme Learning Machine (ELM), aiming at the best prediction of daily solar irradiance in a São Paulo context. The largest dataset in Brazil for meteorological parameters, containing measurements from 1933 to 2014, was used to train and compare the results of the algorithms. The results showed good approximation between measured and predicted global solar radiation for the three algorithms; however, for São Paulo, the SVM produced a lower Root-Mean-Square Error (RMSE), and ELM, a faster training rate. Using all 10 meteorological parameters available for the site was the best approach for the three algorithms at this location.
Autorizo a reprodução e divulgação total ou parcial deste trabalho, por qualquer meio convencional ou eletrônico, para fins de estudo e pesquisa, desde que citada a fonte.
dezembro 22Palavras-chave: Aprendizado de máquina, redes neurais, máquinas de aprendizado extremo, máquinas de vetores de suporte, previsão de energia solar fotovoltaica vii
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.