The concern about air pollution in urban areas has substantially increased worldwide. One of its main components, particulate matter (PM) with aerodynamic diameter of ≤2.5 µm (PM2.5), can be inhaled and deposited in deeper regions of the respiratory system, causing adverse effects on human health, which are even more harmful to children. In this sense, the use of deterministic and stochastic models has become a key tool for predicting atmospheric behavior and, thus, providing information for decision makers to adopt preventive actions to mitigate air pollution impacts. However, stochastic models present their own strengths and weaknesses. To overcome some of disadvantages of deterministic models, there has been an increasing interest in the use of deep learning, due to its simpler implementation and its success on multiple tasks, including time series and air quality forecasting. Thus, the objective of the present study is to develop and evaluate the use of four different topologies of deep artificial neural networks (DNNs), analyzing the impact of feature augmentation in the prediction of PM2.5 concentrations by using five levels of discrete wavelet transform (DWT). The following types of deep neural networks were trained and tested on data collected from two living lab stations next to high-traffic roads in Guildford, UK: multi-layer perceptron (MLP), long short-term memory (LSTM), one-dimensional convolutional neural network (1D-CNN) and a hybrid neural network composed of LSTM and 1D-CNN. The performance of each model in making predictions up to twenty-four hours ahead was quantitatively assessed through statistical metrics. The results show that wavelets improved the forecasting results and that discrete wavelet transform is a relevant tool to enhance the performance of DNN topologies, with special emphasis on the hybrid topology that achieved the best results among the applied models.
Wind power forecasting is pivotal in promoting a stable and sustainable grid operation by estimating future power outputs from past meteorological and turbine data. The inherent unpredictability in wind patterns poses substantial challenges in synchronizing supply with demand, with inaccuracies potentially destabilizing the grid and potentially causing energy shortages or excesses. This study develops a data-driven approach to forecast wind power from 30 min to 12 h ahead using historical wind power data collected by the Supervisory Control and Data Acquisition (SCADA) system from one wind turbine, the Enercon/E92 2350 kW model, installed at Casa Nova, Bahia, Brazil. Those data were measured from January 2020 to April 2021. Time orientation was embedded using sine/cosine or cyclic encoding, deriving 16 normalized features that encapsulate crucial daily and seasonal trends. The research explores two distinct strategies: error prediction and error correction, both employing a sequential model where initial forecasts via k-Nearest Neighbors (KNN) are rectified by the Extra Trees Regressor. Their primary divergence is the second model’s target variable. Evaluations revealed both strategies outperforming the standalone KNN, with error correction excelling in short-term predictions and error prediction showing potential for extended forecasts. This exploration underscores the imperative importance of methodology selection in wind power forecasting.
25 August 2025 in International Journal of Climatology
O presente trabalho teve por objetivo avaliar as previsões de irradiância global horizontal (GHI) de até 48h àfrente do modelo WRF-Solar no Centro de Referência em Energia Solar da Eletrobras Chesf, localizada no município dePetrolina (PE), o CRESP, para o período de julho de 2020 e outubro de 2020, meses de menor e maior incidência deradiação solar na região, respectivamente. O estudo abordado enfoca o desenvolvimento e implementação demetodologias para a previsão de radiação solar empregando os modelos WRF em suas versões controle (WRF-CTL) esolar (WRF-Solar), com foco na região de Petrolina-PE. Ambas as versões do WRF foram comparadas através demétricas como BIAS, RMSE e coeficiente de correlação R. O WRF-Solar mostrou-se superior na precisão das previsões,em particular, conseguindo representar com maior acurácia condições de céu nublado e céu claro, apesar de apresentarum coeficiente R ligeiramente inferior ao WRF-CTL. A parametrização de nuvens híbridas e o tratamento de nuvensrasas do WRF-Solar podem ter sido determinantes para seu melhor desempenho. Entretanto, ambos os modelosenfrentaram desafios na representação do ciclo diurno de GHI, com dificuldades marcantes nas horas da manhã,atribuídas à complexidade na determinação numérica de nuvens. Os resultados, alinhados com a literatura existente,fornecem uma validação sólida da aplicabilidade do WRF-Solar para previsões de curto prazo em condições climáticasespecíficas. No entanto, é crucial notar que essa validação se aplica ao contexto específico da região estudada,ressaltando a necessidade de mais pesquisas e validações em diversas condições climáticas e geográficas para aprimorara eficácia e abrangência do modelo. Além disso, a pesquisa indica que a correção de viés e a calibração adicional dosmodelos são áreas promissoras para futuras investigações. Essas medidas podem contribuir significativamente paramitigar erros sistemáticos e aprimorar a acurácia das previsões em estudos subsequentes.Palavras-chave: GHI, Modelo WRF, Previsão solar.