Browsing by Author "Parraguez, Santiago"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Forecasting PM2.5 levels in Santiago de Chile using deep learning neural networks(2021) Menares, Camilo; Pérez, Patricio; Parraguez, Santiago; Fleming, ZöeAir pollution has been shown to have a direct effect on human health. In particular, PM2.5 has been proven to be related to cardiovascular and respiratory problems. Therefore, it is important to have accurate models to predict high pollution events for this and other pollutants. We present different models that forecast PM2.5 maximum concentrations using a Long Short-Term Memory (LSTM) based neural network and a Deep Feedforward Neural Network (DFFNN). Ten years of air pollution and meteorological measurements from the network of monitoring stations in the city of Santiago, Chile were used, focusing on the behaviour of three zones of the city. All missing values were rebuilt using a method based on discrete cosine transforms and photochemical predictors selected through unsupervised clustering. Deep learning techniques provide significant improvements compared to a traditional multi-layer neural networks, particularly the LSTM model configured with a 7-day memory window (synoptic scale of pollution patterns) can capture critical pollution events at sites with both primary and secondary air pollution problems. Furthermore, the LSTM model consistently outperform deterministic models currently used in Santiago, Chile.Publication Photochemical sensitivity to emissions and local meteorology in Bogotá, Santiago, and São Paulo: An analysis of the initial COVID-19 lockdowns(2022) Seguel, Rodrigo J.; Gallardo, Laura; Osses, Mauricio; Rojas, Néstor Y.; Nogueira, Thiago; Menares, Cmilo; Andrade, María Fátima; Belalcázar, Luis C.; Carrasco, Paula; Eskes, Henk; Fleming, Zöe; Huneeus, Nicolás; Ibarra-Espinosa, Sergio; Landulfo, Eduardo; Leiva, Manuel; Mangones, Sonia C.; ernando G. Morais8 , Gregori A. Moreira11, Nicola´ s Pantoja3 , Santiago Parraguez1,12, Jhojan P. Rojas13, Roberto Rondanelli1,2, Izabel da Silva Andrade8 , Richard Toro9 ,; Moreira, Gregori A.; Pantoja, Nicolás; Parraguez, Santiago; Rojas, Jhojan P.; Rondanelli, Roberto; Silva Andrade, Izabel da; Toro, Richard; Yoshida, Alexandre C.This study delves into the photochemical atmospheric changes reported globally during the pandemic by analyzing the change in emissions from mobile sources and the contribution of local meteorology to ozone (O3) and particle formation in Bogotá (Colombia), Santiago (Chile), and São Paulo (Brazil). The impact of mobility reductions (50%–80%) produced by the early coronavirus-imposed lockdown was assessed through high-resolution vehicular emission inventories, surface measurements, aerosol optical depth and size, and satellite observations of tropospheric nitrogen dioxide (NO2) columns. A generalized additive model (GAM) technique was also used to separate the local meteorology and urban patterns from other drivers relevant for O3 and NO2 formation. Volatile organic compounds, nitrogen oxides (NOx), and fine particulate matter (PM2.5) decreased significantly due to motorized trip reductions. In situ nitrogen oxide median surface mixing ratios declined by 70%, 67%, and 67% in Bogotá, Santiago, and São Paulo, respectively. NO2 column medians from satellite observations decreased by 40%, 35%, and 47%, respectively, which was consistent with the changes in mobility and surface mixing ratio reductions of 34%, 25%, and 34%. However, the ambient NO2 to NOx ratio increased, denoting a shift of the O3 formation regime that led to a 51%, 36%, and 30% increase in the median O3 surface mixing ratios in the 3 respective cities. O3 showed high sensitivity to slight temperature changes during the pandemic lockdown period analyzed. However, the GAM results indicate that O3 increases were mainly caused by emission changes. The lockdown led to an increase in the median of the maximum daily 8-h average O3 of between 56% and 90% in these cities.