Bibliographic citations
Espinoza, J., (2021). Evaluación de patrones espaciales y pronóstico de la calidad del aire en Lima Metropolitana mediante técnicas estadísticas multivariadas [Universidad Nacional Agraria La Molina]. https://hdl.handle.net/20.500.12996/4874
Espinoza, J., Evaluación de patrones espaciales y pronóstico de la calidad del aire en Lima Metropolitana mediante técnicas estadísticas multivariadas []. PE: Universidad Nacional Agraria La Molina; 2021. https://hdl.handle.net/20.500.12996/4874
@mastersthesis{renati/245807,
title = "Evaluación de patrones espaciales y pronóstico de la calidad del aire en Lima Metropolitana mediante técnicas estadísticas multivariadas",
author = "Espinoza Guillen, José Abel",
publisher = "Universidad Nacional Agraria La Molina",
year = "2021"
}
In this research, the multivariate statistical methods of principal component analysis (PCA) and hierarchical cluster analysis (HCA) were applied to the concentration data of six air pollutants and five meteorological parameters during the period 2015-2019 with the objective to determine the patterns spatial air quality in the Metropolitan Area of Lima and Callao (MALC). Likewise, the forecast of the concentrations of atmospheric pollutants was carried out using multiple linear regression models (MLR). The study analyzed the hourly concentration values of PM10, PM2,5, NO2, O3, CO, SO2 and meteorological variables such as air temperature, relative humidity, direction, wind speed and solar radiation measured in the Automatic Monitoring Network were analyzed. of Air Quality (AAQMN), administered by the National Service of Meteorology and Hydrology of Peru (SENAMHI). The main results showed that the ten AAQMN stations could be grouped according to their air pollution behavior into six different groups for PM10 and PM2,5, five different groups for NO2 and CO, three different groups for O3, and seven different groups for SO2. Also, according to the evaluation of the meteorological variables, the stations could be grouped into two different groups for air temperature, relative humidity and solar radiation; five different groups for wind speed; and seven different groups for the wind direction. Finally, the models implemented for the forecasting of the concentrations of the six pollutants of interest presented higher performance when the concentrations of the same pollutant from the other monitoring stations were selected as predictor variables. Likewise, the coefficients of determination adjusted for all models were greater than 41%. The forecast model generated for the O3 parameter had the best performance indicators, reaching an adjusted rsquared of 0.86 with a RMSE of 5.1 µg/m3
This item is licensed under a Creative Commons License