Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Forecasting Air Quality by Estimating PM2.5 Concentration Level Using k-Nearest Neighbor Model in Gazipur, Bangladesh
Natural and anthropogenic variables, combined with meteorological components affect the concentration of air pollutants such as particulate matter (PM), sulfur dioxide (SO2), carbon dioxide (CO2), carbon monoxide (CO), nitrogen oxides (NOx), and ozone (O3). The K-nearest neighbor (kNN), a simple and effective machine learning model, is leveraged to anticipate the concentration of PM2.5, one of the most harmful air pollutants, in Gazipur City, Bangladesh. A dataset of PM2.5 and meteorological variables from 2012 to 2018 are used and analyzed in this study. Several error metrics, such as mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), and R2, are used to evaluate the prediction models. A benchmark was established to evaluate the obtained PM2.5 values. The temporal and spatial fluctuations of PM2.5 served as an indicator of the likelihood of high concentrations of PM2.5 particles in the Gazipur locality. Results from this study achieved significantly accurate and dependable predictions of PM2.5 concentration in Gazipur, Bangladesh, which may further contribute to sustainable air pollution prediction strategies to ameliorate air quality.
Forecasting Air Quality by Estimating PM2.5 Concentration Level Using k-Nearest Neighbor Model in Gazipur, Bangladesh
Natural and anthropogenic variables, combined with meteorological components affect the concentration of air pollutants such as particulate matter (PM), sulfur dioxide (SO2), carbon dioxide (CO2), carbon monoxide (CO), nitrogen oxides (NOx), and ozone (O3). The K-nearest neighbor (kNN), a simple and effective machine learning model, is leveraged to anticipate the concentration of PM2.5, one of the most harmful air pollutants, in Gazipur City, Bangladesh. A dataset of PM2.5 and meteorological variables from 2012 to 2018 are used and analyzed in this study. Several error metrics, such as mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), and R2, are used to evaluate the prediction models. A benchmark was established to evaluate the obtained PM2.5 values. The temporal and spatial fluctuations of PM2.5 served as an indicator of the likelihood of high concentrations of PM2.5 particles in the Gazipur locality. Results from this study achieved significantly accurate and dependable predictions of PM2.5 concentration in Gazipur, Bangladesh, which may further contribute to sustainable air pollution prediction strategies to ameliorate air quality.
Forecasting Air Quality by Estimating PM2.5 Concentration Level Using k-Nearest Neighbor Model in Gazipur, Bangladesh
Lecture Notes in Civil Engineering
Nia, Elham Maghsoudi (Herausgeber:in) / Awang, Mokhtar (Herausgeber:in) / Uddin, Rafi (Autor:in) / Faiaz, Abrar (Autor:in) / Islam, Sk. Rakibul (Autor:in)
International Conference on Architecture and Civil Engineering Conference : ; 2023 ; Putrajaya, Malaysia
06.07.2024
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
| DOAJ | 2021
Nearest Neighbor Probabilistic Model for Aluminum Polycrystals
| Online Contents | 2010
Improved K-Nearest Neighbor Weather Generating Model
| British Library Online Contents | 2007
Improved K-Nearest Neighbor Weather Generating Model
| Online Contents | 2007