Short‐term forecasting of air pollution index in Belgrade, Serbia

Abstract

Forecasting air pollution in big cities is of great importance, and there are various types of air pollution indices (APIs). In the present study, the level of air pollution in winter 2011 at four point-locations in Belgrade, Serbia, was measured using wind speed data and non-standard and standard air temperature data, measured at 10 and 2 m, respectively. Using multiple linear regression (MLR) analysis, equations to forecast the API were obtained. This forecast was verified using data from the winter of 2012/2013. The results obtained are well aligned with the monitored API and verified by the root mean square error (RMSE). It is shown that standard meteorological measurements representative of the city can accurately predict the API at individual point-locations as well as using temperature and wind speed measured at each respective location. Three locations, which measured SO 2 , NO 2 , PM 10 , O 3 and CO, showed poor air quality for > 78% of days observed. For the fourth location, the final estimate of prevailing air quality could not be calculated due to the absence of PM 10 measurements. Forecasting the API on a short-term scale can be of great help for long-term air-quality improvements.

Longer Time Span Air Pollution Prediction: The Attention and Autoencoder Hybrid Learning Model

“…On the other hand, the practical value of models for air pollution prediction task can be hindered by the limited forecast time span. For previous study mainly focusing on accuracy [41][42][43], the time span was restricted to one hour and the result was bound to be accurate since it is hard for air pollution values to change dramatically during one hour without specific activity of human beings. us, the correlation coefficient result of the predict and real value will remain high even if we let the current value as the predicted one.…”

Machine learning algorithms to forecast air quality: a survey

“…Then, they apply multi-linear regression to predict AQI in Catalonia. Durić and Vujović ( 2020 ) apply multi-linear regression, using 3 predictor variables, to forecast AQI in four stations of Belgrade.…”

Evaluation and Comparison of Air Pollution Governance Performance: An Empirical Study Based on Jiangxi Province

“…Specifically, the discussion focused on the following three areas. First, from a multidisciplinary perspective, scholars have used Data Envelopment Analysis (DEA) models, multiple linear regression (MLR), fuzzy ranking method, life cycle assessment (LCA) method, and other mathematical and theoretical models to empirically study the air environment state [3][4][5][6]. Second, for considering air mobility and other characteristics, some scholars assess the performance of collaborative air pollution governance among local governments [7][8][9].…”