Air quality is assessed on the basis of air monitoring data. Monitoring data are often not complete enough to carry out an air quality assessment. To fill the measurement gaps, predictive models can be used, which enable the approximation of missing data. Prediction models use historical data and relationships between measured variables, including air pollutant concentrations and meteorological factors. The known predictive air quality models are not accurate, so it is important to look for models that give a lower approximation error. The use of artificial neural networks reduces the prediction error compared to classical regression methods. In previous studies, a single regression model over the entire concentration range was used to approximate the concentrations of a selected pollutant. In this study, it was assumed that not a single model, but a group of models, could be used for the prediction. In this approach, each model from the group was dedicated to a different sub-range of the concentration of the modeled pollutant. The aim of the analysis was to check whether this approach would improve the quality of modeling. A long-term data set recorded at two air monitoring stations in Poland was used in the examination. Hourly data of basic air pollutants and meteorological parameters were used to create predictive regression models. The prediction errors for the sub-range models were compared with the corresponding errors calculated for one full-range regression model. It was found that the application of sub-range models reduced the modeling error of basic air pollutants.
The purpose of the paper was to analyse the trends observed at air monitoring stations in the Malopolska Province - one of the most polluted regions in Poland. The study was carried out on the basis of long-term measurement data registered at five selected stations of automatic monitoring of air quality in the Malopolska Province. Trends evaluation was made on the basis of mean annual concentrations, taken from the database of the Chief Inspectorate for Environmental Protection in Poland. Separately for each basic air pollutant, such as SO2, NO2, NOx, CO, PM10 and O3, trend lines and their linear equations were determined to illustrate the direction of changes in concentrations. The obtained equations of the trend lines indicate the threat to the environment in the Malopolska Province. Based on the results obtained it can be concluded that for recent years there has been observed the concentration decrease of main air pollutants, except of tropospheric ozone.
Predykcja średniomiesięcznych stężeń zanieczyszczeń powietrza dla wybranych obszarów województwa mazowieckiegoThe study was carried out using long-term data, recorded at two air monitoring stations in Masovian Voivodeship. Hourly time series, obtained from the monitoring system, were averaged in calendar months to get monthly time series. The data sets, containing time series of monthly mean values from two different monitoring sites, were subjected to multivariate regression analysis. Models of multidimensional linear regression were built for the both sets of data. The obtained models describe statistical dependencies between concentrations of specified air pollutants and concentrations of other pollutants and meteorological parameters, recorded at the same monitoring station. The achieved regression equations were used to predict long-term courses of monthly concentrations. For visualization of prediction accuracy, the charts containing time series of actual and predicted monthly concentrations were prepared. The approximation precision was estimated by calculating modelling errors for each regression model. Three different measures of approximation error were applied: mean absolute error (MAE), root mean square error (RMSE), and Pearson correlation coefficient (r).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.