The biggest problem facing air protection in Poland is the high levels of suspended particular matter concentrations. Air monitoring reports show that air quality standards, related to PM10 and PM2.5 concentrations, are exceeded every year in many Polish cities. The PM2.5 aerosol fraction is particularly dangerous to human and animal health. Therefore, monitoring the level of PM2.5 concentration should be considered particularly important. Unfortunately, most monitoring stations in Poland do not measure this dust fraction. However, almost all stations are equipped with analyzers measuring PM10 concentrations. PM2.5 is a fine fraction of PM10, and there is a strong correlation between the concentrations of these two types of suspended dust. This relationship can be used to determine the concentration of PM2.5. The main purpose of this analysis was to assess the accuracy of PM2.5 concentration prediction using PM10 concentrations. The analysis was carried out on the basis of long-term hourly data recorded at several monitoring stations in Poland. Artificial neural networks in the form of a multilayer perceptron were used to model PM2.5 concentrations.
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 use of averaged directional air pollution inflows has been investigated for the area representativeness evaluation of automatic air monitoring stations. Two-year data from chosen monitoring stations were used. The one-hour values of SO 2 , NO, NO 2 , CO, and PM10 concentrations were ordered with respect to their inflow direction, by dividing them into 36 sectors of 10º range and calculating their arithmetic mean. For the obtained values, the dispersion analysis was carried out. It was concluded that the averaged concentration dispersion of pollutants in the direction sectors can be used as one of the criteria for the automatic air monitoring stations area representativeness evaluation. The changeability coefficients can be used as a measure of the dispersion. They are dimensionless quantities, often expressed as percentages.
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.