Accurate Prediction of Concentration Changes in Ozone as an Air Pollutant by Multiple Linear Regression and Artificial Neural Networks

This study considers the usage of multilinear regression and artificial neural network modelling to forecast ozone concentrations with regard weather-related indicators (wind speed, wind direction, relative humidity temperature). Initial data were obtained by measuring meteorological parameters using PC Radio Weather Station. Ozone near high-voltage lines measured RS1003 at a 220 m distance ML9811. Neural models such as multilayer perceptron radial basis function networks constructed. The prognostic capacities designed assessed comparing result way square coefficient multiple correlations (R2) mean error (MSE) values. number hidden neurons was optimised decreasing an that recorded units in layers precision expanded networks. software IBM SPSS 26v used for (ANN) modelling. demonstrated linear approach lacking its capacity predict investigated parameters, whereas use ANN offered more precise outcomes. conducted tests’ results established strength irrelevant differences between detected forecasted data.