Abstract. This scientific paper is dedicated to the use of artificial neural networks for the ecological prediction of state of the atmospheric air of an industrial city for capability of the operative environmental decisions. In the paper, there is also the described development of two types of prediction models for determining of the air pollution index on the basis of neural networks: a temporal (short-term forecast of the pollutants content in the air for the nearest days) and a spatial (forecast of atmospheric pollution index in any point of city). The stages of development of the neural network models are briefly overviewed and description of their parameters is also given. The assessment of the adequacy of the prediction models, based on the calculation of the correlation coefficient between the output and reference data, is also provided. Moreover, due to the complexity of perception of the «neural network code» of the offered models by the ordinary users, the software implementations allowing practical usage of neural network models are also offered. It is established that the obtained neural network models provide sufficient reliable forecast, which means that they are an effective tool for analyzing and predicting the behavior of dynamics of the air pollution in an industrial city. Thus, this scientific work successfully develops the urgent matter of forecasting of the atmospheric air pollution index in industrial cities based on the use of neural network models.

In order to control the chemical composition of atmospheric air in cities located in the zone of influence of petrochemical enterprises, automatic atmospheric air monitoring stations (ASKAV) are installed. For the effective use of experimental data, the authors of the article developed a data collection system with ASKAV, in which the air control in residential quarters and the gas mixture at the source of organized emissions are synchronized. The analysis of data on the concentration of pollutants in the atmospheric air of the Sterlitamak obtained from ASKAV, on the basis of which a list of marker substances for enterprises of the city was compiled. Priority sources of air pollution with marker substances during a different wind regime were identified. The authors developed models for changing the concentration of marker substances in the air using the method of factor regression. Based on the results of the cross-correlation function, the time of movement of the contaminated gas cloud from the source of emission to the residential area of the city is obtained. Conclusions are made about the effectiveness of the developed air monitoring system and the field of application of the acquired models.

A study of the peculiarities of the change in the concentration of toluene in the atmospheric air of the city, where the sources of the substance are both vehicles and an industrial enterprise for the production of synthetic rubber, has been carried out. The paper analyzes the behavior of methylbenzene in different periods: with small and large volumes of industrial emissions. The sources of the substance intake are described. A diagram of the change in the emission volumes of the toluene source enterprise has been built. The periods, characterized by different industrial load on the hygienic state of the air in the city, have been determined. Statistical characteristics of data arrays of methylbenzene concentration for the periods of 2010–2012 and 2015–2017 were calculated. Wind directions are obtained showing the priority influence of the pollution source. The nature of the influence of meteorological parameters on the toluene content in the air of the residential part of the city was revealed at various volumes of the petrochemical enterprise’s emission. The study revealed a change in the influence of temperature and wind speed on the toluene content in the atmospheric air of the city under various anthropogenic load.

In order to monitor the chemical composition of atmospheric air in cities located in the zone of petrochemical enterprises influence, automatic atmospheric air monitoring stations (AAAMS) are being established. The concentration of phenol and methanol in the air of the residential part of the city is recorded at AAAMSs. In the industrial zone air, the methanol content is measured at the source of pollution. Processing the numerical series of the measured concentrations values using the cross-correlation function allows you to get the time lag of the contaminated gas cloud moving from the source of emission to the city. Models have been developed for changes in concentration of phenol in the air of the residential area using the factor regression method, taking into account the concentration of the analyzed compounds, the time lag from the source of pollution to the living area and weather conditions: - air temperature and humidity, wind direction and speed.

Аннотация. Многолетняя деятельность предприятий нефтеперерабатывающей и нефтехимической промышленности неизбежно оказывает значительное негативное воздействие на все сопряженные с ними компо-© Электронный научный журнал «Нефтегазовое дело». 2015. №1 http://www.ogbus.ru ненты окружающей среды. Атмосфера и гидросфера, являясь динамичными компонентами с высокой скоростью самоочищения не накапливают в