Improving the accuracy of the calculated environmental monitoring of atmospheric air quality in cities based on a corrective neural network

• Published in: IOP conference series. Earth and environmental science Vol. 864; no. 1; pp. 12029 - 12032
• Main Authors: Tunakova, Y A, Novikova, S V, Shagidullin, A R, Valiev, V S, Novikova, K N
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.09.2021
• Subjects: Air monitoring; Air pollution; Air quality; Environmental monitoring; Impurities; Mathematical analysis; Natural resources; Neural networks; Outdoor air quality; Pollutants; Pollution sources; Temporal resolution
• ISSN: 1755-1307; 1755-1315
• DOI: 10.1088/1755-1315/864/1/012029

To obtain the values of the concentrations of atmospheric impurities with a spatial-temporal resolution throughout the city, which is not achieved during systematic experimental observations, it is recommended to use calculation methods. A significant advantage of the calculated concentrations, in contrast to the experimental ones, is the ability to determine the concentration at any point in the study area at the present time and in the future when the characteristics of stationary pollution sources change. To calculate the dispersion of emissions of pollutants in the air and determine the surface concentrations of impurities, the order of the Ministry of Natural Resources and Environment of the Russian Federation regulates the use of the universal program for calculating atmospheric pollution (UPCAP) “Ecolog”. To increase the convergence of the measured concentrations of impurities and calculated concentrations obtained using UPCAP “Ecolog-Gorod” we propose the use of neural network technologies.