MODIFICATION OF THE AIR QUALITY INDEX CLASSIFIER IN BISHKEK TAKING INTO ACCOUNT THE POLLUTION FACTOR

Authors

Lychenko N.M. Machinery researching and Аutomatics Institute of Kyrgyz Republic National Academy of Science
Sorokovaya A.V. Machinery researching and Automatics Institute of Kyrgyz Republic National Academy of Sciences

Keywords:

classification, forecast, air quality index, LSTM neural network, pollution factors

Abstract

The results of the analysis and use of information on the number of tons of coal burned daily at the CHPP in Bishkek to improve the accuracy of the forecast of the air quality index (AQI) class based on the LSTM-neural classifier are presented. This classifier allows, depending on meteorological conditions and the previous history of AQI values, to predict the AQI class from the possible four integrated classes: AQI50 / 50 <AQI100 / 100 <AQI150 / AQI> 150. Taking into account the pollution factor as an additional input of the classifier made it possible to obtain a forecast of the AQI class with an accuracy of at least 80%.

References

Великанова Л.И., Лыченко Н.М. Мультирегрессионные и обобщенно-регрессионные нейросетевые модели краткосрочного прогноза загрязнения РМ2.5 в г. Бишкек с учетом метеорологических параметров// Проблемы автоматики и управления.- N2. Бишкек: Илим, 2019. –С. 42-51.

Лыченко Н.М., Сороковая А.В. Прогнозирование классов индекса качества воздуха г. Бишкек с учетом новых данных 2020-2021 гг. на базе LSTM-нейросетевого классификатора// Проблемы автоматики и управления. 2021. № 2 (41). С. 89-99.

Air Quality Index (AQI) - A Guide to Air Quality and Your Health. US EPA. 9 December 2011.

Cайт «Расписание погоды rp5.ru» Архив погоды в Бишкеке https://rp5.ru/%D0%90%D1%80%D1%85%D0%B8%D0%B2_%D0%BF%D0%BE%D0%B3%D0%BE%D0%B4%D1%8B_%D0%B2_%D0%91%D0%B8%D1%88%D0%BA%D0%B5%D0%BA%D0%B5 (дата обращения: 30.07.2021)

Burhan Baran. Prediction of Air Quality Index by Extreme Learning Machines// 2019 International Artificial Intelligence and Data Processing Symposium (IDAP) DOI: 10.1109/IDAP.2019.8875910

Soubhik Mahanta, T. Ramakrishnudu; Rajat Raj Jha; Niraj Tailor. Urban Air Quality Prediction Using Regression Analysis//TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON). Date of Conference: 17-20 Oct. 2019 DOI: 10.1109/TENCON.2019.8929517

M. Sharma; S. Aggarwal; P. Bose; A. Deshpande. Meteorology-based forecasting of air quality index using neural network//IEEE International Conference on Industrial Informatics, 2003. INDIN 2003. Proceedings. DOI: 10.1109/INDIN.2003.1300360

AirNow Depatment of State // https://airnow.gov/index.cfm?action=airnow.global _summary #U.S._Department_of_State $Bishkek, (дата обращения: 30.07.2021).

Лыченко Н.М. Регрессионный анализ метеорологических факторов и концентраций частиц РМ2.5 в атмосферном воздухе г. Бишкек// Проблемы автоматики и управления.- N2. Бишкек: Илим, 2019. –С. 5-15.

Бокс Д., Дженкинс Т. Анализ временных рядов: прогноз и управление. М.: Мир, 1974. 242 с.

X. Zhao, R. Zhang, J.-L. Wu, P.-C. Chang. A Deep Recurrent Neural Network for Air Quality Classification // Journal of Information Hiding ultimedia Signal Processing. – V.9, N.2, March 2018.

Understanding LSTM Networks. – URL: http://colah.github.io/posts/2015-08-Understanding-LSTMs/ (дата обращения 14.09.2021).