FORECASTING OF BISHKEK AIR QUALITY INDEX CLASSES ACCOUNTING FOR THE 2020-2021 PERIOD NEW DATA ON THE BASE LSTM-NETWORKS CLASSIFIER
Keywords:
classification, air quality index, LSTM neural network, forecast accuracy.Abstract
Predictive models of the air quality index AQI in Bishkek have been developed based on classifiers based on the LSTM network. The models allow, depending on meteorological conditions and the previous history of AQI values, to predict the AQI class from the possible four integrated classes: AQI≤50 / 50 <AQI≤100 / 100 <AQI≤150 / AQI> 150. The forecast is possible up to 4 days ahead with an accuracy of at least 77%.
References
AirNow Depatment of State // https://airnow.gov/index.cfm?action=airnow.global _summary #U.S._Department_of_State $Bishkek, (дата обращения: 30.04.2021).
Лыченко Н.М., Великанова Л.И., Верзунов С.Н., Сороковая А.В. Модели прогноза уровня загрязнения атмосферного воздуха г. Бишкек// Вестник КРСУ. Т.24. №4. 2021. С.87-95.
Air Quality Index (AQI) - A Guide to Air Quality and Your Health. US EPA. 9 December 2011.
Лыченко Н.М., Сороковая А.В. Применение LSTM-нейронных сетей для классификации индекса качества воздуха г. Бишкек // Проблемы автоматики и управления. 2020. № 1 (38). С. 70-80. DOI: 10.5281/zenodo.3904130
Understanding LSTM Networks. – URL: http://colah.github.io/posts/2015-08-Understanding-LSTMs/. (дата обращения 14.09.2020)
Курс CS231n: Convolutional Neural Networks for Visual Recognition.- URL: https://cs231n.github.io/neural-networks-3/#baby (дата обращения 01.09.2020)
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: 30.04.2021)
Оценка классификатора (точность, полнота, F-мера). - URL: http://bazhenov.me/blog/2012/07/21/classification-performance-evaluation.html. (дата обращения 29.05.2020).
FORECASTING OF BISHKEK AIR QUALITY INDEX CLASSES ACCOUNTING FOR THE 2020-2021 PERIOD NEW DATA ON THE BASE LSTM-NETWORKS CLASSIFIER
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2021 Лыченко Н.М., Сороковая А.В.
This work is licensed under a Creative Commons Attribution 4.0 International License.