Application of artificial neural networks in the development of the PM10 air pollution prediction system

• Autorzy: Wiktorzak Aneta , Sawicki Andrzej

Identyfikatory

DOI

10.34808/bamk-q919

• Języki publikacji: EN

Abstrakty

EN

This article presents research on the model of forecasting the average daily air pollution levels focused mainly on two solutions, artificial neural networks: the NARX model and the LSTM model. The research used an air quality monitoring system. This system includes individually designed and implemented sensors to measure the concentration of pollutants such as PM10, PM2.5, SO2, NO2 and to record weather conditions such as temperature, humidity, pressure, wind strength and speed. Data is sent to a central database server based on the MQTT protocol. Additional weather information in the area covered by pollution monitoring is collected from the weather services of the IMGW and openwethermap.org. The artificial neural network models were built in the MATLAB environment, the process of learning neural networks was performed and the results of pollution prediction for the level of PM10 dust were tested. The models showed good and acceptable results when forecasting the state of PM10 dust concentration in the next 24 hours. The LSTM prediction model were more accurate than the NARX model. The future work will be related to the use of artificial intelligence algorithms to predict the concentration of other harmful substances, e.g. PM2.5, NO2, SO2 etc. A very important task in the future will be to frame the entire system of monitoring and predicting smog in a given area.

Słowa kluczowe

EN

NARX; LSTM; PM10

PL

NARX; LSTM; PM10

• Wydawca: Politechnika Gdańska
• Czasopismo: TASK Quarterly : scientific bulletin of Academic Computer Centre in Gdansk
• Rocznik: 2023
• Tom: Vol. 27, No 1
• Strony: 1--9
• Opis fizyczny: Bibliogr. 11 poz., rys., tab.

Twórcy

autor

Wiktorzak Aneta

• Lomza State University of Applied Science

• https://orcid.org/0000-0002-3885-1340

autor

Sawicki Andrzej

• Lomza State University of Applied Science

• https://orcid.org/0000-0001-8904-2845

Bibliografia

• [1] R. Hyndman and G. Athanasopoulos, “Forecasting: principles and practice,” 2021.
• [2] B. G. Horne, H. T. Siegelmann, and C. L. Giles, “What narx net-works can compute,” in SOFSEM ’95: Proceedings of the 22ndSeminar on Current Trends in Theory and Practice of Informatics,(Berlin, Germany), pp. 95–102, Springer-Verlag, 2015.
• [3] O. Omolaye and T. Badmos, “Predictive and comparative analysis of narx and nio time series prediction, ”American Journal of Engineering Research (AJER), pp. 155–165, 2017.
• [4] T. Liu, T. Wu, M. Wang, M. Fu, J. Kang, and H. Zhang, “Recur-rent neural networks based on lstm for predicting geomagnetic field,” in Proceedings of the 2018 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology (ICARES),(Bali, Indonesia), p. 1–5, Institute of Electrical and Electronics Engineers (IEEE), 20–21 September 2018 2018.
• [5] J. Fan, Q. Li, J. Hou, X. Feng, H. Karimian, and S. Lin, “A spatiotemporal prediction framework for air pollution based on deep rnn,”ISPRS Ann. Photogramm. Remote. Sens. Spat. Inf. Sci, vol. 4,p. 15–22, 2017.
• [6] Math Works, Deep Learning Toolbox, 2022. Design, train, and analyze deep learning networks [13.09.2022].
• [7] A. Heydari, M. Majidi Nezhad, D. Astiaso Garcia, and et al., “Airpollution forecasting application based on deep learning model and optimization algorithm, ”Clean Techn Environ Policy, vol. 24,p. 607–621, 2022.
• [8] S. Agarwal, S. Sharma, R. Suresh, M. Rahman, S. Vranckx, B. Maiheu, L. Blythb, S. Janssen, P. Gargava, V. Shukl, and S. Batra, “Air quality forecasting using artificial neural networks with real time dynamic error correction in highly polluted regions,” 2020.
• [9] G. Gennaro, L. Trizio, A. Di, J. Pey, N. Pérez, M. Cusack, A. Alastuey, and X. Querol, “Neural network model for the pre-diction of pm10 daily concentrations in two sites in the western mediterranean,”Sci Total Environ, vol. 463–464, p. 875–883, 2013.
• [10] D.-R. Liu, S.-J. Lee, Y. Huang, and C.-J. Chiu, “Air pollution fore-casting based on attention- based lstm neural network and ensemble learning, ”Expert Syst, vol. 37, no. 3, p. 1–16, 2020.
• [11] M. Zeinalnezhad, A. Gholamzadeh, and J. Kleme, “Air pollution prediction using semi- experimental regression model and adaptive neuro-fuzzy inference system, ”J Clean Prod, vol. 261,p. 121218, 2020.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).