Authors : Nongthombam Premananda Singh; Romesh Laishram

Volume/Issue : Volume 9 - 2024, Issue 7 - July

Google Scholar : https://tinyurl.com/2xew4vzc

Scribd : https://tinyurl.com/4wvw7fsn

DOI : https://doi.org/10.38124/ijisrt/IJISRT24JUL154

Abstract : In this study, a forecasting system is developed for predicting PM10 levels in Imphal City over the next three days (+1, +2, and +3 days) using artificial neural networks (ANN). The experimental findings indicate that the ANN model can achieve reasonably accurate predictions of air pollutant levels. Moreover, optimizations in model performance are explored through variations in input parameters and experimental setups. Initially, predictions for each of the +1, +2, and +3 days are made independently using the same training dataset. Subsequently, cumulative predictions for +2 and +3 days are generated using previously predicted values from preceding days, yielding improved prediction accuracy. Additionally, the study identifies the optimal size of the training dataset, determining that using data spanning 3 to 15 past days yields the minimum error rates in predicting pollutant concentrations. Finally, the investigation includes the consideration of days-of-week as an input parameter, which enhances forecast accuracy noticeably.

Keywords : Air Pollution, Artificial Neural Network, Forecasting, Modelling Technique, Particulate Matter.

References :

1. Akkoyunlu, A., Ertürk F. Evaluation of air pollution trends in İstanbul. Int J Environ Pollut;18:388–98 (2003)
2. Athanasiadis, I. N., K. Karatzas, and P. Mitkas. "Contemporary air quality forecasting methods: a comparative analysis between classification algorithms and statistical methods." Fifth international conference on urban air quality measurement, modelling and management, Valencia, Spain (2005)
3. Bishop, A.: Neural networks for pattern recognition. Oxford University Press, UK (1995)
4. Boznar M, Lesjack M, Mlakar P. A neural network based method for short-term predictions of ambient SO2 concentrations in highly polluted industrial areas of complex Terrain. Atmos Environ 270:221–30 (1993)
5. Chaloulakou A, Saisana M, Spyrellis N. Comparative assessment of neural networks and regression models for forecasting summertime ozone in Athens. Sci Total Environ 313:1-13 (2003)
6. Deleawe, S., Kusznir, J., Lamb, B., Cook, D.J.: Predicting air quality in smart environments. J. Ambient Intell. Smart Environ. 2(2), 145–154 (2010)
7. Dimitriou, K., Paschalidou, A.K., Kassomenos, P.A.: Assessing air quality with regards to  its effect on human health in the European Union through air quality indices. Ecol. Ind.  27, 108–115 (2013)
8. Elbir T, Muezzinoglu A, Bayram A. Evaluation of some air pollution indicators in Turkey. Environ Int 26(1–2):5–10 (2000)
9. Fausett, Laurene. "Neural networks: architectures, algorithms and applications." Prentice-Hall, Inc., New Jersy 1 869-873 (1994)
10. Gardner, Matt W., and S. R. Dorling. "Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences." Atmospheric environment 32.14/15: 2627-2636. (1998)
11. Gardner, M.W., Dorling, S.R.: Neural network modelling and prediction of hourly NOx and NO2 concentrations in urban air in London. Atmos. Environ. 33(5), 709–719 (1999)
12. Hertz, J.A., Krogh, A.S., Palmer, R.G.: Introduction to the theory of neural computation. Addison Wesley, Canada (1995)
13. Kandasamy, S., Baret, F., Verger, A., Neveux, P., Weiss, M.: A comparison of methods for smoothing and gap filling time series of remote sensing observations application to MODIS LAI products. Biogeosciences 10(6), 4055–071 (2013).
14. Karaca, F., Alagha, O., Ertürk, F.: Application of inductive learning: air pollution forecast in Istanbul. Turkey. Intell. Autom. Soft Comput. 11(4), 207–216 (2005)
15. Karaca F, Alagha O, Ertürk F. Statistical characterization of atmospheric PM₁₀ and PM_2.5 concentrations at a non-impacted suburban site of Istanbul, Turkey. Chemosphere; 59(8):1183–90 (2005b)
16. Karaca F, Nikov A, Alagha O. NN-AirPol: a neural-network-based method for air pollution  evaluation and control. Int J Environ Pollut;28(3/4):310–25 (2006a)
17. Karaca F, Ölmez I, Aras NK. A radiotracer method to study the transport of mercury (II) chloride from water to sediment and air. J Radioanal Chem;259:223–6 (2004)
18. Kolehmainen, M., Martikainen, H., Ruuskanen, J.: Neural neworks and periodiccomponents used in air quality forecasting. Atmos. Environ. 35(5), 815–825 (2001)
19. Kukkonen, J., Partanen, L., Karppinen, A., Ruuskanen, J., Junninen, H., Kolehmainen, M., Cawley, G.: Extensive evaluation of neural network models for the prediction of  NO2 and PM₁₀ concentrations, compared with a deterministic modelling system and measurements in central Helsinki. Atmos. Environ. 37(32), 4539–4550 (2003)
20. Künzli N, Kaiser R, Medina S, Studnicka M, Chanel O, Filliger P, et al. Public health impact of outdoor and traffic-related air pollution. Eur Assess; 356(9232):795–801 (2000)
21. Monteiro A, Lopes M, Miranda AI, Borrego C, Vautard R. Air pollution forecast in Portugal: a demand from the new air quality framework directive. Int J Environ Pollut;5:1–9 (2005)
22. Rumelhart, E., Hinton, J., Williams, R.: Learning internal representations by error propagation, in parallel distributed processing: exploration in the microstructure of cognition, vol. 1. MIT press, Cambridge (1986)
23. Tayanç M. An assessment of spatial and temporal variation of sulfur dioxide levels over Istanbul, Turkey. Environ Pollut;107(1):61–9 (2000)
24. Pope III, C.A., Burnett, R.T., Thun, M.J., Calle, E.E., Krewski, D., Ito, K., Thurston, G.D.:   Lung cancer, cardiopulmonary mortality, and long-term exposure to fine particulate air   pollution. JAMA 287(9), 1132–1141 (2002)
25. Viotti, P., Liuti, G., Di Genova, P.: Atmospheric urban pollution: applications of an  artificial neural network (ANN) to the city of Perugia. Ecol. Model. 148(1), 27–46 (2002)