Neural Network Fitting using Levenberg-Marquardt Training Algorithm for PM10 Concentration Forecasting in Kuala Terengganu

Authors

  • Samsuri Abdullah School of Marine and Environmental Sciences, Universiti Malaysia Terengganu, 21030, Kuala Terengganu, Terengganu, Malaysia.
  • Marzuki Ismail School of Marine and Environmental Sciences, Universiti Malaysia Terengganu, 21030, Kuala Terengganu, Terengganu, Malaysia.
  • Si Yuen Fong School of Marine and Environmental Sciences, Universiti Malaysia Terengganu, 21030, Kuala Terengganu, Terengganu, Malaysia.
  • Ali Najah Ahmed Faculty of Engineering, Universiti Tenaga Nasional, 43650, Bangi, Selangor, Malaysia.

Keywords:

Kuala Terengganu, Levenberg-Marquardt, Particulate Matter, Principal Component Analysis.

Abstract

The forecasting of Particulate Matter (PM10) is crucial as the information can be used by local authority in informing community regarding the level air quality at specific location. The non-linearity of PM10 in atmosphere after it was subjected by several meteorological parameters should be treated with powerful statistical models which can provide high accuracy in forecasting the PM10 concentration for instance Neural Network (NN) model. Thus, the aim of this study is establishment of NN model using Levenberg-Marquardt training algorithm with meteorological parameters as predictors. Daily observations of PM10, wind speed, relative humidity, ambient temperature, rainfall, and atmospheric pressure in Kuala Terengganu, Malaysia from January 2009 to December 2014 were selected for predicting PM10 concentration level. Principal Component Analysis (PCA) was applied prior the establishment of NN model with the aim of reducing multi-collinearity among predictors. The three principal components (PC-1, PC-2, PC-3) as the result of PCA was used as the input for the NN model. The NN model with 14 hidden neurons was found as the best model having MSE of 0.00164 and R values of 0.80435(Training stage), 0.85735(Validation stage), and 0.8135(Testing stage). Overall the model performance was achieved as high as 81.1% for PM10 forecasting in Kuala Terengganu.

References

M.T. Latif, S.Z. Azmi, A.D.M. Noor, A.S. Ismail, Z. Johny, S. Idrus, A.F. Mohamed, and M. Mohktar. “The impact of urban growth on regional air quality surrounding the Langat river basin. Malaysia’, in Environmentalist, vol. 31, pp. 315-324. 2010.

D.M. Markovic, D.A. Markovic, A. Jovanovic, L. Lazic, and Z. Mijic. “Determination of O3, NO2, SO2, CO and PM10 measured in Belgrade urban area”, in Environmental Monitoring and Assessment, vol. 145(1), pp. 349-359. 2008

D.W. Dockery, “Health effects of particulate air pollution”, in Annals of Epidemiology, vol. 19(4), pp. 257-263. 2009.

R. Afroz, M.N. Hassan, and N.A. Ibrahim. “Review of air pollution and health in Malaysia”, in Environmental Research, vol. 92, pp. 71-77, 2003.

D.C. Shin. “Health effects of ambient particulate matter”, in Journal of the Korean Medical Association, vol. 50 (2), pp. 175-182, 2007.

X. Querol, A. Alastuey, C.R. Ruiz, B. Artinano, H.C. Hansson, R.M. Harisson, E. Buringh, H.M. ten Brink, M. Lutz, P. Bruckmann, P. Straehl, and J. Schneider. “Speciation and origin of PM10 and PM2.5 in selected European Cities”, in Atmospheric Environment, vol. 38, pp. 6547-6555, 2004.

S. Abdullah, M. Ismail, S.Y. Fong, and A.N. Ahmed. “Principal Component Regression (PCR) for PM10 forecasting in Kuala Terengganu, Terengganu”, in Proceedings of National Conference on Wood based Technology, Engineering and Innovation, pp. 82-88, 2015.

R. Afroz, M.N. Hassan, and N.A. Ibrahim. “Review of air pollution and health in Malaysia”, in Environmental Research, vol. 92, pp. 71-77, 2003.

G.D. Gennaro, L. Trizio, A.D. Gilio, J. Pey, N. Perez, M. Cusack, A. Alastuey, and X. Querol, X. “Neural network model for the prediction of PM10 daily concentrations in two sites in the Western Mediterranean”, in Science of the Total Environment, vol. 463-464, pp. 875-883, 2013.

H. Niska, T. Hiltunen, A. Karppinen, J. Ruuskanen, and M. Kolehmainen. “Evolving the neural network model for forecasting air pollution time series”, in Engineering Applications of Artificial Intelligence, vol. 17, pp. 159-167, 2004.

M.N. Noor, and M.I. Zainudin, M.L. “A review: Missing values in environmental data sets”, in Proceeding of International Conference on Environment, Malaysia, 2008.

G. Hawthrone, and P. Elliot. “Imputing cross-sectional missing data: comparison of common techniques”, in Australian and New Zealand Journal of Psychiatry, vol. 39, pp. 583-590, 2005.

R. Yu, X.C. Liu, T. Larson, and Y. Wang. “Coherent approach for modeling and nowcasting hourly near-road black carbon concentrations in Seattle, Washington”, in Transportation Research Part D, vol. 34, pp. 104-115, 2015.

Chapra, S. C., and Canale, R.P. Numerical Methods for Engineers. Singapore: McGra-Hill, 1998.

S.A. Abdul-Wahab, C.S. Bakheit, and S.M. Al-Alawi. “Principal component multiple regression analysis in modelling of ground-level ozone and factors affecting its concentrations”, in Environmental Modeling and Software, vol. 20, pp. 1263-1271, 2005.

S. Abdullah, M. Ismail, M., S.Y. Fong, and A.N. Ahmed. “Evaluation for long term PM10 concentration forecasting using Multi Linear Regression (MLR) and Principal Component Regression (PCR) models:, in EnvironemntAsia, vol. 9(2), pp. 101-110, 2016.

N.R. Awang, N.A. Ramli, A.S. Yahaya, and M. Elbayoumi, “Multivariate methods to predict gound level ozone during daytime, nighttime, and critical conversion time in urban areas”, in Atmospheric Pollution Research, vol. 6, pp. 726-734, 2015.

A.Z. Ul-Saufie, A.S. Yahaya, N.A. Ramli, N. Rosida, and H.A. Hamid. “Future daily PM10 concentrations prediction by combining regression models and feedforward back propagation models with Principle Component Analysis (PCA)”, in Atmospheric Environment, vol. 77, pp. 621-630, 2013.

I.N. Daliakopoulas, P. Coulibaly, and I.K. Tsanis, I.K. “Groundwater level forecasting using artificial neural network”, in Journal of Hydrology, vol. 309, pp. 229-240, 2005.

A.Z. Ul-Saufie, A.S. Yahya, N.A. Ramli, and H.A. Hamid. “Comparison between multiple linear regression and feed forward back propagation neural network models for predicting PM10 concentration level based on gaseous and meteorological parameters”, in International Journal of Applied Science and Technology, vol. 1(4), pp. 42-49, 2011.

N.A. Ramli, N.A. Ghazali, and A.S. Yahaya “Diurnal fluctuations of ozone concentrations and its precursors and prediction of ozone using multiple linear regressions”, in Malaysian Journal of Environmental Management, vol. 11(2), pp. 57-69, 2010.

H. Ahmat, A.S. Yahaya, and N.A. Ramli, N. A. “The Malaysia PM10 analysis using extreme value”, in Journal of Engineering Science and Technology, vol. 10(12), pp. 1560-1574, 2015.

Department of Environment. Malaysia Environmental Quality Report 2014. Kuala Lumpur: Department of Environment Malaysia. 2015.

R. Afroz, M.N. Hassan, and N.A. Ibrahim. “Review of air pollution and health in Malaysia”, in Environmental Research, vol. 92, pp. 71-77, 2003.

Downloads

Published

2016-12-01

How to Cite

Abdullah, S., Ismail, M., Yuen Fong, S., & Ahmed, A. N. (2016). Neural Network Fitting using Levenberg-Marquardt Training Algorithm for PM10 Concentration Forecasting in Kuala Terengganu. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 8(12), 27–31. Retrieved from https://jtec.utem.edu.my/jtec/article/view/1431