A Hybrid ARIMA and Artificial Neural Networks Model to Forecast Air Quality in Urban Areas: Case of Tunisia

Abstract:

Forecasting air quality time series represents a very difficult task since air quality contains autoregressive, linear and nonlinear patterns. Autoregressive Integrated Moving Average (ARIMA) models have been widely used in air quality time series forecasting. However, they fail to detect extreme events because of their presumed linear form of data. Artificial Neural Networks (ANN) models have proved to be promising nonlinear tools for air quality forecasting. A hybrid model combining ARIMA and ANN improved forecasting more than either of the models used independently. Experimental results with meteorological and Particulate Matter data indicated that the combined model can be used as an efficient forecasting and early warning system for providing air quality information towards the citizen, not only in Sfax Southern Suburbs but in other Tunisian regions that suffer from poor air quality conditions.

• Periodical: Advanced Materials Research (Volumes 518-523)
• Pages: 2969-2979
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.518-523.2969
• Online since: May 2012
• Authors: Ayari Samia, Nouira Kaouther, Trabelsi Abdelwahed
• Keywords: ARIMAX Models, Artificial Neural Network (ANN), Hybrid Models, Particulate Matter

References

[1] Aslanargun, N. Mammadov, B. Yazici and S. Yolacan, Comparaison of ARIMA, Neural Networks and Hybrid Models in Time Series: Tourist Arrival Forecasting: submitted to Journal of Statistical Computation and Simulation (2007).

DOI: 10.1080/10629360600564874

[2] A. Zolghadri and F. Cazaurang, Adaptive nonlinear State-Space Modelling for the Prediction of Daily Mean PM10 Concentrations: submitted to Environmental Modelling and Software (2006).

DOI: 10.1016/j.envsoft.2005.04.008

[3] A.J. Ansuj, M.E. Camargo, R. Radharamanan and D.G. Petry, Sales Forecasting using Time Series and Neural Networks: submitted to Computers and Industrial Engineering (1996).

DOI: 10.1016/0360-8352(96)00166-0

[4] B. Chelani Asha and S. Devotta, Air Quality Forecasting using a Hybrid Autoregressive and Nonlinear Model: submitted to Atmospheric Environment (2006).

DOI: 10.1016/j.atmosenv.2005.11.019

[5] B. Lennox, G.A Montaque, A.M. Frith, C. Gent and V. Bevan, Industrial Application of Neural Networks: an Investigation : submitted to Journal of Process Control (2001).

DOI: 10.1016/s0959-1524(00)00027-5

[6] C.A. Pope, R.T. Burnett, M.J Thun, E.E. Calle, D. Krewski, K. Ito and G.D. Thurston, Lung Cancer, Cardiopulmonary Mortality and Long-Term Exposure to Fine Particulate Air Pollution: submitted to The Journal of the American Medical Association (2002).

DOI: 10.1001/jama.287.9.1132

[7] C.A. Pope, M. Ezzati and D.W. Dockery, Fine Particulate Air Polution and Life Expectancy in the United States: submitted to The New England Journal of Medicine (2009).

DOI: 10.1056/nejmsa0805646

[8] D. Jiang, Y. Zhang, X. Hu, J. Tan and D. Shao, Progress in Developing an ANN Model for Air Pollution Index Forecast: submitted to Atmospheric Environment (2004).

DOI: 10.1016/j.atmosenv.2003.10.066

[9] D. Rumelhart, G. Hinton and R. Williams, Learning Representations by Back-Propagating Errors: submitted to Nature (1986).

DOI: 10.1038/323533a0

[10] D. Wang and W-Z. Lu, Ground Level Ozone Prediction using Multilayer Perceptron trained with an innovate Hybrid Approach: submitted to Ecological Modelling (2006).

DOI: 10.1016/j.ecolmodel.2006.05.031

[11] D.P. Connel, J.A. Withum, S.E. Winter and R.M. Statnick, The Steubenville Comprehensive Air Monitoring Program (SCAMP): Associations among Fine Particulate Matter, co-pollutants and Meteorological Conditions: submitted to Journal of the Air and Waste Management Association (2005).

DOI: 10.1080/10473289.2005.10464631

[12] D.W. Dockery, C.A. Pope, X. Xu, J. Ware, M. Fay, B. Ferris and F. Speizer, An Association between Air Pollution and Mortality in six U.S cities: submitted to The New England Journal of Medicine (1993).

DOI: 10.1056/nejm199312093292401

[13] D.W. Dockery, J. Schwartz and J.D. Spengler, Air Pollution and Daily Mortality: Associations with Particulates and Acid Aerosols: submitted to Environmental Research (1992).

DOI: 10.1016/s0013-9351(05)80042-8

[14] F. Laden, L.M. Neas, D.W Dockery and J. Schwartz, Association of Fine Particulate Matter from Different Sources with Daily Mortality in six U.S Cities: submitted to Environmental Health Perspective (2000).

DOI: 10.1289/ehp.00108941

[15] G. Box and G. Jenkins: Times Series Analysis: Forecasting and Control (Holden-Day Publications, San Francisco 1996).

[16] G. Corani, Air Quality Prediction in Milan: Feed-Forward Neural Networks pruned Neural Networks and Lazy Learning: submitted to Ecological Modelling (2005).

DOI: 10.1016/j.ecolmodel.2005.01.008

[17] G. Zhang, E. Patuwo and M.Y Hu, Forecasting with Artificial Neural Networks: the State of the Art: submitted to International Journal of Forecasting (1998).

[18] G. Zhang, in: Neural Networks in Business Forecasting, Idea Group Publishing , USA (2004).

[19] G.P. Zhang, Series Forecasting using a Hybrid ARIMA and Neural Network Model: submitted to Neurocomputing (2003).

[20] Pulido-Calvo and M.M. Portela, Application of Neural Approaches to one-step Daily Folw Forecasting in Portiguese Watersheds: submitted to Journal of Hydrology (2007).

DOI: 10.1016/j.jhydrol.2006.06.015

[21] J.B. Ordieres, E.P. Vergara, R.S. Capuz and R.E. Salazar, Neural Network Prediction Model for Fine Particulate Matter(PM2.5) on the US-Mexico border in El Paso(Texas) and Ciudad Juarez (Chihuahua): submitted to Environmental Modelling and Software (2005).

DOI: 10.1016/j.envsoft.2004.03.010

[22] J.C Gutiérrez-Estrada, R. Vaconcelos and M.J. Costa, Estimating Fish Community Diversity in the Environmental Features in the Tagus Estuary (Portugal): Multiple Linear Regression and Artificial Neural Network Approaches: submitted to Journal of Applied Ichthyology (2008).

DOI: 10.1111/j.1439-0426.2007.01039.x

[23] K. Katsouyanni, G. Touloumi, C. Spix, J. Schwartz, F. Balducci, S. Medina, G. Rosso, B. Wojtyniak, J. Sunyer, A. Ponla and H. Anderson, Short Term Effects of Ambient Sulphur Dioxide and Particulate Matter on Mortality in 12 European Cities: Results fromTime Series Data from the APHEA Project: submitted to Air Pollution and Health: a European approach (1997).

DOI: 10.1136/bmj.314.7095.1658

[24] L.A. Dias-Robles, J.C. Ortega, J.C. Fu, G. Reed, J. Chow, J.G. Watson and J.A. Moncada-Herrera, A Hybrid ARIMA and Artificial Neural Networks models to forecast Particulate Matter in Urban Areas: The case of Temuco, Chile: submitted to Atmospheric Environment (2008).

DOI: 10.1016/j.atmosenv.2008.07.020

[25] L.P-WG Grace, Simulation of the Daily Average PM10 Concentrations at Ta-Liao with Box-Jenkis Times Series Models and Multivariate Analysis: submitted to Atmospheric Environment (2009).

DOI: 10.1016/j.atmosenv.2009.01.055

[26] M. Kantardzic: Data Mining: Concepts, Models, Methods and Algorithms (Weley-IEE press, Louisville 2002).

[27] M. Parizeau: Réseaux de Neurones (Université LAVAL, Laval, 2004).

[28] P. Goyal, A.T. Chan and N. Jaiswal, Statistical Models for the Prediction of Respirable Suspended Particulate Matter in Urban Cities: submitted to Atmospheric Environment (2006).

DOI: 10.1016/j.atmosenv.2005.11.041

[29] P. Pérez and J. Reyes, Prediction of Maximum 24-h Average of PM10 Concentrations 30h in advance in Santriago, Chile: submitted to Atmospheric Environment (2002).

DOI: 10.1016/s1352-2310(02)00419-3

[30] P. Pérez, A. Trier and J. Reyes, Prediction of PM2.5 Concentrations Several Hours in Advance Using Neural Networks in Santiago, Chile: submitted to Atmospheric Environment (2000).

DOI: 10.1016/s1352-2310(99)00316-7

[31] S. Thomas and R.B. Jacko, Model for Forecasting Expressway Fine Particulate Matter and Carbon Monoxide Concentration: Application of Regression and Neural Network Model: submitted to Journal of the Air and Waste Management (2007).

DOI: 10.3155/1047-3289.57.4.480

[32] U. Gehring, J. Heinrich, U. Kramer, V. Grote, M. Hochadel, D. Sugiri, M. Kraft, K. Rauchfuss, H.G. Eberwein and H.E. Wichmann: submitted to Epidemiology (2006).

DOI: 10.1097/01.ede.0000224541.38258.87

[33] U. Schlink, O. Herbarth, M. Richter, S. Dorling, G. Nunnari, G. Cawley and E. Pelikan, Statistical Models to Assess the Health Effects and to Forecast Ground-Level Ozone: submitted to Environmental Modelling and Software (2006).

DOI: 10.1016/j.envsoft.2004.12.002