Short-term prediction of atmospheric concentrations of ground-level ozone in Karaj using artificial neural network

Document Type : Original Research Paper

Authors

Department of Civil Engineering, Kharazmi University, Tehran, 43 Mofateh Ave, Iran

Abstract

Air pollution is a challenging issue in some of the large cities in developing countries. Air quality monitoring and interpretation of data are two important factors for air quality management in urban areas. Several methods exist to analyze air quality. Among them, we applied the dynamic neural network (TDNN) and Radial Basis Function (RBF) methods to predict the concentrations of ground-level ozone in Karaj City in Iran. Input data included humidity, hour temperature, wind speed, wind direction, PM2.5, PM10 and benzene, which were monitored in 2014. The coefficient of determination between the observed and predicted data was 0.955 and 0.999 for the TDNN and RBF, respectively. The Index of Agreement (IA) between the observed and predicted data was 0.921 for TDNN and 0.9998 for RBF. Both methods determined reliable results. However, the RBF neural network performance had better results than the TDNN neural network. The sensitivity analysis related to the TDNN neural network indicated that the PM2.5 had the greatest and benzene had the minimum effect on prediction of ground-level ozone concentration in comparison with other parameters in the study area. 

Keywords

References

Abbaspour Sani, K.F., Arahmandpour, B. and Hajazi, G. (2007). Determining a base year of sun radiation using 12 year Karaj sun radiation: material and energy research center, a project research.
Azid, A., Juahir, H., Toriman, M.E., Kamarudin, M.K.A., Saudi, A.S.M. CheHasnam, C.N., Abdul Aziz, N.A., Azaman, F., Latif, M.T. et al. (2014). Prediction of the Level of Air Pollution Using Principal Component Analysis and Artificial Neural Network Techniques: a Case  study in Malaysia, water ,air &soil pollut., 225(2063), 2-14.

 

Biancofiore, F., Verdecchia, M., Di Carlo, Tomassetti, B., Aruffo, E., Busilacchio, M., Bianco, S. Di Tommaso, S. and Colangelic, C. (2015). Analysis of surface ozone using a recurrent neural network, Sci.of total environ., 514, 379-3870.
Bonasoni, P., Evangelisti, F., Bonafe, U., Ravegnani, F., Calzolari, F., Stohl, A. and Colombo, T. (2000). Stratospheric ozone intrusion episodes recorded at Mt. Cimone during the VOTALP project: case studies, Atmos. Environ. J., 34 (9), 1355-1365.
Chiarelli, P.S., Pereira, L.A.A., Saldiva, P.H., D.N., Filho, C.F., Garcia, M.L.B., Braga, A.L.F. and Martins, L.C. (2011). The association between air pollution and blood pressure in traffic controllers in Santo André, São Paulo, Brazil, Enviro. Res., 111(5), 650-655.
Comrie, A.C. (1997). Comparing neural networks and regression models for ozone forecasting: J. of the Air & Waste Manag. Associ., 47(6), 653-663.
Gasana, J., Dillikar, D., Mendy, A., Forno, E. and Ramos Vieira, E. (2012). Motor vehicle air pollution and asthma in children: A meta-analysis, Environ. Res., 117, 36-45.
Heckman, J.J. (1979). Sample selection bias as a specification error,Econometrica: J.of the Econom. Soci.,153-161.
Hooti, A. (2006). Assessment of liquefaction potential using artificial neural network: according to cone penetration factor and speed of shear wave, MSc thesis, Khrazmi University.
Hrust, L., Klaić, Z.B., Križan, J., Antonić, O., and Hercog, P. (2009). Neural network forecasting of air pollutant hourly concentrations using optimized temporal averages of meteorological variables and pollutant concentrations: Atmos. Environ. J., 43(35), 5588-5596.
Lu, H.C., Hsieh, J.C. and Chang, T.S. (2006). Prediction of daily maximum ozone concentrations from meteorological conditions using a two-stage neural network: Atmo. Res., 81(2), 124-139.
Luna, A.S., Paredes, M.L.L., de Olivera, G.C.G. and Correa, S.M. (2014). Prediction of ozone concentration in tropospheric levels using artificial neural networks and support vector machine at Rio de Janeiro,Brazil, Atmos. Environ. J., 98, 98-104.
Lu, W.Z. and Wang, D. (2014). learning machine: rational and application in ground-level ozone, App. soft comput., 24,135-141.
Menhaj, M. (1998). Computational Intelligence, Fundamentals ofArtificial Neural Networks. Vol. 1, Amirkabir University publisher (In Persian).
Moazami, S., Noori, R., Jabbarian Amiri, B., Yeganeh, B., Partani, S. and Safavi, S. (2016). Developed support vector machine, Atmos. pollut. Res., 73(3), 412-418.
Neville, A.M., and Kennedy, J.B. (1964). Basic statistical methods for engineers and scientists (International Textbook).
Nejadkoorki, F. and Baroutian, S. (2011). Forecasting Extreme PM10 concentrations using artificial neural network, 6(1), 227-284.
Nouri, R.E., Ashrafi, Kh. and Azhdarpour, A.A.F. (2008). Comparison of ANN and PCA based multivariate regression applied to predict the daily average concentration of carbon monoxide: a case study of Tehran, J. of the earth and space phys., 34(1), 135-152.
Noori, R., Hoshyaripour, G., Afshari, K. and Rasti, O.(2013). Introducing an Appropriate Model using Support Vector Machine for Predicting Carbon Monoxide Daily Concentration in Tehran Atmosphere, Irani. J. Health & Environ, 6(1), 1-10.
Noori, R., Hoshyaripour, G., Ashrafi, K. and Nadjar Araabi, B. (2010). Uncertainty analysis of developed ANN and ANFIS models in prediction of carbon monoxide daily concentration, Atmos. Environ. J., 44(4), 476-482.
Norooz Velashadi, R., Ghahreman, N. and Irannejad, P. (2012). Simulation model to determine humidity and temperature of soil covered by corn plant and soil without covering, Water & Soil J., 26 (1), 55-65.
Paoli, C., Notton, G., Nivet, M.L., Padovani, M. and Savelli, J.L. (2011). A neural network model forecasting for prediction of hourly ozone concentration in Corsica: In Environment and Electrical Engineering (EEEIC), 10th International Conference on (pp. 1-4). May, IEEE.
Pastor-Bárcenas, O., Soria-Olivas, E., Martín-Guerrero, J.D., Camps-Valls, G., Carrasco-Rodríguez, J.L. and Del Valle-Tascón, S. (2005). Unbiased sensitivity analysis and pruning techniques in neural networks for surface ozone modelling: Ecological Modelling, 182 (2), 149-158.
Razavi, F. (2006). Rain Predicting using artificial neural network, M.S thesis. Amir Kabir Univ, Tehran. Iran.
Reddy, B.S.K., Kumar, K.R., Balakrishnaiah, G., Gopal, K.R., Reddy, R.R. Ahammed, Y. N., Lal, S. (2010). Observational studies on the variations in surface ozone concentration at Anantapur in southern India. Atmos.Res., 98 (1), 125-139.
Ribas, A. and Peñuelas, J. (2004).Temporal patterns of surface ozone levels in different habitats of the North Western Mediterranean basin, Atmos. Environ. J., 38, 985-992.
Seghataleslami, N., Mousavi, S.M. and Alami, M. (2006). Modeling and predicting of ozone concentration in air of Mashadusing artificial neural network: ANFIS,11th national conference of Iranian Chem. Eng., Autumn, Iran.
Sergio, C.P., Amador Pereira, L.A., NascimentoSaldiva, P.H.D., Ferreira Filho, C., Bueno Garcia, M.L., Ferreira Braga, A.L. and Conceição Martins, L. (2011). The association between air pollution and blood pressure in traffic controllers in Santo André: São Paulo, Brazil, Environ. Res., 111, 650-655.
Yeganeh, B., Shafie Pour Motlagh, M., Rshidi, Y. and Kamalan, H. (2012) Prediction of CO concentrations based on a hybrid Partial Least Square and Support Vector Machine model, Atmos. Environ. J. 55,357-365.
Pollution
Volume 2, Issue 4
October 2016
Pages 475-488

Files

Share

How to cite

Statistics