Prediction of Carbon Monoxide Concentration in Tehran using Artificial Neural Networks

Subject Areas : environmental management

Hamid Reza Jeddi ¹ , Rahim Ali Abbaspour ² , Mina Khalesian ³ , Seyed Kazem Alavipanah ⁴

1 - - MSc in GIS/RS, Department of GIS/RS, Faculty of Geography, University of Tehran, Tehran ,Iran.
2 - Assistant Professor, Faculty of Surveying and Geospatial information engineering, College of Engineering, University of Tehran, Tehran ,Iran.* (Corresponding Author)
3 - - PhD Faculty of Surveying and Geospatial Information Engineering, College of Engineering, University of Tehran, Tehran ,Iran.
4 - Professor Department of GIS/RS, Faculty of Geography, University of Tehran, Tehran , Iran.

Received: 2015-02-25 Accepted : 2015-12-28 Published : 2017-08-23

Keywords: Prediction of air pollution, Artificial Neural Network (ANN, Carbon Oxide (CO),

Abstract :

Background and Objective: Nowadays, air pollution is one of the most important problems almost all over the world. There are many strategies to control and reduce air pollution, one of which is prediction of this event and getting ready to deal with the negative effects of it. The aim of this study is to provide a multi-layer structure of artificial neural networks (ANN) for predicting of carbon monoxide pollution at subsequent 24 hours in Tehran metropolis. Method: To predict the amount of CO emissions in near future (subsequent 24 hours), wind speed and direction, temperature, relative humidity, and barometric pressure characteristics are used as meteorological data, and concentration of carbon monoxide is considered as a pollution parameter. To eliminate the noise of data, wavelets transform method and determining the threshold with normal distribution are used before training the ANN. Finally, two neural networks as two general models are proposed and used for modelling. Findings: The results show that the correlation coefficient, index of agreement, accuracy of prediction, and root mean square error for model no. 1 with duplicate data are 0.9012, 0.915, 0.848, and 0.1012 and for model no. 2 with duplicate data are 0.9572, 0.978, 0.963, and 0.0385 respectively. Moreover, the results of listed parameters for model no. 1 with new data are 0.9086, 0.89, 0.885, and 0.0825 and for model No. 2 with new data are 0.8678, 0.928, 0.932, and 0.1163 respectively. Conclusion: Results showed that there is a good agreement between predicted and observed values, hence the proposed models have a high potential for air pollution prediction.

References:

1-      اصیلیان. حسن، قانعیان. محمدتقی و غنی­زاده. قادر، 1386، آلودگی هوا، انتشارات میترا.

2-      Zannetti, p. 1990; Air pollution modeling, theories, computational methods and software’s, computational mechanics publication, WIT Press.

3-      Collett RS, Oduyemi K. 1997; Air quality modelling: a technical review of mathematical approaches. Meteorological Applications. 4(03):235-46.

4-      Sharma N, Chaudhry K, Rao CC. 2005; Vehicular pollution modeling using artificial neural network technique: A review. Journal of Scientific and Industrial research. 64(9):637.

5-      Ibarra-Berastegi G, Elias A, Barona A, Saenz J, Ezcurra A, de Argandoña JD. 2008; From diagnosis to prognosis for forecasting air pollution using neural networks: Air pollution monitoring in Bilbao. Environmental Modelling & Software. 23(5):622-37.

6-      Ul-Saufie AZ, Yahya AS, Ramli NA, Hamid HA. 2011; Comparison between multiple linear regression and feed forward back propagation neural network models for predicting PM10 concentration level based on gaseous and meteorological parameters. International Journal of Applied. 1(4).

7-      Tecer LA, 2007; Prediction of SO2 and PM Concentrations in a Coastal Mining Area (Zonguldak, Turkey) Using an Artificial Neural Network. Polish J. of Environ. Stud. 16(04): 633-638

8-   بوداقپور. سیامک،1390، پیش بینی میزان غلظت آلاینده­های هوای تهران با استفاده از شبکه عصبی­مصنوعی، علوم و تکنولوژی محیط زیست، دوره 13، صص 1-10.

9-      Nejadkoorki, F. and S. Baroutian, 2012. "Forecasting extreme PM10 concentrations using artificial neural networks." Int. J. Environ. Res 6(1): 277-284.

10- سبحانی اردکانی. س، اسماعیلی ساری. ع، چراغچی. م، طیبی. ل و قاسمرودی. م، 1386، تعیین کیفیت بهداشتی هوای تهران در سال 1383 با استفاده از شاخص کیفیت هوا ، علوم تکنولوژی و محیط­زیست­، شماره 4، صص 38-33.

11- صدر موسوی. میرستار، و رحیمی. اکبر، 1387، ارزیابی کاربرد شبکه‌های عصبی مصنوعی در پیش­بینی منوکسید کربن در هوای شهر تبریز، فصل‌نامه منابع طبیعی ایران ، سال شصت و یکم، شماره 3

12- سبحانی اردکانی. س و اسماعیلی ساری. ع، چراغچی. م، طیبی. ل و قاسمرودی. م، 1386، تعیین کیفیت بهداشتی هوای تهران در سال 1383 با استفاده از شاخص کیفیت هوا ، علوم تکنولوژی و محیط زیست، شماره 4، صص  38-33.

13- نظم آرا. ش، هاشم خانی. م، ذوقی. الف، 1386، بررسی وضعیت CO موجود در شهر تهران با استفاده از شاخص کیفیت هوا  (AQI)  دهمین همایش ملی بهداشت محیط ، دانشگاه علوم پزشکی همدان.

14-  اله حسینی، الف، هاشمی. ه و نیکروان، م، 1389، تحلیل و بررسی آماری داده‌های شاخص آلودگی هوای تهران از سال 1381 الی 1387، پنجمین کنگره ملی مهندسی عمران ، دانشگاه فردوسی، مشهد.

15-  منهاج. محمدباقر، 1384 ،مبانی شبکه های عصبی مصنوعی، انتشارات دانشگاه صنعتی امیر کبیر.

16-  Patterson, W. 1996; Artificial Neural Network: Theory and Applications, second edition, Prentice Hall Press.

17-  Shepherd, G.M, 1990, The synaptic organization of the brain, third edition, Oxford university press

18-  Fausett, Larson. 1994; Fundamental of neural network: architecture, algorithms, and applications, prentice Hall Press.

19-  Chelani, Asha B., Chalapati Rao, K.M. Phadke & M.Z. Hasan, 2002; Prediction of Sulphur dioxide concentration using artificial neural networks. Environmental Modelling & Software; 17: 161–168.

20-  شرعی پور. زهرا، 1389،بررسی غلظت آلاینده­های هوا و ارتباط آن با پارامترهای هواشناسی، چهاردهمین کنفرانس ژئوفیزیک ایران، ایران.

21-  Narasimhan, S.V., Nandini Basumallick, S. 2011, Introduction to Wavelet Transform: A Signal Processing Approach.