فصلنامه علمی- پژوهشی اطلاعات جغرافیایی « سپهر»

فصلنامه علمی- پژوهشی اطلاعات جغرافیایی « سپهر»

پیش بینی آلودگی هوای ناشی از حمل ونقل شهری کلانشهر تهران با بهره گیری از تلفیق GIS با مدلLUR وشبکه عصبی مصنوعی

نوع مقاله : مقاله پژوهشی

نویسنده
ناهید سجادیان
دانشیار جغرافیا و برنامهریزی شهری، دانشگاه شهید چمران اهواز
10.22131/sepehr.2015.15556
چکیده
تاکنون طرح‌هایی چند در جهت کاهش آلودگی هوای شهر تهران به مرحله اجراگذاشته شده است. اما مسئله این است که در کنار سایر کاستی‌ها، این طرح‌ها اغلب با تبعیت از مدیریت بحران به جای مدیریت ریسک،در واقع عکس‌العملی منفعلانه ومقطعی در مقابل افزایش آلودگی هوا بوده ودر تصمیمات مدیریتی مبتنی بر این طرح‌ها از سامانه پشتیبانی تصمیم‌گیری استفاده نشده است. لذا این پژوهش به سبب اهمیت موضوع با روشی تحلیلی-کاربردی وبا استفاده از داده‌های ساعتی، غلظت منوکسید کربن 12 ایستگاه از مجموعه ایستگاه‌های سنجش آلودگی هوا متعلق به شرکت کنترل کیفیت هوا وهمچنین داده‌های هواشناسی سرعت باد، جهت باد ودما مربوط به ایستگاه مهرآباد، همگی مربوط به سال1389، و داده‌های حجم همسنگ سواری معابر شهر تهران با هدف پیش‌بینی زمانی-مکانی آلودگی هوای ناشی از حمل ونقل شهری کلانشهر تهران در راستای کاربرد در سامانه پشتیبانی تصمیم‌گیری فضایی مدیریت کیفیت هوا و با هدف نهایی مدیریت بهینه حمل و نقل شهری کلانشهر تهران به تحقیق پرداخت. در این راستا، از آنجا که هدف غایی تحقیق حاضر، بهره‌گیری از نتایج آن در کنترل بهینه حمل و نقل شهری به عنوان منبع مهم آلاینده هوا است؛ از روش LUR برای سنجش شاخص منوکسید کربن در حمل و نقل کلانشهر تهران در کنار سایر آلاینده‌ها استفاده گردید.سپس از شبکه عصبی مصنوعی برای پیش‌بینی زمانی احتمال وقوع آلودگی هوا البته با تأکید بر مدیریت ریسک بهره گرفته شد؛ و سپس بر پایه پیش‌بینی‌های زمانی حاصل از شبکه عصبی مصنوعی، با استفاده از شاخص کریجینگ مناطقی که احتمال وقوع آلودگی هوا در آنها بالاست، شناسایی گردید. براساس یافته‌های تحقیق، نتایج مناسب تشخیص داده شد به گونه‌ای که می‌توان از این الگو در سامانه پشتیبانی مدیریت کیفیت هوا به هدف نهایی مدیریت بهینه حمل و نقل شهری کلانشهر تهران استفاده نمود.
کلیدواژه‌ها
آلودگی هوا
حمل ونقل شهری
شبکه عصبی مصنوعی
سامانه پشتیبانی تصمیم گیری فضایی
GIS
مدل LUR

عنوان مقاله English

Prediction of Air Pollution caused by Urban Transport in Tehran Metropolis using the Combination of GIS with LUR Model and Artificial Neural Network

نویسنده English

Nahid Sajadian
Associate Professore in geography and urban planning Shahid Chamran University
چکیده English

To date, a number of plans have been implemented to reduce air pollution in the city of Tehran.But the problem is that, along with other shortcomings,these planshave often been a passive and temporaryreaction to the increase of air pollution with adherence to crisis management rather than risk management, and no decision-making support system has been used in management decisions based on these plans.Therefore, due to the importance of the subject, this research was carried out by an analytical-applied method using hourly data, carbon monoxide density of 12 stations from a collection of air pollution measurement stations belonging to the air quality company, as well as meteorological dataof wind speed, wind direction and the temperature at the Mehrabad station, all related to the year 1389, and the number of the cars on the highways and streets of city of Tehran with the aim of predicting the temporal-spatial air pollution caused by the urban transport of Tehran Metropolis in line with the application of the spatial decision- making of the air quality management and with the ultimate goal of optimal management of urban transport of Tehran Metropolis. In this regard, since the ultimate goal of the present study is to use its results in controlling the optimal urban transportation as an important source of air pollutants, the LUR method was used to measure carbon monoxide index in the transportationof Tehran metropolis along with other pollutants. An artificial neural network was then used to predict the time of the possible occurrence of air pollution with emphasis on using risk management, and then, based on time predictions resulted from the artificial neural network, the regions with high possibility of air pollution occurrence were identified using the Kriging index.According to the findings of this research,the results were appropriate, so that this model could be used in the air quality management support system to reach the ultimate goal of optimal urban transport management in Tehran Metropolis.

کلیدواژه‌ها English

Air pollution
City transport
Artificial neural network
Spatial decision-making support system
GIS
LUR Model
  1. Aliyari sh, M., Teshnelab, M., Khaki Sedigh, A., (2008), Short Term prediction of air pollution using MLP,Gamma,ANFIS and Hybrid training based on PSO.Journal of Control,Vol.2,NO.1,fall 2008,pp.1-19.
  2. Athanasiadis, j.N.,et aL.,((2006)), classification techniques for air quality forecasting, Fifth ECAL workshop on Binding Environmental sciences and Artificial Intelligence, 17th European conference on Artificial Intelligence, Riva del Garda, Italy, August 2006
  3. Athanasiadis, N., Mitkas, p.A.,(2007), knowledge Discovery for operational Decision Support in Air Quality Management, journal of Environmental Informatics,(2)9,pp.100-107.
  4. Athansiadis,L.N., Mitkas, p.A.,(2004), Supporting the Decision-Making process in Environmental Monitoring systems with knowledge Discovery Techniques, knowledge Discovery for Environmental Management, 210-Bonn,Germany,KDnet, june 2004,pp.1-12.
  5. Aver kin AN, Agrafonova ‘I . Titova N. Synthesis of distributed furzy hierarchical model in decision support system in fuzzy cnvironrncw. In: Step nicka M, Bocictthofer U, Editors. New Dimensions in Fuzzy Logic and Related Technologies. Proceedings of the 5th EUSFLAT Conference, 2007 Sep 11-14; Ostrava, Czech Republic. p 377-9.
  6. Baralis E, Ceri S, Fratermtli P. Paraboschi S. Support environment for active rule design. Journal of Intelligent information System 1996:7(2)129-49.
  7. Bascom,R.,Bromberg ,P.A.,(1996),Health effect of outdoor air pollution,Am J Respir Care Med,153,pp.3-50
  8. Bodaghpour,S.,Charkhestani,A.,(2011),Prediction of Gas pollutant,s concentration by means of artificial neural network in Tehran urban air,Journal of Environmental Science and Technology,NO.13(1(48)),spring 2011,pp.1-10.
  9. Bomba D, L and T. The feasibility of implementing an electronic prescribing decision support system a case Study of an Australian public hospital. Aust Health Rev 2006; 30(3): 380-8.
  10. Boznar.M.,Lesiak.M.,Mlaker.P.,(1993).A neural network based method for shortterm predictions of ambient S02 concentrations in highly polluted industrial areas of complex terrain.Atmos.Environ.27B(2),pp.221-230.
  11. Brauer,M., et aL(2003), Estimating Long-term average particulate air pollution concentrations:application of traffic indicators and geographic information systems, EpidemioLogy,14(2),pp.228-239.
  12. Briggs, D. Exposure assessment. In:Elliot p., eakefieLd., Best N., and Briggs D.(Eds)., (2000).SpatiaL Epidemiology:Methods and Aplications,oxford university press.oxford, pp.335-359.
  13. Carnicro A. Group Decision Support System for Choosing Strategic Alternatives Journal of Management Decision 2001: 39(3): 218-26.
  14. Chelani.A.B et al.,(2002).Prediction of sulphur dioxide concentration using artificial neural networks, Environ. Modell. Softw.,17,161-168.
  15. Cheon,seong-pyo,kim.shin.,(2005),Directed knowLeadye DiscoVery Methodology for the pvediction of Ozone Concentvation Computer Science, VoLume 3, 13/2005,pp.772-781.
  16. Corani.G.,(2005),Air quality prediction in Milan feed-forward neural networks.pruned neural networks and lazy learning.Ecol.Model.,185,513-529.
  17. Dordowics.B et al.,(I 997),A neural network based model for the analysis of carbon monoxide voncentration in the urban area of Rosario.In:power.H.,Tirabasssis,T.,Brebbia.,C. A.(Eds).Air Pollution,Vol.V.Computational Mechanics Inc.,Southampton,Boston,677-685.
  18. Epley.R,Menon.M.,((2008)),A Method of Assembling Cross sectional Indicators into a community quality of life,Social Indicators Resarch,88.
  19. Galeotti,M.,((2007)),Economic growth and the quality of the Environment:Taking Stock,Environment Development and Sustainability,9,pp.427-454.
  20. Gardner.M.w.,Dorling.S.R.,(1998),Artificial neural networks (the multilayer perceptron)-a weview of applications in the atmospheric science, Atmos Environ.,32(14/15),2627-2636.
  21. GeLbert,N.L.,et aL((2005)),Assessing spatial Variability of ambient nitrogen dioxide in MotreaL, Canada, with a Land-use regression model.j.Air waste Manage. Assoc,5,pp.1059-1063.
  22. Henderson,S.H.,et aL.,((2007)),Application of Land use Regression to Estimate Long-Term Concentrations of Traffic-Related Nitrogen.
  23. Jaakkala,J.J.K et al.,(2001),Environmental tobacco smoke,parental autopsy,and childhood asthma,Environ Health Perspect,109,pp.82-579.
  24. jerrett,M., et aL(2001),A GIS-Environmental justice analysis of particulate air pollution in Hamilton, Canada, Environ plan A 2001a , 33, pp. 955-973.
  25. kanaroglou, P.,et aL.,(2003), Establishing an air pollution monitoring network for intra-urban population exposure assessment . Proceedings of the transport and air pollution,conference,Avigon,France,2003.
  26. Kashima,s., et aL.,(2009).,Application of Land use regression to regulatory air quality data in japan, science of the Total Environment,407,pp.3055-3062.
  27. Klasner,A.E., et al.,(1998),Carbon monoxide mass exposure in a pediatric population,Acad Emerg Med,5(10),pp.6-992.
  28. Kumar-Dey P. Decision support system for risk management: A Casestudy. Journal of manageme14.Carnicro A. Group Decision Support System for Choosing Strategic Alternatives Journal of Management Decision 2001: 39(3): 218-26.
  29. Lebert ,E., et aL.,(2000), small area Variations in ambient NO2 concentrations in four European areas, Atmos Environ,34,pp.177-185.
  30. Lee.Y.J.,(2008),Subjective quality of life measurement in Taipei,Building and Environment,43(7)25.
  31. Malczewski,J.,(1999),GIS Multicriteria Decision Analysis,John Wiley&Sons,Canada.
  32. Matkan,A.,et al.,(2009),Determination of spatial variation of CO and PM10 Air pollution,using GIS Techniques(case study:Tehran,Iran),Iranian Remote Sensing&GIS,Vol.1,NO.1,spring 2009,pp.57-72.
  33. Moore,D.k.,et aL.,(2007),A Land use regression model for predicting ambient fine pavticulate matter acvoss Los Angeles, CA, journal of Environmental Monitoving, 9,pp.246-256.
  34. Moseholm.L et al.,(1996).Forecasting carbon monoxide concentration near a sheltered intersections using video traffic surveillance and neural networks. Transport. Res., D1,15-28.
  35. Noori,R., et al.,((2009)),Comparison of ANN and PCA based multivariate linear Regression applied to predict the daily average concentration of CO:a case study of Tehran,Journal of the Earth and Space Physics,NO.34(1),pp.135-152.
  36. opera,M.M.,(2005), A case Study of knowledge modeling in an air pollution control decision support system, AL Communications, Volume 18,pp.293-303
  37. Oxides and Fine particulate matter, Environ.sci.TachnoL,41,2422-2428.     
  38. Pain D, Ficlden K, Shibl RA. Opinions on the Use of Clinical Decision Support Systems for Pediatric: Preseribing a New Zealand hospital. Logistic Information Management 20031: 2003:16(3):201-6.
  39. Poorazizi,M.E.,Alesheikh,A.A.,(2010),Introducing Interoperable Geospatial services to present and process sensor observation(case study:Tehran air quality sensors),Iranian Remote Sensing &GIS,Vol.2,NO.1,spring2010,pp.75-97.
  40. Ramani KV, A management information system to plan and monitor the delivery of delivery of health-case sevices in government hospitals in India. J HealthOrgan Manag 20-27: (2-3) 18,2004.
  41. Rao Mohan P. Expert systems application in Productivity Analysis Industrial Management 2004.104(9) 85.
  42. RosenLund,M.,et aL.,(2009),Comparison of regression models with Land-use and emission data to predict air pollution in Rome. J Expo Sci Environ Epidemiol 18,pp.9-192.
  43. Ross,Z.,et aL.,(2006),Nitrogen dioxide prediction in Southern California using Land use regression modeling: potential for environmental health analyses.j.Exposure AnaL,  Environ EpidemioL, 16(2), pp.106-114.
  44. Ross,z.,et aL.,(2007),A Land use regression for predicting fine particulate matter concentrations in the New york city region, Atmos Envivon, 41,pp.69-2255
  45. Ryan,p.H.,et aL.,(2007), A comparison of proximity and Land use regression traffic exposure models and wheezing in infants, Environ Health perspect, 115,pp.84-278.
  46. Sadr Mosavi,M.S.,Rahimi,A.,(2010),Comparison of the results of Multilayer perceptron neural networks and multiple linear regressions for prediction of ozone concentration in Tabriz city,Physical Geography Research Quarterly,NO.71,Spring 2010,pp.65-72.  
  47. Sahin.U et al.,(2005).,Modeling of S02 distribution in Istanbul using artificial neural networks, Environ. Model Assess., 10,135-142.
  48. Schwartz,J.,(1991),Particulate air pollution and daily mortality:a synthesis,Public Health Rew,19,pp.39-603
  49. Shad,R., et al.,(2009),Developing and Evaluation of an Agent-based GIS to Identify the Impacts of air pollution over the Environmental Risk Areas, Iranian Remote Sensing&GIS,Vol.1,NO.3,Autumn 2009,pp.1-15.
  50. Shi.J.P.,Harrison,R.M.,(1997),Regression modeling of hourly NOX and N02 concentration in urban air in London.,Atmos.Environ.Modell&Softw.,22,264-275.
  51. UN Human Settlement Program(2001),The State of worlds cities Report 2001,United Nations,New york.
  52. wheeler,A.j.,et aL.,(2008), Intra –urban Variability of air pollution in windsor, Ontario Measurement and Modeling for human exposure assessment, Environmental Research 106,pp.7-16.