ارزیابی تکنیک‌های هوش محاسباتی در پیش‌بینی سرانه تولید پسماند (مطالعه موردی: استان هرمزگان)

نوع مقاله : مقاله کامل پژوهشی

نویسندگان

1 دانشکده‌ مهندسی، دانشگاه شیراز

2 رییس مرکز محیط زیست و توسعه پایدار دانشگاه شیراز

10.22034/ceej.2018.7584

چکیده

شناخت کمیت پسماندهای یک شهر یا منطقه، لازمه برنامه­ریزی در زمینه مدیریت پسماند است. روش دستیابی به کمیت پسماندها دانستن سرانه یا نرخ تولید آن است. در خصوص پیش­بینی مقادیر سرانه تولید پسماند تا کنون در اکثر مدل­های تدوین شده از داده­های سری زمانی مربوط به منطقه مورد مطالعه استفاده شده است. اما در شرایطی که چنین داده­هایی موجود نباشد استفاده از سیستم­های هوشمند پیش­بینی نظیر تکنیک­های یادگیری ماشین که بر اساس داده­های اندازه­گیری شده در یک سال تدوین شوند، بسیار ﻣﺆثر خواهند بود. از آنجا که داده­های زمان­مندی جهت مقادیر سرانه تولید پسماند مناطق جمعیتی ساحلی جنوب ایران جهت طراحی اصولی سیستم مدیریت پسماند وجود نداشته است، در این مطالعه با در نظر گرفتن پارامترهای ارتفاع از سطح دریا، جمعیت، درجه شهری و تناوب جمع­آوری پسماند، توانایی روش­های هوشمند MLP، SVM و M5P در پیش­بینی سرانه تولید پسماند شهرها و روستاهای ساحلی استان هرمزگان بکار گرفته شده و با هم مقایسه شده است. نتایج حاصله نشان دهنده این است که روش M5P با مقدار مجذور میانگین مربعات خطا (RMSE) (gr/d) 34/55 و میانگین قدر مطلق خطای نسبی (MARE) 26/6 درصد، بهترین عملکرد را نسبت به سایر روش­ها دارد.

کلیدواژه‌ها


عنوان مقاله [English]

Performance Assessment of Computational Intelligence Techniques in Solid Waste Generation Forecasting (A Case Study)

نویسندگان [English]

  • Mohammad Minousepehr 1
  • Mohammad Reza Alizadeh 1
  • Nasser Talebbeydokhti 2
1 Environmental Engineering, Shiraz University
2 Department of Civil and Environmental Engineering, Shiraz University
چکیده [English]

Knowing the quantity of generated solid waste play a very significant role in solid waste management programs in a region. Due to lack of measured data as well as unavoidable errors in measurements, assessment of volume of generated solid waste is always challenging. Also, field measurement and continues monitoring of the volume of solid waste is usually costly, difficult and time-consuming. Accurate prediction of solid waste generation can be regarded as a key factor in future solid waste management system planning. Conventional forecasting methods in solid waste generation forecasting frequently use the demographic and socioeconomic factors in a per capita basis. In most cases, insufficient funds, the limited measuring equipment, lack of appropriate management systems and due to the lack of recorded data for the volume of generated solid waste cause many problems in integrated solid waste systems management (Dyson and Chang, 2005). In this study, three computational intelligence techniques including M5P model trees, support vector machines (SVM) and multi-layer perceptron (MLP) artificial neural network are utilized to predict solid waste generation in Hormozgan Province, Iran. After a sensitivity analysis, four more influential factors including elevation, population, urban development index (measures the level of development in cities based on infrastructure, the municipality established year, the metropolitan area, population, city product and income, health and education) and the frequency of garbage collection were considered in developing models. The performance of proposed models in solid waste generation forecasting are assessed via different error evaluation indices and finally the results are compared.

کلیدواژه‌ها [English]

  • Solid waste Generation forecasting
  • Multi-layer perceptron
  • Support vector machines
  • M5P model trees
Abbasi M, Abdoli MA, Omidvar, B., Baghvand, A., “Forecasting Municipal Solid Waste Generation by Hybrid Support Vector Machine and Partial Least Square Model”, International Journal of Environmental Research, winter 2013, Volume 7, Issue 1, 27-38.
Abdoli MA, Falah Nezhad M, Salehi Sede R, Behboudian S, “Long term Forecasting of Solid Waste Generation by the Artificial Neural Networks”, Environmental Progress & Sustainable Energy, December 2012, Volume 31, Issue 4, 628-636.
Antanasijević D, Pocajt V, Popović I, Redžić N, Ristić M, “The forecasting of municipal waste generation using artificial neural networks and sustainability indicators”, Sustainability Science, January 2013, Volume 8, Issue 1, 37-46.
Avci E, “Selecting of the optimal feature subset and kernel parameters in digital modulation classification by using hybrid genetic algorithm-support vector machines: HGASVM”, Expert Systems with Applications, March 2009, Volume 36, Issue 2, Part 1, 1391-1402.
Bach H, Mild A, Natter M, Weber A, “Combining Socio-demographic and logistic factors to explain the generation and collection of waste paper”, Resources, Conservation and Recycling, April 2004, Volume 41, Issue 1, 65-73.
Batinić B, Vukmirović S, Vujić G, Stanisavljević N, Ubavin D, Vukmirović G, “Using ANN model to determine future waste characteristics in order to achieve specific waste management targets -case study of Serbia”, Journal of Scientific and Industrial Research (JSIR), July 2011, 70(07), 513-518.
Bayar S, Demir I, Engin GO, “Modeling leaching behavior of solidified wastes using back-propagation neural networks”, Ecotoxicology and Environmental Safety, 2009, 72 (3), 843-850.
Bogner J, Matthews E, “Global methane emissions from landfills: new methodology and annual estimates 1980-1996”, Global Biogeochemical Cycles, June 2003, 17, NO. 2, 1-18.
Chang N B, Lin Y T, “An analysis of recycling impacts on solid waste generation by time series intervention modeling”, Resources, Conservation and Recycling, March 1997, Volume 19, Issue 3, 165-186.
Chen HW, Chang N B, “Prediction analysis of solid waste generation based on grey fuzzy dynamic modeling”, Resources, Conservation and Recycling, May 2000, Volume 29, Issues 1-2, 1-18.
Daskalopoulos E, Badr O, Probert SD, “Municipal solid waste: a prediction methodology for the generation rate and composition in the European Union countries and the United States of America”, Resources, Conservation and Recycling, November 1998, Volume 24, Issue 2, 155-166.
Dong C, Jin B, Li D, “Predicting the heating value of MSW with a feed forward neural network”, Waste Management, 2003, Volume 23, Issue 2, 103-106.
Dyson B, Chang NB, “Forecasting Municipal Solid Waste Generation in a Fast-Growing Urban Region with System Dynamics Modeling”, Waste Management, 2005, Volume 25, Issue 7, 669-679.
Hockett D, Lober DJ, Pilgrim K, “Determinants of per capita municipal solid waste generation in the Southeastern United States”, Journal of Environmental Management, November 1995, Volume 45, Issue 3, 205-217.
Jahandideh S, Asadabadi E, Askarian V, Movahedi MM, Hosseini S, Jahandideh M, “The use of artificial neural networks and multiple linear regression to predict rate of medical waste generation”, Waste Management, November 2009, Volume 29, Issue 11, 2874-2879.
Jenkins R R, “The Economics of Solid Waste Reduction: The Impact of User Fees (New Horizons in Environmental Economics)”, Elgar, Edward Publishing, Inc, 1 edition, 1993.
Kalogirou SA, “Artificial intelligence for the modeling and control of combustion processes: a review”, Progress in Energy and Combustion Science, 2003, Volume 29, Issue 6, 515-566.
Karaca F, Ozkaya B, “NN-LEAP: A neural network-based model for controlling leachate flow-rate in a municipal solid waste landfill site”, Environmental Modeling & Software, August 2006, Volume 21, Issue 8, 1190-1197.
Karavezyris V, Timpe KP, Marzi R, “Application of system dynamics and fuzzy logic to forecasting of municipal solid waste”, Mathematics and Computers in Simulation, September 2002, Volume 60, Issues 3-5, 149-158.
Mingers J, “An Empirical Comparison of Pruning Methods for Decision Tree Induction”, Machine Learning, 1989, 4(2), 227-243.
Navarro-Esbrí J, Diamadopoulos E, Ginestar D, “Time series analysis and forecasting techniques for municipal solid waste management”, Resources, Conservation and Recycling, May 2002, Volume 35, Issue 3, 201-214.
Noori R, Abdoli MA, Jalili Ghazizade M, Samieifard R, “Comparison of neural network and principal component-regression analysis to predict the solid waste generation in Tehran”, Iranian Journal of Public Health, 2009, Volume 38, Issue 1, 74-84.
Noori R, Karbassi A, Sabahi MS, “Evaluation of PCA and Gamma test techniques on ANN operation for weekly solid waste prediction”, Journal of Environmental Management, January-February 2010, Volume 91, Issue 3, 767-771.
Quinlan JR, “Learning with continuous classes”, in Proceedings, AI’92, 5th Australian Joint Conference on Artificial. Intelligence, Adams & Sterling (eds.), World Scientific, Singapore, 1992, 343-348.
Tchobanoglous G, Theisen H, Vigil SA, “Integrated Solid Waste Management: Engineering Principles and Management Issues”, New York: McGraw–Hill Book Co., Inc, 1993.
Vapnik V, “The Nature of Statistical Learning Theory (Information Science and Statistics)”, New York, NY: Springer-Verlag, 1 edition, January 1995.
Wang Y, Witten I, “Inducing model trees for continuous classes”, In Proceedings of the 9th European Conference on Machine Learning Poster Papers, Prague, 1997, 128-137.
Wanmg CM, Huang, Y. F., “Evolutionary- based feature selection approaches with new criteria for data mining: A case study of credit approval data”, Expert Systems with Applications, April 2009, Volume 36, Issue 3, Part 2, 5900-5908.
مینوسپهر م، ”مطالعات طرح جامع مدیریت پسماند شهرها و روستاهای ساحلی استان هرمزگان“، مهندسین مشاور عمران محیط­زیست شهر سبز پارسیان، استانداری هرمزگان، 1394-1391 .