ارزیابی کارایی برخی روش‌های هوش مصنوعی در مدل‌سازی فرسایش‌پذیری بادی خاک در بخشی از اراضی شرق دریاچه ارومیه

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشجوی دکترا گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه تبریز، تبریز

2 عضو هیات علمی گروه علوم خاک دانشکده کشاورزی دانشگاه تبریز

3 استاد گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه تبریز، تبریز

4 استاد گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز، تبریز

5 دانشیار گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه ارومیه

چکیده

پیش­بینی فرسایش­پذیری بادی از طریق ویژگی­های خاک به عنوان گامی اساسی در مدل­سازی فرسایش بادی محسوب می‌شود. این پژوهش با هدف مقایسه کارایی چهار روش مختلف شامل رگرسیون خطی چندمتغیره، شبکه عصبی مصنوعی، شبکه عصبی مصنوعی هیبریدشده با الگوریتم ژنتیک و شبکه عصبی هیبریدشده با الگوریتم بهینه‌سازی وال در مدل‌سازی فرسایش‌پذیری بادی در بخشی از اراضی پیرامون شرقی دریاچه ارومیه انجام شد. برای این منظور، 96 نمونه خاک به روش تصادفی نظارت شده جمع­آوری و 32 ویژگی مختلف فیزیکی و شیمیایی آن­ها در آزمایشگاه تعیین شدند. همچنین فرسایش‌پذیری بادی نمونه­ها نیز با استفاده از تونل باد تعیین گردید. از میان ویژگی­های خاک، چهار ویژگی شامل فراوانی ذرات ثانویه 1/0 تا 25/0 میلی‌متری، فراوانی ذرات ثانویه  7/1 تا 2 میلی‌متری، فراوانی ذرات شن ریز و محتوای کربن آلی از طریق رگرسیون گام به گام به عنوان ورودی مدل­های پیش­بینی فرسایش‌پذیری، انتخاب شدند. نتایج نشان داد که مدل شبکه عصبی هیبریدشده با الگوریتم بهینه‌سازی وال با توجه به کمترین مقادیر میانگین خطا (11/0-) و جذر میانگین مربعات خطا (9/2) و بیشترین مقادیر ضریب تبیین (87/0) و ضریب کارایی نش-ساتکلیف (87/0) از کارایی مطلوب‌تری در پیش‌بینی فرسایش­پذیری بادی خاک­های منطقه برخوردار است و پس از آن روش‌های شبکه عصبی مصنوعی هیبرید شده با الگوریتم ژنتیک، شبکه عصبی مصنوعی و رگرسیون خطی چندمتغیره به ترتیب در رتبه‌های بعدی قرار داشتند. در مجموع با توجه به کارایی قابل قبول مدل شبکه عصبی هیبریدشده با الگوریتم بهینه‌سازی وال در پیش‌بینی فرسایش‌پذیری بادی، استفاده از این روش برای تعیین سریع و دقیق فرسایش­پذیری خاک‌های منطقه توصیه می­شود.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Evaluating Efficiency of Some Artificial Intelligence Techniques for Modeling Soil Wind Erodibility in Part of Eastern Land of Urmia Lake

نویسندگان [English]

  • bijan raei 1
  • Abbas Ahmadi 2
  • Mohammad Rza Neyshaburi 3
  • Mohammad Ali Ghorbani 4
  • Farokh Asadzadeh 5
1 PhD Student, Department of Soil Science, faculty of agriculture, University of Tabriz, Tabriz, Iran
2 Assistant Professor, Department of Soil Science, faculty of agriculture, University of Tabriz, Tabriz, Iran.
3 Professor, Department of Soil Science, faculty of agriculture, University of Tabriz, Tabriz, Iran.
4 Professor, Department of Water Engineering, faculty of agriculture, University of Tabriz, Tabriz, Iran
5 Associate Professor, Department of Soil Science, faculty of agriculture, Urmia University, Urmia, Iran
چکیده [English]

Prediction of soil wind erodibility through soil characteristics is an important aspect for modeling soil wind erosion. This study was conducted to compare the efficiency of multiple linear regression (MLR), artificial neural network (MLP), artificial neural network based on genetic algorithm (MLP-GA) and artificial neural network based on whale optimization algorithm (MLP-WOA) for prediction of soil wind erodibility in part of eastern land of Urmia Lake. In this research, 96 soil samples were collected based on a stratified random sampling method and their physicochemical properties were measured. Additionally, the wind erodibility of soil samples was measured using a wind tunnel. Among the 32 measured soil properties, four properties including the percentages of fine sand, size classes of 1.7-2.0, and 0.1-0.25 mm (secondary particles) and organic carbon were selected as the model inputs by stepwise regression. Result showed that the MLP-WOA was the most effective method for predicting soil wind erodibility in the study area regarding to the lowest RMSE (2.9) and ME (-0.11), and the highest R2 (0.87) and NSE (0.87) values; followed by MLP-GA, MLP, and MLR. Considering the high efficiency of MLP-WOA, This method can be used as a promising method for determination of soil wind erodibility in the study area.

کلیدواژه‌ها [English]

  • "Artificial Neural Network
  • Genetic Algorithm
  • Whale Optimization Algorithm
  • Wind Erosion
  • Wind Tunnel"
Abbasi, Y., Ghanbarian-Alavijeh, B., Liaghat, A. and Shorafa, M. (2011). Evaluation of pedotransfer functions for estimating soil water retention curve of saline and saline-alkali soils of Iran. Pedosphere 21 (2), 230–237.
Aljarah, I., Faris, H. and Mirjalili, S. (2016). Optimizing connection weights in neural networks using the whale optimization algorithm. Soft Computing, 22 (1), 1-15.
Barzegar, R., Asghari Moghadam, A. and baghban, H. (2015). A supervised committee machine artifical intelligent for improving DRASTIC method to assess groundwater contamination risk: a case study from tabriz plain aquifer, iran. Stoch Environ Res Risk Assess, 30(3), 883–899.
Chebud, Y., Naja, G.M., Rivero, R.G. and Melesse, A.M. (2012). Water quality monitoring using remote sensing and artificial neural network. Water Air Soil Pollut, 223, 4875–4887.
Cook, D.F., Ragsdale, C.T. and Major, R.L. (2000). Combining a neural network with a genetic algorithm for process parameter optimization. Engineering Applications of Artificial Intelligence 13: 391-396.
Dastranj, H., Tavakoli, F. and  Soltanpour, A. (2018). Investigating the water level and volume variations of Lake Urmia using satellite images and satellite altimetry. Scientific - Research Quarterly of Geographical Data 27(107), 149-163. (In Farsi).
De-Gennaro, G., Trizio, L., DiGilio, A., Pey, J., Pérez,  N., Cusack, M., Alastuey, A. and Querol, X. (2013). Neural network model for the prediction of PM10 daily concentrations in two sites in the Western Mediterranean. Science of the Total Environment, 463–464, 875–883.
Fallah-Mehdipour, E., Bozorg Haddad, O. and Marino, M.A. (2013). Prediction and simulation of monthly groundwater levels by genetic programming. Journal of Hydro-environment Research, 7, 253-260.
Galletly, J.E. (1992). An overview of genetic algorithms. Kybernetes 21(6): 26-30.
Garcia, M. and Arguello, C. (2005). A hybrid approach based on neural networks and genetic algorithms to study the profitability in the Spanish stock market. Applied Econnomics Letters, 12, 303–308.
Gee, G.W. and Or, D. (2002). Particle size analysis. In: Dane J.H., G.C.Topp, editors. Methods of soil analysis. Part 4. Physical methods. Soil Science Society of America. Madison (WI), p. 255–293.
Haghverdi A., Ghahraman, B., Joleini, M., Khoshnud A., Yazdi, A. and Arabi, Z. (2011). Comparison of different Artificial Intelligence methods in modeling water retention curve (Case study: North and Northeast of Iran). J. of Water and Soil Conservation, 18(2), 65-84. In Farsi
Hamm, L., Brorsen, B.W. and Hagan, M.T. (2007). Comparison of stochastic global optimization methods to estimate neural network weights. Neural Process Lett, 26, 145–58.
Hashimoto, Y. (1997). Applications of artificial neural networks and genetic algorithms to agricultural system. Computers and Electronics in Agriculture 18:71- 72.
Holland, J.H. (1992). Genetic Algorithms. Scientific American, 267(1), 66-72.
Jain, A. and Srinivasulu, S. (2004). Development of effective and efficient rainfall-runoff models using integration of deterministic, real-coded genetic algorithms and artificial neural network techniques. Water and resource research, 40(4), W04302.
Jamalizadeh Tajabadi, M.R., Moghadam Nia, A.R., Piri, J. and Ekhtesasi, M.R. (2010). Application of artificial neural networks in dust storm prediction (case study: Zabol city). Iranian Journal of Rangeland and Desert Research 17 (2): 205-220. (In Farsi)
Kantardzic, M. (2011). Data Mining: concepts, models, methods, and algorithms. John Wiley & Sons. Alberta, Canada. pp 529.
Kaunda, R.B. (2015). A neural network assessment tool for estimating the potential for backward erosion in internal erosion studies. Computers and Geotechnics, 69, 1–6.
Kaveh, A., Ghazaan,  M.I. (2017). Enhanced whale optimization algorithm for sizing op- timization of skeletal structures, Mech. Based Des. Struct. Mach, 45(3), 345–362.
Kemper, W.D. and Rosenau, R.C. (1986). Aggregate stability and size distribution. In: Klute A,editor, Methods of Soil Analysis. ASA and SSSA, Madison (WI), p. 425–442.
Keshavarzi, A. and Sarmadian, F. (2010). Comparison of artificial neural network andmultivariate regression methods in prediction of soil cation exchange capacity. Int. J. Environ. Chem. Ecol. Geo GeoEng. 4(12): 644–649.
Kim,  R.J., Loucks, D.P. and Stedinger, J.R. (2012). Artificial neural network models of watershed nutrient loading. Water Resour. Manage, 26, 2781–2797.
Ladumor, D.P., Jangir, p., Trivedi, P.N. and Kumar, A. (2016). A whale optimization algorithm approach for unit com- mitment problem solution, in: Proceeding of the 2016 National Conference on Advancements in Electrical and Power Electronics Engineering (AEPEE-2016), Morbi.
Liu, L.Y., Li, X.L., Shi, P.J., Gao, S.Y., Wang, J.H., Ta, W.Q., Song, Y., Liu, M.X., Wang, Z. and Xiao, B.L. (2007). Wind erodibility of major soils in the farming-pastoral ecotone of China. Journal of Arid Environments, 68, 611-623.
Lopez, M.V., de Dios Herrero, J.M., Hevia, G.G., Gracia, R. and Buschiazzo, D.E. (2007). Determination of the wind-erodible fraction of soils using different methodologies. Geoderma, 139, 407–411.
Mafarja, M. and  Mirjalili, S.  (2017). Hybrid Whale Optimization Algorithm with simulated annealing for feature selection. Neurocomputing, 260, 302–312.
Mafarja, M. and Mirjalili, S. (2018). whale optimization approaches for wrapper feature selection. Applied Soft Computing, 62, 441–453.
Menhaj, M.B. (2018). Fundamental of neural network (Computational intelligence). Amirkabir University of Technology Press, Tehran, Iran. pp 716. (In Farsi)
Mirjalili, S. and Lewis, A. (2016) The whale optimization algorithm. Adv Eng Softw 95:51–67.
Nazghelichi, T., Aghbashlo, M. and Kianmehr, M.H. (2011). Optimization of an artificial neural network topology using coupled response surface methodology and genetic algorithm for fluidized bed drying. Computers and Electronics in Agriculture, 75, 84–91.
Nelson, D.W. and Sommers, L.E. (1982). Total carbon, organic carbon, and organic matter. Pp. 539–579. In: Page AL, Miller RH and Keeney DR (eds). Methods of Soil Analysis, part 2. ASA and SSSA, Medison, Wisconsin.
Nelson, R.E. (1982). Carbonate and Gypsum. P. 181- 197. In Page, A. L. (ed.). Methods of Soil Analysis. Part 2. (2nd ed.). Agron. Mongor. 9. ASA and SSSA, Madison, WI.
Nimmo, J.R. and Perkins, K.S. (2002). Aggregate stability and size distribution. In: Dane, J.H., Topp, G.C. (Eds.), Methods of Soil Analysis. Part 4. Physical Methods. Soil Science Society of America, Inc., Madison, WI, pp. 317–328.
Ostovari, Y., Ghorbani-Dashtaki, S., Bahrami, H.A., Naderi, M., Dematte, J.A.M. and Kerry, R. (2016). Modification of the USLE K factor for soil erodibility assessment on calcareous soils in Iran. Geomorphology, 273, 385–395.