برآورد سرعت نفوذ نهایی خاک با استفاده از الگوریتم خوشه‌بندی فازی، روش نرو-فازی (ANFIS) و نظام استنتاج فازی (FIS)

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری

2 دانشیار دانشکده منابع طبیعی دانشگاه علوم کشاورزی و منابع طبیعی ساری

3 فارغ التحصیل کارشناسی ارشد آبخیزداری، دانشکده منابع طبیعی دانشگاه علوم کشاورزی و منابع طبیعی ساری

چکیده

نفوذ در هیدرولوژی سطحی و زیر سطحی نقش مهمی ایفا کرده و عامل کلیدی در معادلات بارش و رواناب است. استفاده از روش‌هایی که محدودیت‌های روش‌های تئوری و تجربی متداول تعیین روابط نفوذ را نداشته باشد، لزوم انجام آزمایش‌های پرهزینه و زمان‌بر تعیین مقادیر نفوذپذیری را به حداقل رسانده و تخمین مقادیر کاربردی آن را ممکن خواهد ساخت. در همین راستا در این تحقیق، میزان نفوذپذیری خاک در دشت ساحلی بهشهر-گلوگاه واقع در استان مازندران با استفاده از روش فازی، الگوریتم خوشه‌بندی فازی و همچنین شبکه عصبی-فازی انطباقی (نرو-فازی) برآورد گردید به‌طوری‌که درصد رطوبت وزنی پیشین خاک، درصد مواد آلی خاک و درصد آهک خاک به عنوان پارامترهای ورودی و سرعت نفوذ نهایی خاک به عنوان پارامتر خروجی مدل‌ها در نظر گرفته شدند و نتایج به­دست آمده از این سه روش با مقادیر مشاهده‌ای نفوذ نهایی به روش تک‌ استوانه مورد مقایسه قرار گرفت. بر اساس نتایج به­دست آمده، روش نرو-فازی با میانگین انحراف 0042/0سانتی‌متر در دقیقه، میانگین اختلاف 67/0 سانتی‌متر در دقیقه، ریشه­ میانگین مربعات خطای 21/1 سانتی‌متر در دقیقه و ضریب همبستگی 92/0 بهترین عملکرد را در تخمین سرعت نفوذ نهایی خاک در بین مدلهای مورد مطالعه نشان داد، در‌‌ حالی‌که الگوریتم خوشه­بندی فازی با میانگین انحراف 0075/0، میانگین اختلاف 12/2، ریشه­ میانگین مربعات خطای 02/2 و ضریب همبستگی 88/0 و سیستم استنتاج فازی با میانگین انحراف 016/0، میانگین اختلاف50/2، ریشه­ میانگین مربعات خطای 45/2 و ضریب همبستگی 82/0 به ترتیب در رتبه‌های بعد قرار گرفتند. همچنین بیشترین همبستگی میان مقادیر مشاهده‌ای و برآورد شده در مدل نرو-فازی (85/0=R2) مشاهده گردید و پس از آن، مدل‌های الگوریتم خوشه‌بندی فازی (77/0=R2) و سیستم استنتاج فازی (66/0=R2) قرار گرفتند. در پایان این تحقیق پیشنهاد گردیده است تا با تهیه داده­های بیشتر از مشخصات فیزیکی و شیمیایی خاک‌ها و مقادیر نفوذپذیری محدوده مطالعات زمینه تخمین و مقایسه دقیق‌تر مدل‌های مورد مطالعه فراهم گردد.

کلیدواژه‌ها


عنوان مقاله [English]

Estimation of Final Soil Infiltration Rate Using Fuzzy Clustering Algorithm, Nero Fuzzy (ANFIS) and Fuzzy Inference System (FIS) (A Case Study: Behshahr Plain, Galougah, Mazandaran, Iran)

نویسندگان [English]

  • Iman Saleh 1
  • Ataollah Kavian 2
  • Zeynab Jafarian 2
  • Reza Ahmadi 3
1
2
3
چکیده [English]

Infiltration plays an important role in surface and subsurface hydrology and it is a key factor in the rainfall and runoff equations. The use of new approaches that have no limitations of common theoretical and empirical methods to determine infiltration relationships, will minimize the necessity of time consuming and costly experiments to determine permeability values and will make it possible to estimate the functional values. In this regard, in the present study the amount of soil permeability was estimated in Behshahr plain of Galougah located in Mazandaran province, using Fuzzy Inference System (FIS), Fuzzy Clustering Algorithm (FCA) and Nero-Fuzzy (ANFIS); so that, initial soil moisture content, soil organic matter content and soil lime content were considered as input parameters, and final soil infiltration rate was considered as output parameters of the models. Finally, the results obtained by the three mentioned modes were compared to the observed values by single-ring approach. According to the achieved results, Nero-Fuzzy approach with a mean deviation of 0.0042 cm/min, BIAS value of 0.6754 cm/min, Root-Mean-Square Error of 1.2096 cm/min and correlation coefficient of 0.9233 showed the most appropriate performance to estimate soil infiltration rate among the studied models; while, Fuzzy Clustering Algorithm with a mean deviation of 0.0075 cm/min, BIAS value of 2.1165 cm/min, Root-Mean-Square Error of 2.0244 cm/min and correlation coefficient of 0.8776, and Fuzzy Inference System with a mean deviation of 0.0161 cm/min, BIAS value of 2.5042 cm/min, Root-Mean-Square Error of 2.4533 cm/min and correlation coefficient of 0.8167 were placed in the next ranks respectively. Also, the highest correlation between observed and estimated values was seen in Nero-Fuzzy model (R2=0.85), and the two other studied models including Fuzzy Clustering Algorithm (R2=0.77) and Fuzzy Inference System (R2=0.66) are at the next ranks respectively. At the end of this research providing more data of soil physical and chemical characteristics as well as permeability amounts has been recommended in order to more accurate estimation of the studied models.

کلیدواژه‌ها [English]

  • Behshahr-Galougah
  • Permeability
  • Soil lime percentage
  • Soil moisture content
  • Soil organic matter
Aboukarima A.W.M., El Marazky M.S.A., and Guirguis A.E. 2007. Fuzzy system for determining water infiltration affected by field practices. Misr Journal of Agricultural Engineering, 24 (4): 903-922.
Ahmadi H., Tahmooreth M., and Mohamad Asgari H. 2008. The use of Fuzzy Inference System in suspended sediment estimation (A case study: Taleqan Watershed). Iranian Journal of Watershed Sciences and Engineering, 2(5): 53-62. (In Persian)
Ahmadi H., Tahmoureth M., and Asgari H.M. 2008. The use of Fuzzy Inference System in estimation of suspended load (A case study: Taleqan Watershed). Iran-Watershed Management Science and Engineering, 2(5): 53-62. (In Persian)
Amini M., Afyuni M., Fathianpour N., Khademi H., and Fluchler H. 2005. Continuous soil pollution mapping using fuzzy logic and spatial interpolation. Geoderma, 124: 223-233.
Baker L., and Ellison D., 2008. Optimisation of pedotransfer functions using an artificial neural network ensemble method. Geoderma, 144: 212–224.
Baybordi M. 1983. Principles of Irrigation Engineering. Soil-Water Relationship, Tehran University Press, 633p. (In Persian)
Bezdek JC. 1981. Pattern recognition with fuzzy objective function algorithms. Plenum Press, New York.
Bouwer H. 1986. Intake Rate: Cylinder Infiltrometer. In: Methods of Soil Analysis, Part 1: Physical and Mineralogical Methods, Klute, A. (Eds.). Soil Science Society of America, Wisconsin, ISBN-10: 0891188118, pp. 825-844.
Canarache A., Motoc E., and Dumitriu R. 1968. Infiltration rate as related to hydraulic conductivity, moisture deficit and other soil properties. In: Rijtema P.E., Wassink H. (Eds.), Water in the Unsaturated Zone. Proceedings of the Wageningen Symposium, Vol. 1, pp. 392–401.
 Chahinian N., Voltz M., Moussa R., and Trotoux G. 2006. Assessing the impact of hydraulic properties of a crusted soil on overland flow modelling at the field scale. Hydrological Processes 20(8): 1701-1722.
Dashtaki S.G., Homaee M. and Khodaverdiloo H. 2010. Derivation and validation of pedotransfer functions for estimating soil water retention curve using a variety of soil data. Soil Use and Management, 26(1): 68-74.
Ebrahimi K., and Nayeblouei F. 2009. Estimating final soil permeability using artificial neural network (A case study: Pards Aboureyhan field). Journal of Soil and Water Conservation Researches, 16 (1): 37-57. (In Persian)
Ghorbani Dashtaki Sh., Homaee M., and Mahdian MH. 2010. Effect of land use change on spatial variability of infiltration parameters. Iranian Journal of Irrigation and Drainage, 2(4): 206-221. (In Persian)
Ghorbani Dashtaki Sh., 2008. Estimating Soil Water Infiltration Parameters Using Pedotransfer Functions, Artificial Neural Networks and Geostatistics. Tarbiat Modares University, Iran, PhD Dissertation. (In Persian)
Ghorbani Dashtaki Sh., Homaee M., Mahdian M.H., and Kouchakzadeh, M. 2009. Site-Dependence Performance of Infiltration Models. Water Resources Management, 23(13): 2777–2790.
Haghverdi A., Cornelis W.M., and Ghahraman B. 2012. A pseudo-continuous neural network approach for developing water retention pedotransfer functions with limited data. Journal of Hydrology, 442–443: 46–54.
Hathaway R.J., and Bezdek J.C. 2001. Fuzzy c-means clustering of incomplete data. IEEE Transaction Systems, Man and Cybernetics, 31: 735– 744.
Hillel D. 1998. Environmental Soil Physics. Academic Press, San Diego, CA.
Hong Y.S., Rosen M.R., and Reeves R.R. 2002. Dynamic fuzzy modelling of storm water infiltration in urban fractured aquifers. Journal of Hydrologic Engineering, 7: 380-391.
Jang J.S.R. 1993. ANFIS: Adaptive-network-based fuzzy inference systems. IEEE Transaction Systems, Man and Cybernetics, 23:665-685.
Kashi H., Emamgholizadeh S., Ghorbani H., and Hashemi, S.A.A. 2011. Estimation of basic infiltration rate using physical and chemical characteristics of the soil by Artificial Neural Network. 11th National Conference of Irrigation and Evaporation Reduction.
Kashi H., Emamgholizadeh S., Qorbani H., and Hashemi S.A.A. 2011. Estimation of final soil permeability using soil physical and chemical characteristic by ANN. 11th Conference of Irrigation and Evaporation Reduction, Iran.
Kashi H., Emamqolizadeh S., Qorbani H., and Hashemi S.A.A. 2013. Estimation of soil infiltration using artificial neural network and linear regression in agricultural lands. Journal of Environmental Erosion Research, 3(9): 19-34. (In Persian)
Kumar C.P. 2006. Groundwater Flow and Contaminant Transport Models: An Overview. Journal of Applied Hydrology, Association of Hydrologists of India, 2: 94-110.
Lange J.C., Leibundgut N., Greenbaum and Schick A.P. 1999. A noncalibrated rainfall-runoff model for large, arid catchments, Water Resources, 35(7): 2161-2172.
Lassabatere, L., Angulo-Jaramillo R., Goutaland D., Letellier L., Gaudet J.P., Winiarski T., and Delolme C., 2010. Effect of the settlement of sediments on water infiltration in two urban infiltration basins. Geoderma, 156: 316-325.
Machiwal D., Madan K., and Mal B.C. 2006. Modelling infiltration and quantifying spatial soil variability in a wasteland of Kharagpur, India Biosystems Engineering, 95(4): 569-582.
Mamdani E.H. 1976. Advances in linguistic synthesizes of fuzzy controllers. International Journal of Man-Machine Studies, 8: 669-678.
Mbagwu J.S.C., 1997. Quasi-steady infiltration rates of highly permeable tropical moist savannah soils in relation to landuse and pore size distribution. Soil Technology, 11: 185-195.
Mohammadi M.H., and Refahi H. 2005. Estimation of infiltration through soil physical characteristics. Iranian Journal of Agricultural Sciences, 36(6): 1391-1398. (In Persian)
Nimm J.R., Schmidt K.M., Perkins K.S., and Stock JD. 2009. Rapid measurement of field-saturated hydraulic conductivity for areal characterization. Vadose Zone Journal, 8(1): 142-149.
Noorzadeh M., Hashemi S.M., and Malakooti M.J. 2011. Continuous zoning of electrical soil conductivity-acidity based on fuzzy clustering for Qom plain. Journal of Science and Technology of Agriculture and Natural Resources, 57: 199-207. (In Persian)
Parchami-Araghi F., Mirlatifi S.M., Ghorbani Dashtaki S., and Mahdian M.H. 2013. Point estimation of soil water infiltration process using artificial neural networks for some calcareous soils. Journal of Hydrology, 481: 35-47.
Poostizadeh N., Samani J.M., and Koorepazan Dezfooli. 2008. River flow prediction using fuzzy inference system. Iranian Journal of Water Resources Research, 4(5): 23-34. (In Persian)
Poustizadeh N., Samani, J.M.V. and Dezfuli, AK. 2008. River flow forecasting using fuzzy inference system. Iranian Journal of Water Resources Research, 4 (2): 23-34. (In Persian)
Rao A.R., and Srinivas V.V. 2005. Regionalization of watersheds by fuzzy cluster analysis. Journal of Hydrology, 318: 57-79.
Rawls W.J., Brakensiek D.L., and Savabi, M.R. 1989. Infiltration parameters for rangeland soils. Journal of Rangeland Management, 42 (2): 139-142.
Ren M., Wang B., Liang Q., and Fu G. 2010. Classified real-time flood forecasting by coupling fuzzy clustering and neural network. International Journal of Sediment Research, 25: 134-148.
Reynolds W.D., Elrick D.E., and Youngs E.G. 2002. Ring or cylinder infiltrometers (vadose zone). In: Dane J.H., and Topp G.C. (Eds.), Methods of Soil Analysis: Part 4, Physical Methods. Soil Science Society of America, Inc. Madison, WI. pp: 818-820.
Schaap M.G., Leij, F.J., van Genuchten M.Th. 2001. Rosetta: a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions. Journal of Hydrology, 251, 163–176.
Shu C., and Ouarda T.B.M.J. 2008. Regional flood frequency analysis at ungauged sites using the adaptive neuro-fuzzy inference system. Journal of Hydrology, 349: 31-43.
Singh V.P., ASCE F., Woolhiser D., and ASCE M. 2002. Mathematical modeling of watershed hydrology. Journal of Hydrologic Engineering, 7(4): 270-285.
Sohrabi T., and Paydar Z. 2005. Irrigation Systems Design. Tehran University Press.
Turner E.R. 2006. Comparison of infiltration equations and their field validation with rainfall simulation. M.Sc. Thesis, University of Maryland, USA, 202p.
Van De Genachte G., Mallants, D., Ramos J., Deckers A., and Feyen J., 1996. Estimating infiltration parameters from basic soil properties. Hydrological. Processes, 10: 687–701.
Vernieuwe H., Verhoest N.E.C., De Baets B., Hoeben R., and De Troch F.P. 2007. Cluster-based fuzzy models for groundwater flow in the unsaturated zone. Advances in Water Resources, 30: 701-714.