ارزیابی سامانه استنتاج فازی- عصبی تطبیقی و توابع انتقالی رگرسیونی در برآورد هدایت آبی اشباع خاک

نوع مقاله : مقاله پژوهشی

نویسنده

دانشیاردانشکده کشاورزی و منابع طبیعی مغان- دانشگاه محقق اردبیلی

چکیده

اندازه­گیری ویژگی‌های هیدرولیکی خاک مانند هدایت آبی اشباع خاک که از مهم‌ترین ویژگی‌های فیزیکی خاک می‌باشد. در این تحقیق از روش توابع انتقالی و سامانه استنتاج فازی بر پایه شبکه عصبی تطبیقی(ANFIS[1])  برای برآورد هدایت آبی اشباع خاک از بافت خاک استفاده شده است. ورودی­های مدل شامل درصد رس, سیلت و شن خاک بود. برای ارزیابی عملکرد مدل از پارامترهای مجذور میانگین مربعات خطا (RMSE)، درصد خطای نسبی (ε)، میانگین خطای مطلق (MAE) و ضریب تبیین (R2)  استفاده شد که برای مدل (ANFIS) به ترتیب 557/0(میلی‌متر بر روز) ، 627/0(درصد)، 844/0(میلی‌متر بر روز) و 997/0 به‌دست آمد. همچنین دقت توابع انتقالی، به ترتیب از مدل فرر-جولیا و همکاران (2004)، رزتا، دنی و پوکت (1994)، کاسبای و همکاران (1984)، پوکت و همکاران (1985) و کمپل و شوزاوا (1994) کاهش یافت. از میان روش‌های توابع انتقالی روش فرر-جولیا و همکاران (2004) با (89/0R2=) و خطای (میلی‌متر بر روز 1/2RMSE = ) از دقت بالاتری برخوردار بود. نتایج نشان‌داد سامانه استنتاج فازی- عصبی ANFIS نسبت به توابع انتقالی رگرسیونی از دقت بیشتری برخوردار می‌باشد.
 
[1]. Adaptive Neuro-Fuzzy Inference Systems 

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Evaluation of Adaptive Neuro Fuzzy Inference System and Regression-Based Pedo Transfer Functions for Estimating Saturated Hydraulic Conductivity

نویسنده [English]

  • yaser hoseini
Assistance Professor, Faculty of Agriculture and Environmental Science, University of Mohaghegh, Ardabili, Iran
چکیده [English]

Measurement of soil hydraulic properties such as soil saturated hydraulic conductivity is one of the most important physical properties of soil. In this study, adaptive neuro fuzzy inference system (ANFIS) and pedo-transfer functions (PTFs) are used to estimate soil saturated hydraulic conductivity. The model inputs included soil texture, the percent of silt, clay, and sand. To evaluate the performance of the model, parameters of root mean square error (RMSE), percentage of relative error (ε), mean absolute error (MAE) and the coefficient of determination (R2) were used, which for (ANFIS) model were determined as 0.557, 0.627%, 0.844, and 0.997, respectively. Accuracy of PTFs methods decreased from Ferrer-Julià (2004), Roseta (UNSODA(lab)-SSC), Dane (1994), Cosby (1984), Puckett (1985), and Campbell (1994). Among PTFs methods, Ferrer-Julià (2004) had more accuracy with a regression coefficient of (R2 =0.89) and (RMSE =2.1). Performance evaluation of the models showed that the ANFIS model compared with PTFs was able to predict soil hydraulic conductivity with more accuracy.

کلیدواژه‌ها [English]

  • Irrigation and Drainage Networks
  • Soil Hydraulic Properties
  • Ferrer-Julià method
  1. اصغری، ش.، و حاتم وند، م.، و حسنپورکاشانی، م. (1398). اشتقاق توابع انتقالی برای برآورد هدایت هیدرولیکی اشباع خاک در شمال غرب دریاچه ارومیه. پژوهش های فرسایش محیطی, 9(3 (پیاپی 35) ), 102-118.
  2. حسن زاده, ی., معظم نیا, م., صادق فام, س. و ع، ندیری. 1398. تخمین هدایت هیدرولیکی و ارزیابی عدم قطعیت بین مدل‌ها و داده‌های ورودی توسط متوسط‌گیری بیزین از مدل‌های هوش مصنوعی. نشریه مهندسی عمران امیرکبیر. 52(9):1-13.
  3. رضایی ارشد، ر . صیاد ،غ. مظلوم ،م. شرفا،م. و م. جعفرنژادی. 1391. مقایسة روش‌های شبکه عصبی مصنوعی و رگرسیونی برای پیشبینی هدایت آبی اشباع خاکهای استان خوزستان، مجله علوم و فنون کشاورزی و منابع طبیعی، علوم آب و خاک،6(60): 107-117.
  4. Agyare, W. A., Park, S. J. and P. L. G. 2007. Artificial neural network estimation of saturated hydraulic conductivity. Vadose Zone Journal, 6(2): 423–431.
  5. Akbarzadeh, A., Mehrjardi, R.T., Rouhipour, H., Gorji, M. and H.G. 2009. Estimating of soil erosion covered with rolled erosion control systems using rainfall simulator (neuro-fuzzy and artificial neural network approaches). Journal of Applied Science Research, 5 (5): 505–514.
  6. Aqil, M., Kita, I., Yano, A. and S. 2007. A comparative study of artificial neural networks and neuro-fuzzy in continuous modeling of the daily and hourly behavior of runoff, Journal of Hydrology. 337 (1-2): 22–34.
  7. Campbell, G.S. and S. Shozawa. Prediction of hydraulic properties of soils using particle-size distribution and bulk density data. Proceedings of International Workshop on Indirect Methods. University 0f California, 30: 211–223.
  8. Cosby, B. J., Hornberger, G. M., Clapp, R. B. and T. R. Ginn. 1984. A statistical exploration of the relationship of soil moisture characteristics to the physical properties of soils. Water Resources Research, 20 (6): 682-690.
  9. Gokceoglu, C. 2002. A fuzzy triangular chart to predict the uniaxial compressive strength of the Ankara agglomerates from their petrographic composition. Engineering Geology, 66: 39–51.
  10. Dane, J.H. and W. Puckett. 1994. Field soil hydraulic properties based on physical and mineralogical information. p. 389-403. In: M.Th. van Genuchten et al. (eds) Proceedings of the International workshop on indirect methods for estimating the hydraulic properties of unsaturated soils. Univ. of California, Riverside, CA.
  11. Elrick, D.E., Reynolds, W.D., Tan, K.A. 1989. Hydraulic conductivity measurements in the unsaturated zone using improved well analyses. Ground water monitoring. 9:184-193.
  12. Ferrer-Julià, M., Estrela Monreal, T., Sánchez Del Corral Jiménez, A. and E. García Meléndez. 2004. Constructing a saturated hydraulic conductivity map of Spain using pedotransfer functions and spatial prediction. Geoderma, 123: 275-277.
  13. Finol, J., Guo, Y.K. and X.D. Jing. 2001. A rule based fuzzy model for the prediction of petro physical rock parameters, Journal of Petroleum Science and Engineering, 29: 97–113.
  14. Jacovides, C.P. 1997. Reply to comment on Statistical procedures for the evaluation of evapotranspiration models. Agricultural Water Management, 3: 95-97.
  15. Jang, J. S. R. 1993. ANFIS: Adaptive Network Based Fuzzy Inference System, IEEE transactions on Systems, Man and Cybernetics, 23 (3): 665–683.
  16. Jamieson, P.D., Porter, J.R. and D.R. Wilson. 1991. A test of the computer simulation model ARC-WHEAT1 on wheat crops grown in New Zealand. Field Crops Res. 27: 337–350.
  17. Jang, J. S. R. and C. T. 1997. Neuro-Fuzzy Modeling and Control, Proceedings of the IEEE, 83 (3): 378-406.
  18. hassanzadeh, y., Moazamnia, M., Sadeghfam, S., Nadiri, A. A. 2020. Hydraulic conductivity and uncertainty analysis of between-models and input data by using Bayesian model averaging of artificial intelligence model. Amirkabir Journal of Civil Engineering. 52(9):2171-2190.
  19. Karakus, M. and B. Tutmez. 2006. Fuzzy and multiple regression modelling for evaluation of intact rock strength based on point load, Schmidt hammer and sonic velocity, Rock Mech. Rock Eng. 39 (1): 45–57.
  20. Karatalopoulos, S. V. 2000. Understanding Neural Networks and Fuzzy Logic- Basic Concepts and Applications; Prentice Hall, New-Delhi, India.
  21. Luk, K. C., Ball, J. E. and A.   2000. a study of optimal model lag and spatial inputs to artificial neural network for rainfall forecasting, Journal of Hydrology, 227: (1-4): 56–65.
  22. Marshal, T. J. 1958. A relationship between permeability and size distribution of pores. Soil Science, 9:1-8.
  23. Manyam, C., Morgan, C. L., Heilman, J. L., Fatondji, D., Gerard, B. and W.A. 2007. Modeling hydraulic properties of sandy soils of Niger using pedotransfer functions. Geoderma, 141: 407 – 415.
  24. Nadiri, A.A., Yousefzadeh, S. 2017. A Comparison of the Performance of Artificial Neural Network, Fuzzy Logic and Adaptive Neuro-Fuzzy Inference Systems Models in the Estimation of Aquifer Hydraulic Conductivity. A Case Study: Maraghe-Bonab Aquifer, Hydrogeomorphology, 3(10): 21-40.
  25. Naderloo, L., Alimardani, R., Omid, M., Sarmadian, F., Javadikia, P., Yaser Torabi, M. and F. Alimardani. 2012. Application of ANFIS to predict crop yield based on different energy inputs. Measurement, 45: 1406-1413.
  26. Puckett, W. E., Dane, J. H. and B. F. 1985. Physical and mineralogical data to determine Soil hydraulic properties. Soil Science Society of America Journal, 49: 831-836.
  27. Rawls, W. J. 2004. Pedotransfer functions for the United States. Developments in Soil Science, 30: 437-447.
  28. Reynolds, W.D., Elrick, D.E., Clothier, B.E. 1985. The constant head well permeameter Effect on unsaturated flow. Soil Science. 139(2): 172-18.
  29. Reynolds, W.D., Elrick D.E. 1985. In situ measurement of field saturated hydraulic conductivity sorpitivity a parameter using Guelph permeameter. Soil science. 140 (4): 292-302.
  30. Rahimi-Ajdadi, F. and Y. Abbaspour-Gilandeh. 2011. Artificial neural network and stepwise multiple range regression methods for prediction of tractor fuel consumption. Measurement, 44 (10): 2104-2111.
  31. Sajikumar, N. and B.S. Thandaveswara. 1999. A nonlinear rainfall–runoff model using artificial neural networks, Journal of Hydrology, 216: 32-55.
  32. Schaap, M. G. and F. J. Leij. 1998. Using neural networks to predict soil water retention and soil hydraulic conductivity. Soil and Tillage Research, 47: 37-42.
  33. Salazar, O., Wesstrom, I. and A.  2008. Evaluation of Drain mod using saturated hydraulic conductivity estimated by a pedotransfer function model. Journal of Agricultural Water Management, 95: 1135 – 1143.
  34. Wagner, B., Tarnawski, V. R., Hennings, V., Müller, U., Wessolek, G. and R. Plagge. 2001. Evaluation of pedo-transfer functions for unsaturated soil hydraulic conductivity using an independent data set. Geoderma.102: 275-297.
  35. Van Genuchten, M.T. 1980. A closed form equation for predicting the hydraulic conductivity of soils. Soil Sci. Soc. J, 44: 892-898.
  36. Vereecken, H., Maes, J. and J. Feyen, 1990. Estimating unsaturated hydraulic conductivity from easily measured soil property. Soil Science, 149: 1-12.
  37. Yilmaz, I. and O. Kaynar, 2011. Multiple regressions, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils. Expert Systems with Applications. 38(5): 5958–5966.