تخمین سرعت نفوذپذیری پایه با استفاده از مدل‌های نروفازی، شبکه عصبی و رگرسیون خطی چندمتغیره

نوع مقاله: مقاله پژوهشی

نویسندگان

1 هیات علمی

2 کارشناس گروه خاک دانشکاه کردستان

3 هیات علمی دانشگاه اردکان

چکیده

ننفوذ یکی از مهم‌ترین مشخصه‌های فیزیکی خاک است که اندازه‌گیری مستقیم آن دشوار، زمان‌بر و پرهزینه می‌باشد. هدف از این پژوهش تخمین سرعت نفوذپذیری پایه با استفاده مدل‌های نروفازی، شبکة مصنوعی و رگرسیون خطی چند متغیره است. بدین منظور، در 100 نقطه در منطقه دهگلان استان کردستان سرعت نفوذپذیری پایه با استفاده از استوانه مضاعف اندازه‌گیری شد. ویژگی‌های فیزیکی خاک (تخلخل، جرم ویژه ظاهری، شن، سیلت و رس) و توپوگرافی به عنوان ویژگی‌های زودیافت اندازه‌گیری شده و برای برآورد نفوذپذیری خاک استفاده شدند. داده‌ها به دو سری آموزشی (70 درصد داده‌ها) و آزمون (30 درصد داده ها) تقسیم شدند. مدل‌ها بر اساس نوع ورودی به نوع 1 (ویژگی‌های فیزیکی خاک) و 2 (ویژگی‌های فیزیکی خاک و توپوگرافی) طبقه بندی شدند. نتایج ارزیابی مدل‌ها بر اساس شاخص‌های ریشة میانگین انحراف خطا، مربعات خطا، میانگین خطا، خطای استاندارد نسبی و بهبود نسبی نشان داد که مدل نروفازی نوع 1 به ترتیب با آماره‌های 0.24، 1.3، 1.69، 0.25 و 65.41 و نوع 2 به ترتیب با آماره-های 0.1-، 0.95، 0.84، 0.18 و 71.52، دارای بالاترین دقت در تخمین سرعت نفوذپذیری پایه می‌باشد. همچنین مشاهده شد که استفاده از داده‌های توپوگرافی به عنوان ورودی همراه با ویژگی‌های فیزیکی خاک می‌تواند منجر به بهبود دقت تخمین سرعت نفوذپذیری پایه شود.

کلیدواژه‌ها


عنوان مقاله [English]

Estimation of steady infilterability rate using Neuro-Fuzzy, Artificial neural network and Multivariate linear regression models

چکیده [English]

Infiltration is the most important soil physical characteristic which its direct measurement is laborious, time consuming and expensive. The purpose of this study is to estimate steady infilterability rate, using Neuro-Fuzzy, Neural Network and Multivariate Linear Regression models. Consequently, steady infilterability rate, was measured using double rings in 100 points in Dehgolan region, Kurdistan Province, Iran. Soil physical (porosity, bulk density, sand, silt and clay) and topography characteristics were measured as readily available properties and used to estimate steady infilterability rate, The data were divided into two sets of terrain (70% of the data) and test (30% of the data). The models based on input type were categorized into type 1 (physical characteristics) and 2 (soil physical and topography characteristics). The results based on mean bias error (MBE), Root Mean Square Error (RMSE), Mean Error (ME), Relative Standard Error (RSE) and Relative Improvement (RI) showed that the Neuro-Fuzzy model (type 1 respectively with statistics 0.24, 2.01, 0.46, 4.04 and 46.65) (type 2 respectively with statistics -0.1, 1.24, 0.23, 1.54 and 58.62) has the most accuracy of steady infilterability rate, estimation. Also was observed using topography data as input together with soil physical characteristics can lead to improvement of the estimation accuracy of steady infilterability rate.

کلیدواژه‌ها [English]

  • Readily available properties؛ Slope؛ Pedotransfer function
  • Dehgolan
References

Aali K.A., Parsinejad M., and Rahmani B. 2009. Estimation of saturation percentage of soil using multiple regression, ANN, and ANFIS techniques. Computer and Information Science, 2: 127–136.

Amini M., Afyuni M., Fathianpour N., Khademi H., and Fluchler H. 2005. Continuous soil pollution mapping using fuzzy logicand spatial interpolation. Geoderma, 124: 223–233.

Blake G.R., and Hartge K.H. 1986. Bulk density. In: Klute A. (Ed.) Methods of Soil Analysis. Part 1, 2nd Edition. Agronomy Monograph. Vol. 9. American Society of Agronomy, Madison, WI, pp. 363–375.

Ceddia M.B., Vieira S.R., Villela L.O., Mota L.S., Anjos H.C., and Carvalho F.D. 2009. Topography and spatial variability of soil physical properties. Scientia Agricola, 66: 338-352.

Doaei M., Shabanpour-e-Shahrestani M., and Bagheri F. 2005. Modelling of saturated hydraulic conductivity of Gilan province involving Artificial Neural Networks. The Agricultural Science Research Report, Faculty of Agriculture, Gilan University, 1(6): 41-48. (In Persian)

Ebrahimi K., and Nayebloei F. 2009. Estimation of basic infiltration rate using Artificial Neural Networkcase study, Aburaihan Campus Farm. Journal of Water and Soil Conservation, 16(1): 37-56. (In Persian)

Fakori T., Emami H., Ghahramani B., and Mohajerpor M. 2012. The estimation of soil steady and instantaneous infiltration rate using pedotranferfunction. The First National Conference on Farm Water Managment, Soil and Water Research Institute, Karaj, 104-107. (In Persian)

Gee G.W. and Bauder J.W. 1986. Particle size analysis. In: Klute A. (Ed.), Methods of Soil Analysis. Part 1. American Society of Agronomy. Madison, WI, pp. 383-411.

Ghorbani Dashtaki S., and Homayi M. 2002. Parametric estimation of hydraulic function of unsaturated soil with pedotransfer functions. Agricultural Science Journal, 3(12): 3-15.

Hartley D.M. 1992. Interpretation of Kostiakov infiltration parameters for borders. Journal of Irrigation and Drainage Engineering, 118(1): 156-164.

Hengl T., Rossiter D.G., and Stein A. 2003. Soil sampling strategies for spatial prediction by correlation with auxiliary maps. Geoderma, 120: 75-93.

Jang J., Sun C., and Mizutani E. 1997. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence. Prentice Hall, Upper Saddle River, New Jersey, USA.

Jiang P., and Thelen K.D. 2004. Effect of soil and topographic properties on crop yield in a north-central corn soybean cropping system. Agronomy Journal, 96: 252-258.

Kashi H., Emamgholizadeh S., Ghorbani H., and Hashemi S.A.H. 2013. Estimation of soil infiltration in agricultural and pasture lands using artificial neural networks and multiple regressions. Scientific - Research Quarterly On Environmental Erosion Researches, 9: 42-56. (In Persian)

Kostiakov A.N. 1932. On the dynamic of coefficient of water-percolation in soils and on the necessity for studying it from a dynamic point of view for purposes of amelioration. Trans 6th Common International of Soil Science Society, Russia, 17-21.

Marcel G.S., Feike J.L., Martinus T., and van Genuchten H. 1998. Neural network analysis for hierarchical prediction of soil hydraulic properties. Soil Science Society of America Journal, 62: 847-855.

Mattara M.A., Alazbab A.A., and Zin El-Abedin T.K. 2015. Forecasting furrow irrigation infiltration using artificial neuralnetworks. Agricultural Water Management, 148: 63-71.

Menhaj M. 2009. Fundamental of Artificial Neural Networks, Amirkabir Press, 245p.

Merdun H., Cinar O., Meral R., and Apan M. 2006. Comparison of artificial neural network and regression pedotransfer functions for prediction of soil water retention and saturated hydraulic conductivity. Soil and Tillage Research, 90: 108-116.

Minasny B., and McBratney A.B. 2002. The Neuro-m method for fitting neural network parametric pedotransfer functions. Soil Science Society of America Journal, 66: 352–361.

Minasny B., McBratney A.B., and Bristow K.L. 1999. Comparison of different approaches to the development of pedotransfer functions for water-retention curves. Geoderma, 93: 225-253.

Mohammadi J., and Taheri M. 2005. Estimation of pedotransfer function using fuzzy regression. Journal of Agriculture Science and Technology, 2: 51-60.

Nabiollahi K., Haidari A., and Taghizadeh-Mehrjardi M. 2014. Digital mapping of soil texture using regression and artificial neural network in Bijar, Kurdistan. Journal of Water and Soil, 28(5): 1025-1036. (In Persian)

Nelson D.W., and Sommers L.E. 1996. Total carbon, organic carbon and organic matter. In: Methods of Soil Analysis. Part 2, 2nd ed. Page A.L. et al. (Ed.), Agronomy 9. American. Society of Agronomy, Inc. Madison, WI, pp. 961-1010.

Nelson R.E. 1982. Carbonate and gypsum. In: Page A.L., Miller R.H., and Keeny R. (Ed.), Methods of Soil Analysis. Part 2, Chemical and Microbiological Properties, Madison, WI, pp. 181-196.

Neshat, A., and Parehkar M. 2007. The comparison of methods for determining the vertical infiltration rate. Journal of Agriculture Science Natural Resource, 14(3): 186-195. (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.

Rasheed S., and Sasikumarb K. 2015. Modelling vertical infiltration in an unsaturated porous media using neural network architecture. Aquatic Procedia, 4: 1008 – 1015.

Rezaei S., and Gilkes R. 2005. The effects of landscape attributes and plant community on soil physical properties in rangelands, Geoderma, 125: 167-176.

Sarmadian F., Taghizadeh R.A., Asgari H.M., and Akbarzadeh A. 2009. The Comparison of Neuro fuzzy, ANN and Multiple Regression in prediction some soil characteristics in golestan province. Iraninan Soil and Water Research Journal, 1(41): 211-220.

Si J., Feng Q., Wena X., Xi H., Yu T., Li W., and Zhao C. 2015. Modeling soil water content in extreme arid area using an adaptive neuro-fuzzy inference system. Journal of Hydrology, 527: 679-687.

Sparks D.L., Page A.L., Helmke P.A., Leoppert R.H., Soltanpour P.N., Tabatabai M.A., Johnston G.T., and Summer M.E. 1996. Methods of Soil Analysis. Soil Science Society of America Journal, Madison, Wisconsin.

Taghizadeh-Mehrjardi M., Nabiollahi K., and Kerry R. 2016. Digital mapping of soil organic carbon at multiple depths using different data mining techniques in Baneh region, Iran. Geoderma, 266: 98-110.

Taghizadeh-Mehrjardi R., Sarmadian F., Savaghebi G.H., Omid M., Tomanian N., Rosta M.J., and Rahimian M.H. 2013. Comparison of Neuro-Fuzzy, genetic algorithm, artificial neural network and multivariate regression for prediction of soil salinity (Case study: Ardakan City). Journal of Range and Watershed Managment, 66(2): 207-222. (In Persian)

Tomasella J., Hodnett M.G., and Rossato L. 2000. Pedotransfer functions for the estimation of soil water retention in Brazilian soils. Soil Science Society of America Journal, 49: 1100-1105.

Vos B.D., Meirvenne M.V., Quataert P., Deckers J., and Muys B. 2005. Predictive quality of pedotransfer functions for estimating bulk density of forest soils. Soil Science Society of America Journal, 69: 500–510.

Walker W.R., Prestwich C., and Spofford T. 2006. Development of the revised USDA-NRCS intake families for surface irrigation. Agriculture Water Management, 8(5): 157-164.

Zare M., Moghaddamnia A., Tali Khoshk S., and Salmani H. 2015. Landslide hazard assessment by using Neuro-Fuzzy Technique in Vaz Watershed. Journal of Watershed Management Research, 6(11): 101–110. (In Persian)