Estimating the parameters of Philip infiltration equation using artificial neural network

Document Type: Full Article


Department of Irrigation, College of Agriculture, Shiraz University, Shiraz, I. R. Iran


Infiltration rate is one of the most important parameters used in irrigation water management. Direct measurement of infiltration process is laborious, time consuming and expensive. Therefore, in this study application of some indirect methods such as artificial neural networks (ANNs) for prediction of this phenomenon was investigated. Different ANNs structures including two training algorithms (TrainLM and TrainBR), two transfer functions (Tansig and Logsig), and different combinations of the input variables such as sand, silt, and clay fractions, bulk density (BD), soil organic matter (SOM), cumulative infiltration (CI) and elapsed time were used to predict sorption coefficient (S) and hydraulic conductivity (A) in Philip equation (I=S*t0.5+A*t), which corresponded to 30 soil samples from study areas located in the Agricultural College, Shiraz University, (Bajgah). A two-hidden layer ANNs with two and three neurons in the hidden layers, respectively and TrainLM algorithm performed the best in predicting S when Logsig and Tansig were used. Silt+ clay+ sand+ time+ CI combination was the most basic influential variables for the S prediction. Furthermore, a two-hidden layer ANNs with two and three neurons in the hidden layers, respectively and TrainBR algorithm performed the best in predicting A when Tansig and Tansig were used. Silt +clay +sand +BD + OM+ time+ CI combination was the most basic influential variables for A prediction. Results showed that increasing the hidden layers and input variables significantly improved the ANNs performance. The coefficient of determination (R2) confirmed that the ANNs predictions for A (84.6 %) fit data better than S (77.5 %).


Article Title [Persian]

شبکه عصبی مصنوعی هدایت هیدرولیکی معادله فلیپ ضریب جذب نفوذ آب

Authors [Persian]

  • نازنین ابریشمی شیرازی
  • علیرضا سپاسخواه
بخش مهندسی آب ، دانشکده کشاورزی، دانشگاه شیراز، شیراز، ج. ا. ایران
Abstract [Persian]

نفوذپذیری آب در خاک یکی از مهم‌ترین پدیده‌های فیزیکی خاک است. روش‌های تجربی تعیین معادله‌های نفوذ، نیازمند انجام آزمایش‌های زمان بر و پرهزینه است، لذا در این پژوهش از روش غیرمستقیم شبکه عصبی مصنوعی برای تخمین مقادیر ضریب جذب (S)  و فاکتور انتقال(A)  معادله فیلیپ استفاده شد. ساختارهای مختلف شبکه عصبی مصنوعی متشکل از الگوریتم های آموزش TrainLM  و TrainBR و توابع انتقال لوگ سیگموئید و تانژانت سیگموئید برای لایه‌های میانی و تابع تبدیل خطی برای لایه خروجی و ترکیبات متفاوتی از ورودی‌ها، شامل مقادیر نفوذ تجمعی و زمان‌های مربوط به هرکدام، به‌عنوان ورودی ثابت و درصد شن، درصد سیلت، درصد رس، چگالی ظاهری و ماده آلی به عنوان ورودی‌های متغیر، برای 30 نقطه در دانشکده کشاورزی واقع در منطقه باجگاه بررسی گردید. برای تخمین ضریب جذب بهترین ساختار دارای دو لایه مخفی و 3 ورودی (درصد شن، درصد سیلت و درصد رس) با دو نرون در لایه اول و سه نرون در لایه دوم و الگوریتم آموزش TrainLM بود. برای تخمین فاکتور انتقال بهترین ساختار دارای دو لایه مخفی و 5 ورودی (چگالی ظاهری، مقدار ماده آلی، درصد شن، درصد سیلت و درصد رس) با دو نرون در لایه اول و سه نرون در لایه دوم و الگوریتم آموزش Train BR بود. افزایش تعداد لایه‌های مخفی و تعداد ورودی‌ها تاثیر به سزایی در بهبود نتیجه داشت و شبکه عصبی در تخمین مقادیر فاکتور انتقال عملکرد بسیار بهتری نسبت به ضریب جذب را نشان داد. مقدار ضریب تعیین (R2) نشان داد که پیشبینی های شبکه عصبی برای A (% 6/84) بهتر از S (% 5/77) می‌‌باشد.

Keywords [Persian]

  • شبکه عصبی مصنوعی
  • نفوذ آب
  • معادله فلیپ
  • ضریب جذب
  • هدایت هیدرولیکی
Basheer, I. A., & Hajmeer, M. (2000). Artificial neural networks: Fundamentals, computing, design, and application. Journal of Microbiological Methods, 43(1), 3-31. doi:
Blake, G., Hartge, K. p., & methods, m. (1986). Bulk density. In A. Klute(Ed), Methods of Soil Analysis: Part 1—Physical and Mineralogical Methods (pp. 363-375): Soil
Science Society of America, American Society of Agronomy.
Brown, M., & Chris, H. (1994). Neurofuzzy adaptive modeling and control. New York: Prentice Hall.
Cosby, B., Hornberger, G., Clapp, R., & Ginn, T. (1984). A statistical exploration of the relationships of soil moisture
characteristics to the physical properties of soils.  Water Resources Research, 20(6), 682-690.
Gardner, W. R. (1958). Some steady-state solutions of the unsaturated moisture flow equation with application to evaporation from a water table. Soil Science, 85(4), 228-232.
Gee, G., & Bauder, G. (1986). Particle-size analysis. In A. Klute (Ed.), Methods of Soil Analysis: Part 1—Physical
and Mineralogical Methods (pp. 383-409). American Society of Agronomy - Soil Science Society of America.
Ghobadian, B., Rahimi, H., Nikbakht, A., Najafi, G., & Yusaf, T. (2009). Diesel engine performance and exhaust
emission analysis using waste cooking biodiesel fuel with an artificial neural network. Renewable Energy, 34(4), 976-982.
Graupe, D. (2013). Principles of Artificial Neural Networks (Vol. 7). Chicago: World Scientific Publishing Co Pte Ltd.
Green, H. W., & Ampt, G. A. (1911). Studies on soil phyics. The Journal of Agricultural Science, 4(01), 1-24. doi: doi:10.1017/S0021859600001441
Hagan, M., Demuth, H., & Beale, M. (1996). Neural network design. Boston, MA, USA:  PWS Publishing Company.
Hillel, D., & Gardner, W. (1970). Transient infiltration into crust-topped profiles. Soil Science, 109(2), 69-76.
Holtan, H. N. (1961). A Concept for infiltration estimates in watershed engineering. Washington DC, USA:  Agricultural Research Service - U. S. Department of Agriculture.
Horton, R. E. (1940). Approach toward a physical interpretation of infiltration capacity. Soil Science Society of America Journal, 5, 339-417.
Ibn Ibrahimy, M., Ahsan, R., & Khalifa, O. O. (2013). Design and optimization of Levenberg-Marquardt based neural network classifier for EMG signals to identify hand motions. Measurement Science Review, 13(3), 142-151.
Igbadun, H., Othman, M., & Ajayi, A. (2016). Performance of selected water infiltration models in sandy clay loam soil in Samaru Zaria. Global Journal of Researches in Engineering: J General Engineering, 16, 8-14.
Jain, S., Singh, V., & van Genuchten, M. (2004). Analysis of soil water retention data using artificial neural networks. Journal of Hydrologic Engineering, 9(5), 415-420. doi: doi:10.1061/(ASCE)1084-0699(2004)9:5(415)
Kim, S. (2017). MATLAB Deep Learning With Machine Learning, Neural Networks and Artificial Intelligence. New York: Apress.
Kostiakov, A. V. (1932). On the dynamics of the coefficient of water percolation in soils and on the necessity for studying it from a dynamics point of view for purposes ofamelioration. Transactions of 6th Committee International Society of Soil Science, Russia, Part A, 17-21.
Kumar, M., Raghuwanshi, N., Singh, R., Wallender, W., & WO, P. (2002). Estimating evapotranspiration using
artificial neural network. Journal of Irrigation and Drainage Engineering, 128(4), 224-233. doi: doi:10.1061/(ASCE)0733-9437(2002)128:4(224)
Lei, Z. D., Yang, S. X., & Xie, S. C. (1989). One step method of scaling the soil hydraulic properties in the field. Journal of Hydraulic Engineering, 12, 1-10.
Lili, M., Bralts, V. F., Yinghua, P., Han, L., & Tingwu, L. (2008). Methods for measuring soil infiltration: State of the art. International Journal of Agricultural and Biological Engineering, 1(1), 22-30.
Machiwal, D., Jha, M. K., & Mal, B. (2006). Modelling infiltration and quantifying spatial soil variability in a wasteland of Kharagpur, India. Biosystems Engineering, 95(4), 569-582.
Mehrabi, F., & Sepaskhah, A. R. (2013). Spatial variability of infiltration characteristics at watershed scale: a case study of bajgah plain. Journal of Agricultural Engineering Research, 14(1), 13-32.
Merdun, H., Çınar, Ö., Meral, R., & 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(1–2), 108-116. doi:
Minasny, B., & McBratney, A. B. (2002). The method for fitting neural network parametric pedotransfer functions. Soil Science Society of America Journal, 66(2), 352-361. doi: 10.2136/sssaj2002.3520
Moosavi, A. A., & Sepaskhah, A. (2011). Artificial neural networks for predicting unsaturated soil hydraulic characteristics at different applied tensions. Archives of Agronomy and Soil Science, 58(2), 125-153. doi: 10.1080/03650340.2010.512289
Moosavizadeh-Mojarad, R., & Sepaskhah, A. R. (2011). Comparison between rice grain yield predictions using artificial neural networks and a very simple model under different levels of water and nitrogen application. Archives of Agronomy and Soil Science, 58(11), 1271-1282. doi: 10.1080/03650340.2011.577423
Nelson, D., & Sommers, L. (1996). Total carbon, organic carbon, and organic matter. In D. Sparks (Ed.), Methods of Soil Analysis: Part III-Physical and Mineralogical Methods (3rd ed., pp. 961-1010). American Society of Agronomy.
Noori, R., Karbassi, A., & Salman Sabahi, M. (2010). Evaluation of PCA and gamma test techniques on ANN operation for weekly solid waste prediction. Journal of Environmental Management, 91(3), 767-771. doi:
Ogbe, V., Mudiare, O., & Oyebode, M. (2008). Evaluation of furrow irrigation water advance models. Journal of Agricultural Engineering and Technology, 16(1), 74-83.
Pachepsky, Y. A., Timlin, D., & Varallyay, G. (1996). Artificial neural networks to estimate soil water retention from easily measurable data. Soil Science Society of America Journal, 60(3), 727-733. doi: 10.2136/sssaj1996.03615995006000030007x
Parasuraman, K., Elshorbagy, A., & Si, B. C. (2006). Estimating saturated hydraulic conductivity in spatially variable fields using neural network ensembles. Soil Science Society of America Journal, 70(6), 1851-1859. doi: 10.2136/sssaj2006.0045
Philip, J. R. (1957). The theory of infiltration: 1. The infiltration equation and its solution. Soil Science, 83(5), 345-358.
Richter, Q. Y. R. A. J. (1989). A new method for scaling Philip's equation of infiltration. Journal of Hydraulic Engineering, 9, 1-8.
Sablani, S., Ramaswamy, H., Sreekanth, S., & Prasher, S. (1997). Neural network modeling of heat transfer to liquid particle mixtures in cans subjected to end-over-end processing. Food Research International, 30(2), 105-116.
Saxton, K. E., Rawls, W. J., Romberger, J. S., & Papendick, R. I. (1986). Estimating generalized soil-water characteristics from texture. Soil Science Society of America Journal, 50(4), 1031-1036. doi: 10.2136/sssaj1986.03615995005000040039x
Schaap, M. G., Leij, F. J., & van Genuchten, M. T. (1998). Neural network analysis for hierarchical prediction of soil hydraulic properties. Soil Science Society of America Journal, 62(4), 847-855. doi: 10.2136/sssaj1998.03615995006200040001x
Shaalan, K., Riad, M., Amer, A., & Baraka, H. (1999). Speculative work in neural network forecasting: an application to Egyptian cotton production. The Egyptian Computer Journal, 27,  58-76.
Sharma, A., Sahoo, P. K., Tripathi, R., & Meher, L. C. (2016). Artificial neural network-based prediction of performance and emission characteristics of CI engine using polanga as a biodiesel. International Journal of Ambient Energy, 37(6), 559-570.
Sy, N. L. (2006). Modelling the infiltration process with a multi-layer perceptron artificial neural network. Hydrological Sciences Journal, 51(1), 3-20. doi: 10.1623/hysj.51.1.3
Van Genuchten, M. T. (1980). A closed-form equation for predicting the hydraulic conductivity of unsaturated soils. Soil Science Society of America Journal, 44(5), 892-898.
Zhang, G., Eddy Patuwo, B., & Y. Hu, M. (1998). Forecasting with artificial neural networks:: The state of the art. International Journal of Forecasting, 14(1), 35-62. doi:
Zhang, G., & Hu, M. Y. (1998). Neural network forecasting of the British Pound/US Dollar exchange rate. Omega, 26(4), 495-506. doi: