Performance Evaluation of Artificial Neural Networks conjunct with Genetic Algorithm for Estimation of Soil Infiltration Rate (Case Study: Khoda afarin Region of East Azerbaijan Province)

Document Type : Research Paper


1 Member of the faculty of the Ministry of Science, Research and Technology (Department of Research and Technolog)

2 M.Sc. Graduated of Soil Science Department, Faculty of Agriculture, University of Zanjan, Zanjan, Iran

3 Assistant Professor, Shahid Bakeri High Education Center of Miandoab, Urmia University, Urmia, iran


Infiltration plays a pivotal role in the hydrologic cycle by effectively acting to partition water into surface and subsurface components. Direct measurement of infiltration rate is expensive and work and time consuming. Artificial Neural Networks (ANNs), Gene Expression Programing (GEP) and hybrid of ANN and Genetic Algorithm (ANN-GA) can be used for estimation of soil infiltration rate as an indirect methods. The main objective of this research was to develope an infiltration rate model in Khoda afarin region based on the collected data (88 double ring infiltration) and some soil properties. The Pierson correlation revealed among the soil properties, sand and silt contents, porosity and organic matter have the most correlation with the infiltration rate. Determination Coefficient (R2) and Normalized Root Mean Square Error (NRMSE) were calculated to be 0.88 and 7.9%, respectively for the ANN method and 0.75 and 11.3% for the GEP method. Both ANN and GEP methods perform poorly, in extrapolating the minimum and maximum amount of infiltration rate. The hybrid model of ANN-GA was the best model in terms of statistical indices including R2 (0.93) and RMSE (6.1%). This model comprised of 4 neurons (sand, silt, porosity percentage and OM) in input layer and 5 neurons using sigmoidal tangent functions in the hidden layer and linear activation functions in the output layer. The results indicated that the neural-genetics algorithm can be used to optimize weight parameter of artificial neural network. Overall the hybrid ANN-GA model showed better performance than the other models, so that the R2 and NRMSE for the hybrid model were 0.93 and 6.1% respectively. Therefore it is suggested as a powerful tool for estimating infiltration rate.


Main Subjects

Ahmadi O, 2018. (2018). Determination of optimal land use for garden construction in Khodafarin region by MicroLESE DSS. M.Sc. Thesis, Soil Science and Engineering Department, University of Zanjan. (IN Farsi).
Ahmadi, A., Palizvan zand, P. and Palizvan zand, H. (2018). Estimation of saturated hydraulic conductivity by using gene expression programming and ridge regression (A case study in East Azerbaijan province). Iranian Journal of Soil and Water Research, 48(5): 1087-1095. (In Farsi)
Alvisi, S., Mascellani, G., Franchini, M. and Bardossy, A. (2005) Water level forecasting through fuzzy logic and artificial neural network approaches. J.Hydrol. Earth Sys. Sci, 2, 1107-1145.
Amini, M., Abbaspour, K. C., Khademi, H., Fathianpour, N., Afyuni, M., and Schulin, R. (2005). Neural network models to predict cation exchange capacity in arid regions of Iran. European Journal of Soil Science, 56(4), 551-559.
Argyrokastritis, I and Kerkides, P. (2003). A note to the variable sorptivity infiltration equation. Water Resource. Management, 17:133–145.
Aytek, A, and Kisi, O. (2008). A genetic programming approach to suspended sediment modeling. Journal of Hydrology, 351: 288-298.
Azamathulla, H. M. and Jarrett, R. D. (2013) Use of gene-expression programming to estimate Manning’s roughness coefficient for high gradient streams. Water Resources Management, 27, 715-729.
Barikloo, A., Alamdari, P., Moravej, K. and Servati, M. (2017). Prediction of Irrigated Wheat Yield by using Hybrid Algorithm Methods of Artificial Neural Networks and Genetic Algorithm. J. Water and Soil, 30: 3. 715-726. (In Farsi)
Ferrier, S. and Guisan, A. (2006). Spatial modelling of biodiversity at the community level. J. Applied ecology, 43(3): 393-404.
Gee G. W. and Or D. (2002) Particle-size analysis. In: Warren, A.D. Eds. Methods of Soil Analysis. Part 4. Physical Methods. (pp.255-295). Soil Sci. Soc. Am. Inc.
Ghezelbash, Z., Zakerinia, M., Hezarjaribi, A., and Dehghani, A.A. (2015). Performance comparison of gene expression programming and artificial neural network methods to estimate water distribution uniformity in sprinkler irrigation. J. Water and Soil Conservation, 21(6): 95-114. (In Farsi).
Goldberg D.E. (1989). Genetic algorithm in search, optimization and machine learning. Addison-Wesley, Reading, MA, 412p.
Ghorbani Dashtaki, S. and Homaei, M. (2000). Pedotransfer Functions for parametric Predicting of unsaturated Soil Hydraulic conductivity function. Agriculture engineering research, 12(3): 1-16. (In Farsi)
Green, W.H. and Ampt, G.A. (1911). Studies on soil physics: Part 1. The flow of air and water through soil. J. Agriculture Sciences, 4: 1-24.
Haghverdi, A., Ghahraman, B., Joleini, M., Khoshnud Yazdi, A.A. and Arabi, Z. (2011). Comparison of different Artificial Intelligence methods in modeling water retention curve (Case study: North and Northeast of Iran). J. Water and Soil Conservation, 18(2): 65-84. (In Farsi)
Haykin, S. (1999). Neural networks: A Comprehensive Foundation, 2nd ed., Upper Saddle River, NJ: Prentice-Hall.
Hong, Y. S. White., P. A. and Scott, D. M. (2005) Automatic rainfall recharge model induction by evolutionary computational intelligence. WaterResour. Res, 41:W08422.
Jarvis, N. J., Zavattaro, L. K., Reynolds, W. D., Olsen, P. A., McGechan, M., Mecke, M., Mohanty, B., Leeds-Harrison, P. B. and Jacques, D. (2002). Indirect estimation of near-saturated hydraulic conductivity from readily available soil information. Geoderma, 108, 1 -17.
Kao, C.S. and Hunt. J.R. (1996). Prediction of wetting front movement during one-dimentional infiltration into soils. Water Resour. Res, 9(2): 384-395.
Kazman, Z., Shainberg, I, and Gal, M. (1983). Effect of low levels of exchangeable Na and applied phosphogypsum on infiltration rate of various soils. Soil Science Society of America, 135: 184-192.
Khu, S. T., Liong, S. Y., Babovic, V., Madsen, H. and Muttil, N. (2001) Genetic programming and its application in real‐time runoff forecasting1. Journal of the American Water Resources Association, 37, 439-451.
Koza, J. (1992) Genetic Programming: on the Programming of Computers by Means of Natural Selection. MIT Press.
Laurentiu, A., Bernard, P.A., and Faicual, L. (2002). Integrated Genetic Algorithm-Artificial Neural Network Strategy for Modeling Important Multiphase-Flow Characteristics. Ind. Eng. Chem. Res. 41: 2543-2551.
Leij, F., M.G. Schaap and L.M. Arya. (2002). Water retention and storage: Indirect methods. PP. 1009–1045. In: J.H. Dane and G.C. Topp (Ed.), Methods of Soil Analysis. Part 4. SSSA Book Ser. No. 5. SSSA, Madison, W.
Liong, S.Y., Gautam, T.R., Khu, S.T., Babovic, V., Keijzer, M., and Muttil, N. (2002). Genetic programming, A new paradigm in rainfall runoff modeling, J. Am. Water Res. Asso, 38(3), 705-718.
Makkeasorn, A., Chang, N. B., Beaman, M., Wyatt, C. and Slater, C. (2006). Soil moisture estimation in a semiarid watershed using RADARSAT- 1 satellite imagery and genetic programming.Water Resour. Res, 42, W09401.
Maroofpour, S., Fakheri-Fard, A., and Shiri, J. (2017). Development and combination of soft computing and geostatistical models in estimation of spatial distribution of groundwater level. J. Water and Soil Conservation resource, 6(2): 17-28. (In Farsi).
Merdun, H., Meral, O. C., and Apan, R. M. (2006). Comparison of artificial neural network and regression Pedotransfer functions for predict of water retention and saturated hydraulic conductivity. Soil and Tillage Research, 90: 108-116.
Minasny, B. J., Hopman, W.T., Harter, S.O., Eching, A. Toli., and M.A, Denton. (2004). Neural networks prediction of soil hydraulic functions for alluvial soils using multistep outflow data. Soil Sci. Soc. Amer. J, 68: 417– 429.
Nasseh, S., Mohebbi, A., Sarrafi, A., and Taheri, M. (2009). Estimation of pressure drop in venturi crubbers based on annular two-phase flow model, artificial neural networks and genetic algorithm. J. Chemical Engineering, 150: 1. 131-138.
Nelson, D. W. and Sommer, L. E. (1982). Total carbon, organic carbon, and organic matter. In: Sparks, D. L., Page, A. L., Helmke, P. A., Loeppert, R. H., Soltanpour, P. N., Tabatabai, M. A., Johnston, C. T., Sumner, M. E. Eds. Methods of soil analysis: part 3. chemical and microbiological properties. pp. 539–579. Soc. Agron., Madison.
Nelson, R.E. (1982). Carbonate and gypsum. Pp. 181-197. In: Page AL, Miller RH and Keeney DR (eds). Methods of Soil Analysis. Part 2. Chemical and Microbiological Methods. 2nd ed. Agron. Monogr. 9. ASA and SSSA, Madison, WI.
Nestor, S. Y. (2006). Modelling the infiltration process multi-layer perceptron artifical network. HydrologicalSciences Journal, 51(1): 3-20
Nosrati, H. and Eftekhari, M. (2014). A new approach for variable selection using fuzzy logic.Computational Intelligence in ElectricalEngineering, 4, 71 -83.
Pachepsky, Y. A., Timlin, D., and Várallyay, G. (1996). Artificial neural networks to estimate soil water retention from easily measurable data. Soil Science Society of America Journal, 60(3), 727-733.
Parasuraman, K., Elshorbagy, A. and Carey, S. K. (2007). Modeling the dynamics of the evapotranspiration process using genetic programming. Hydrol. Sci. J, 52, 563–578.
Parvaresh Rizi, A., Koochak Zadeh, S., and Omid, M. (2006). Estimating moving hydraulic jump arameyters by means of ANN and the integration of ANN and GA. Agricultural Sciences, 37: 1. 187-196. (In Farsi)
Prasad, R. and Mathur, S. (2007). Groundwater Flow and Contaminant Transport Simulation with Imprecise Parameters. Irrigation and Drainage Engineering, 133(1): 61-70.
Sarmadian, F., Taghizadeh mehrjerdi, R A., Asgari, M. and Akbarzadeh A. (2011). Comparison of neuro fuzzy methods, neural network and multivariate regression in predicting some soil properties (Case study: Golestan province). Iranian Journal of Soil and Water Research, 41(2): 211-220. (In Farsi)
Savic, D.A., Walters, G. A. and Davidson, J. W. (1999) Genetic programming approach to rainfall–runoff modelling. Water Resour. Manage. 13, 219–231.
Singh, V.P. and YU, F.X. Derivation of Infiltration Equation Using Systems Approach. Journal of Irrigation and Drainage Engineering, 116: 6: 307-320.
Sunli K., Sinha, M. and Wang, C. (2008). Artificial neural network prediction models for soil compaction and permeability. Geotechnical and Geological Engineering, 26: 47-64.
Tsanis, I.K. (2006). Modeling leachate contamination and remediation of groundwater at a landfill site. Water ResourManage, 20:109–132.
Zare Abyaneh, H., Bayat Varkeshi, M., Marofi, S., and Amiri Chayjan, R. (2010). Evaluation of artificial neural network and adaptive neuro fuzzy inference system in decreasing of reference evapotranspiration parameters. Water and Soil (Agr. Sci. and Thechnology), 24: 2. 297-305. (In Farsi)
Zare Abyaneh, H., Ghasemi, A., Bayat varkeshi, M., and Marofi, S. (2009). Assessment of Artificial Neural Network (ANN) in prediction of garlic evapotranspiration (ETC) with lysimeter in Hamedan. J. Water and Soil, 23: 3. 176-185. (In Farsi)
Zhang, C. S. and McGrath, D. (2004). Geostatistical and GIS analyses on soil organic carbon concentrations in grassland of southeastern Ireland from two different periods. Geoderma, 119(3-4): 261-275.