Comparison and application of random forest, chaid and geostatistics models in predicting soil saturated hydraulic conductivity

Document Type : Research Article


1 Associate Professor, Department of Water Engineering, Faculty of Water and Soil, University of Zabol. Zabol, Iran

2 Graduate student, Department of Water Engineering, Faculty of Water and Soil, University of Zabol. Zabol, Iran

3 Undergraduate student, Department of Water Engineering, Faculty of Water and Soil, University of Zabol. Zabol, Iran



Soil saturated hydraulic conductivity (Ks) is one of the important factors involved in water, soil, and agricultural sciences. Ks measurement is important for solute and water movement modeling and, in turn, is costly and time consuming. It is also impractical to spatially and temporarily measure the Ks in large scale studies. This parameter can be estimated using early soil parameters. The present research was conducted in order to predict the hydraulic conductivity of soil saturation using random forest, chaid and geostatistical methods in Hirmand city. For this purpose, 130 soil samples were collected from the surface (0-30 cm) and transferred to the laboratory for testing and analysis. In the laboratory, the parameters of hydraulic conductivity of soil saturation, soil texture, organic carbon, acidity, electrical conductivity and Percentage of lime were measured. It was then estimated using measurement parameters and using CHAID, Random Forest and geostatistics models. 20 different patterns of the combination of soil moisture parameters were considered as input to the Chaid model and random forest. Among the different combinations, the best combination was selected based on lower MAE and higher R. The results showed that the random forest model with the highest R2 (0.98) and the lowest MAE (0.0019) is the best model for predicting the saturated hydraulic conductivity of soil in Hirmand region. The results of zoning showed that the amount of saturated hydraulic conductivity of the soil was higher in the west, center and northeast than in other places.


Main Subjects

  • Norouzian Azizi Z, Qajarspanlou M, Emadi S.M, Sadegh-zadeh F. Evaluation of regression models and artificial neural network in estimating hydraulic conductivity of soil saturation in Mazandaran. Soil Research,2016; 31(1):76-88. [Persian].
  • Bouma J. Using soil survey data for quantitative land evaluation. Advances Soil Science. 1989;9: 177–213.
  • Wosten J.H.M, Pachepsky Ya.A, Rawls W.J. Pedotransfer functions: bridging the gap between available basic soil data and missing soil hydraulic characteristics. J. Hydrol. 2001;251: 123–150.
  • Rezaei Arshad R, Sayad G, Mazloum M, Sharfa M, Jafarnjadi A. Comparison of artificial neural network and regression methods for predicting saturated hydraulic conductivity of soils in Khuzestan province. Agricultural Sciences and Techniques and Natural Resources,2012; 16(60):107-117. [Persian].
  • Sobieraj J.A, Elsenbeer H, Veressy R.A. Pedotransfer functions for estimating saturated hydraulic conductivity implications for modeling stormflow generation. J. Hydrol.2001; 251: 202–220.
  • Bijan A, Piri H, Tabatabai S.M, Piri J. Comparison and application of artificial neural network, support vector machine and decision tree in predicting saturated hydraulic conductivity of soil (case study: Hirmand city). Watershed Management, 2022;25:74-85. [Persian].
  • Rodriguez V, Ghimire B, Rogan J, Chica Olmo M, Rigol-Sánchez J.P. An assessment of the effectiveness of a Random Forest classifier for land-cover classification. ISPRS Journal of Photogram Remote Sens. 2012; 67: 9 -104
  • Breiman L. Application and analysis of random forests and machine learning. Journal of Water Management.2001; 15(1): 5-32.
  • Norouzi Ghoshbalagh H, Nadiri A, Asghari Moghaddam A, Qarahkhani M. Comparison of the efficiency of artificial neural networks, fuzzy logic and random forest in estimating the aquifer transfer capability of Malekan plain. Echo Hydrology. 2018;5(3): 739-751 [Persian].
  • Siasar H, Honar T. The application of support vector machine, chaid and random forest models in estimating daily reference transpiration evaporation in the north of Sistan and Baluchistan province. Iran Irrigation and Drainage.2018 ;2(13):378-388. [Persian].
  • Watt M, Palmer S. Use of regression kriging to develop a Carbon: Nitrogen ratio surface for New Zealand. Geoderma.2010;183:49–57.
  • Piri H, Mobaraki M, Siaser P. Temporal and spatial modeling of underground water level in Bushehr plain using artificial intelligence and geostatistics. Watershed Management.2023;13(26):58-68. [Persian].
  • Piri H, Mobaraki M. Comparison of Artificial Intelligence and Geostatistical Methods in Soil Surface Salinity Prediction (Case study: Ghorghori of Hirmand city). Environ. Water Eng.2022;8(3): 551-537. [Persian].
  • Rezaei M, Devatgar N, Tajdari Kh, Abolpur b. Investigating the spatial changes of some quality indicators of underground waters in Gilan province using geostatistics. water and soil. 2018;24:932-941. [Persian].
  • Jahantigh M, Jahantigh M. Study effect of flood productivity on vegetation changes using field work and Landsat satellite images (Case study: Shandak of Sistan region), Journal of RS & GIS for Natural Resources. 2019;10(4), 57-73. [Persian].
  • Gee G. W. Particle-size analysis. In: Warren, A.D. Eds. Methods of Soil Analysis. Part 4. Physical Methods. Soil Sci. Soc. Am. Inc. 2002; 5:255-295.
  • Najibzadeh N, Ghaderi K, Ahmadi M.M. Utilization of support vector regression methods and artificial neural network in runoff precipitation modeling (Case study: Saffarud Dam catchment). Irrigation and Drainage of Iran.2009;6(13):1709-1720[Persian].


  • Nelson D. W, Sommer L. E.Total carbon, organic carbon, ad organic matter.Soc. Agron., Madison. 1982; pp. 539–579.
  • Rhoads J.D. Cation exchange capacity, In; A.C. Page (ed) Methods of soil Analysis, part 2, Am. Soc. Agron,, 1986;9: 149-158.
  • Ramaswami M, Bhaskaran R. A. CHAID based performance prediction model in educational data mining. arXiv preprint arXiv:2010;1002.1144.
  • Kisi O, Onur G, Semih D, Zounemat-Kermani M. Daily pan evaporation modeling using chi-squared automatic interaction detector, neural networks, classification and regression tree. Computers and Electronics in Agriculture. 2016; 122 (112-117)
  • Quinlan JR. Induction of decision trees. Journal of Machine Learning. 1986; 1(1): 81-106.
  • Soleimani K, Habibnejad M, Abkar A, Bani Asadi M. Analysis of depth, surface and continuity curves using geostatistical methods in arid and semi-arid rainfall areas (D.A.D) Case study: Sirizjan salt pan). Desert Magazine.2006 ;11(1):32-41. [Persian]
  • Breiman L. Application and analysis of random forests and machine learning. Journal of Water Management.2001; 15(1): 5-32
  • Hassani Pak A. Geostatistics (Geostatistics). University of Tehran Press.2007. p 325.


  • Gholami Sh, Hosseini S.M, Mohammadi J, Mahini A.S. Spatial variability of soil macrofauna biomass and soil properties in riparian forest of Karkhe river. Journal of Water and Soil. 2010; 25(2)248-257 [Persian].
  • Foroughifar H, Jafarzadah A.A, Torabi Gelsefidi H, Aliasgharzadah N, Toomanian N, Davatgar N. Spatial variations of surface soil physical and chemical properties on different landforms of Tabriz plain. Journal of Soil and Water Science. 2010;21(3):1-21 [Persian].
  • Momtaz H R, Jafarzadah AA, Torabi H, Oustan Sh, Samadi A, Davatgar N, et al. An assessment of the variation in soil properties within and between Landforms in Amol region. Iran. Geoderma. 2009;149: 10-18.
  • Ahmadi A, Palizwanzand p. Palizwanzand H. Estimation of hydraulic conductivity of soil saturation using gene expression programming and ridge regression (Case study in East Azarbaijan province). Iranian Soil and Water Research. 2017;48 (5):1087-1095 [Persian].
  • Indirect estimation of near-saturated hydraulic conductivity from readily available soil information. Geoderma. 2002;108, 1-17.
  • Shi J, Wang H, Xu J, Wu J, Liu X, Zhu H, Yu C. Spatial distribution of heavy metals in soils: a case study of Changxing. China. Environ Geol. 2007 ; (52):1-10.
Volume 10, Issue 2
July 2023
Pages 173-185
  • Receive Date: 01 January 2023
  • Revise Date: 31 January 2023
  • Accept Date: 03 March 2023
  • First Publish Date: 04 April 2023
  • Publish Date: 22 June 2023