Pedotransfer functions based on nearest neighbour and neural networks  approach to estimate available water capacity of shrink-swell soils

Nitin Gorakh Patil; ARUN CHATURVEDI

doi:10.56093/ijas.v82i1.13867

Authors

Nitin Gorakh Patil National Bureau of Soil Survey and Land Use Planning, Amravati Road , Shankaranagar, Nagpur, Maharashtra 440 033
ARUN CHATURVEDI National Bureau of Soil Survey and Land Use Planning, Amravati Road , Shankaranagar, Nagpur, Maharashtra 440 033

https://doi.org/10.56093/ijas.v82i1.13867

Keywords:

Available water capacity, Clay soils, K nearest neighbour, Neural networks, Pedotransfer functions, VG function

Abstract

Point pedotransfer functions (PTF) were developed by nearest neighbour (kNN) algorithm as an alternative to widely used artificial neural networks (ANN) for prediction of field capacity, permanent wilting point, and available water capacity of the seasonally impounded clay soils in central India using the available dataset. They were compared with parametric PTFs to estimate Van Genuchten parameters. Basic soil properties (texture, bulk density and organic carbon content) were related to the properties of interest. The root mean square error (RMSE) in predictions of the three properties (FC, PWP, AWC) by kNN PTFs ranged from 0.0237 to 0.0279 m3/m3with an average of 0.0265 m3/m3. The ANN PTFs performed relatively better with average RMSE 0.0223 m3/m3 and a range of 0.0141 to 0.0295 m3/m3. Magnitude of RMSE was relatively higher in VG parametric PTFs (0.032 m3/m3) followed by kNN (0.0237 m3/m3) and ANN (0.0223 m3/m3) PTFs. kNN algorithm provided viable alternative to neural regression with additional benefit of flexibility in appending reference database.

Downloads

Download data is not yet available.

References

Borgesen C D and Schaap M. 2005. Point and parameter pedotransfer functions for water retention predictions for Danish soils. Geoderma (127): 1-2: 154–67.

Jana R B and Mohanty B. 2010 Enhancing PTFs with remotely sensed data for multi-scale soil water retention estimation. Journal of Hydrology 399 (3-4): 201–11.

Jain S K, Singh V P and Van Genuchten M. Th. 2004. Analysis of soil water retention data using artificial neural networks. Journal of Hydrologic Engineering 9: 415–20.

Nemes A, Roberts R T, Rawls W J, Pachepsky Ya A and van Genuchten M Th. 2008. Software to estimate -33 and -1500 kPa soil water retention using the non-parametric k-Nearest Neighbor technique. Environmental Modeliling and Software 23(2): 254–5.

Nemes, Rawls W J, Pachepsky Ya A and van Genuchten M Th. 2006a. Sensitivity Analysis of the Nonparametric Nearest Neighbor Technique to Estimate Soil Water Retention Vadose Zone Journal 5: 1222–35.

Nemes, Rawls W J and Pachepsky Y A. 2006b. Use of the nonparametric nearest neighbor approach to estimate soil hydraulic properties. Soil Science Society of America Journal 70: 327–36.

Patil N G and Rajput G S. 2009. Evaluation of water retention functions and computer program Rosetta in predicting soil water characteristics of seasonally impounded shrink-swell soils. Journal of Irrigation and Drainage Engineering 135 (3): 286–94.

Patil N G, Rajput G S, Nema R K and Singh R B. 2010. Calibration and evaluation of pedotransfer functions to estimate available water capacity of seasonally impounded shrink-swell soils of Central India. Archives of Agronomy and Soil Science 148 : 159–70.

Rawls W J, Ahuja L R and Brakensiek D L. 1992. Estimating soil hydraulic properties from soils data. (in) Indirect Methods for Estimating the Hydraulic Properties of Unsaturated Soils. Proceedings of International Workshop on Riverside, CA, pp. 329–40. M.Th. van Genuchten et al. (Eds). 11–13 October, 1989, University of California, Riverside.

Sharma Sanjay K, Mohanty Binayak P and Jianting Zhu. 2006. Including topography and vegetation attributes for developing pedotransfer functions. Soil Science Society of America Journal 70:c 1430–40.

Schaap M G, Feike J L, Martinus L, and Van Genuchten M Th. 2001. Rosetta a computer program for estimating soil hydraulic parameters with hierarchial pedotransfer functions. Journal of Hydrology 251: 163–76.

Tomar S S, Tembe G P, Shrma S K, Bhadauria U P S and Tomar V S. 1996. Improvement of physical conditions of black soils in Madhya Pradesh J N K K V, Jabalpur.

Van Genuchten M Th. 1980. A closed-form equation for predicting the hydraulic conductivity of unsaturated soils. Soil Science. Society of America. Journal 43: 892–8.

Williams R D, Ahuja L R and Naney J W. 1992. Comparison of methods to estimate soil water characteristics from texture, bulk density and limited data, Soil Science 153. 172–84.