Use of the nonparametric nearest neighbor approach to estimate soil hydraulic properties

• Published in: Soil Science Society of America journal Vol. 70; no. 2; pp. 327 - 336
• Main Authors: Nemes, A, Rawls, W.J, Pachepsky, Y.A
• Format: Journal Article
• Language: English
• Published: Madison Soil Science Society 01.03.2006; Soil Science Society of America; American Society of Agronomy
• Subjects: Agricultural production; Agronomy. Soil science and plant productions; Algorithms; Biological and medical sciences; bulk density; Earth sciences; Earth, ocean, space; estimation; Exact sciences and technology; Fundamental and applied biological sciences. Psychology; Hydraulic properties; Hydrogeology; Hydrology; Hydrology. Hydrogeology; mathematical models; model validation; Neural networks; Organic matter; pedotransfer functions; Physical properties; Physics, chemistry, biochemistry and biology of agricultural and forest soils; soil density; soil matric potential; soil organic matter; Soil properties; Soil science; Soil sciences; Soil texture; soil water characteristic; soil water retention; Water and solute dynamics; Lazy programming; physical properties; Nearest neighbour; mathematical models; Characteristic; neural networks; Property of soil; Non parametric method; Statistical estimation; Earth science; hydrogeology; soil moisture retention curve; Pedotransfer function; Soil water properties; Scientific computation; Applied mathematics; Soil science; statistical analysis; Learning algorithm; Water holding capacity; Hydraulic properties
• ISSN: 0361-5995; 1435-0661
• DOI: 10.2136/sssaj2005.0128

Nonparametric approaches are being used in various fields to address classification type problems, as well as to estimate continuous variables. One type of the nonparametric lazy learning algorithms, a k-nearest neighbor (k-NN) algorithm has been applied to estimate water retention at -33- and -1500-kPa matric potentials. Performance of the algorithm has subsequently been tested against estimations made by a neural network (NNet) model, developed using the same data and input soil attributes. We used a hierarchical set of inputs using soil texture, bulk density (D(b)), and organic matter (OM) content to avoid possible bias toward one set of inputs, and varied the size of the data set used to develop the NNet models and to run the k-NN estimation algorithms. Different 'design-parameter' settings, analogous to model parameters have been optimized. The k-NN technique showed little sensitivity to potential suboptimal settings in terms of how many nearest soils were selected and how those were weighed while formulating the output of the algorithm, as long as extremes were avoided. The optimal settings were, however, dependent on the size of the development/reference data set. The nonparametric k-NN technique performed mostly equally well with the NNet models, in terms of root-mean-squared residuals (RMSRs) and mean residuals (MRs). Gradual reduction of the data set size from 1600 to 100 resulted in only a slight loss of accuracy for both the k-NN and NNet approaches. The k-NN technique is a competitive alternative to other techniques to develop pedotransfer functions (PTFs), especially since redevelopment of PTFs is not necessarily needed as new data become available.