HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Figures Only Full Text Free Full Text (PDF) Free Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Similar articles in ISI Web of Science Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via ISI Web of Science (2) Citing Articles via Google Scholar Google Scholar Articles by Nemes, A. Articles by van Genuchten, M. Th. Search for Related Content PubMed Articles by Nemes, A. Articles by van Genuchten, M. Th. GeoRef GeoRef Citation Agricola Articles by Nemes, A. Articles by van Genuchten, M. Th. Related Collections Soil Hydrology Pedotransfer Functions Soil Physics

ORIGINAL RESEARCH

Sensitivity Analysis of the Nonparametric Nearest Neighbor Technique to Estimate Soil Water Retention

^a Univ. of California, Dep. of Environmental Sciences, Riverside, CA 92521
^b USDA-ARS Hydrology and Remote Sensing Lab., 10300 Baltimore Ave., Bldg. 007, BARC-West, Beltsville, MD 20705
^c USDA-ARS Environmental Microbial Safety Lab., Powder Mill Road, Bldg. 173, BARC-East, Beltsville, MD 20705
^d USDA-ARS George E. Brown Jr. Salinity Lab., 450 West Big Springs Rd., Riverside, CA 92501
^* Corresponding author (anemes{at}hydrolab.arsusda.gov)

Received 25 January 2006.

A k-nearest neighbor (k-NN) nonparametric algorithm variant was earlier applied successfully to estimate soil water retention. In this study, we tested the sensitivity of that k-NN variant to different data and algorithm options, such as: (i) estimations made to soils with differing distribution of properties; (ii) the use of different sample weighting methods; (iii) the number of ensembles we developed; (iv) data density in the reference data set; (v) the presence of outliers in the reference data set; (vi) unequal weighting of input attributes; and (vii) the addition of locally specific data to the reference data set. We used a hierarchical set of input attributes and data set sizes to develop ensembles of predictions using multiple randomized subset selections. The k-NN technique performed comparably well as neural network models developed on the same data. Using >50 ensemble members did not improve the results any further. The k-NN technique showed little sensitivity to the choice of sample weighting methods and to suboptimal weighting of input attributes. Differences in data density in parts of the reference data set did not substantially impact estimation errors. Estimations substantially improved for locally specific data when some local samples were included in the reference data set, while estimations for other samples remained almost unaffected. The k-NN technique shows a large degree of stability and insensitivity to different settings and options, can easily adopt new data without the need to redevelop equations, and is an effective alternative to other techniques to estimate soil water retention.

Abbreviations: OM, organic matter • SSC, sand, silt, and clay contents (soil texture) • NNet, neural network • k-NN, k-nearest neighbor technique • PTF, pedotransfer function • RMSR, root mean squared residual • 33, water retention at –33kPa matric potential • 1500, water retention at –1500 kPa matric potential