Online citations, reference lists, and bibliographies.
Please confirm you are human
(Sign Up for free to never see this)
← Back to Search

Use Of The Nonparametric Nearest Neighbor Approach To Estimate Soil Hydraulic Properties

A. Nemes, W. Rawls, Y. Pachepsky
Published 2006 · Mathematics

Save to my Library
Download PDF
Analyze on Scholarcy
Share
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 233- and 21500-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 (Db), 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 kNN 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.
This paper references
Comparison of pedotransfer functions to compute water holding capacity using the Van Genuchten model in inorganic soils
B. Imam (1999)
MONOGRAPHS ON STATISTICS AND APPLIED PROBABILITY
V. Isham (2007)
10.1029/2002WR001593
Flood quantiles in a changing climate: Seasonal forecasts and causal relations
A. Sankarasubramanian (2003)
10.1029/2003WR002378
A comparative study of Markov chain Monte Carlo methods for conceptual rainfall‐runoff modeling
L. Marshall (2004)
Nearest-Neighbor methods with application to rainfall/runoff prediction
S Yakowitz (1987)
10.1016/S0016-7061(99)00014-2
Evaluation of different procedures to interpolate particle-size distributions to achieve compatibility within soil databases
A. Nemes (1999)
10.2307/2532810
An Introduction to the Bootstrap.
S. T. Buckland (1994)
10.2136/SSSAJ2003.1093
Functional evaluation of pedotransfer functions derived from different scales of data collection
A. Nemes (2003)
Reproduced from Soil Science Society of America Journal. Published by Soil Science Society of America. All copyrights reserved
Evaluation of different procedures to interpolate the cumulative particle-size distribution to achieve compatibility within a soil database
A Nemes (1999)
10.1007/978-1-4612-3144-8_5
Estimating Soil Water Retention from Soil Physical Properties and Characteristics
W. Rawls (1991)
10.2136/SSSAJ2000.643843X
Improved Prediction of Unsaturated Hydraulic Conductivity with the Mualem‐van Genuchten Model
M. Schaap (2000)
10.1016/0304-4149(93)90050-E
Nearest neighbor regression estimation for null-recurrent Markov time series
S. Yakowitz (1993)
National characterization data
Soil Survey Staff. (1997)
Evaluation of pedotransfer functions
M. Donatelli (2004)
10.1029/97WR02429
Disaggregation Procedures for Stochastic Hydrology Based on Nonparametric Density Estimation
D. Tarboton (1998)
10.2136/SSSAJ1998.03615995006200040001X
Neural network analysis for hierarchical prediction of soil hydraulic properties
M. Schaap (1998)
10.2136/SSSAJ1993.03615995005700040035X
Evaluation of Pedo-Transfer Functions
O. Tietje (1993)
10.1016/S0016-7061(99)00061-0
Comparison of different approaches to the development of pedotransfer functions for water-retention curves
B. Minasny (1999)
10.2136/SSSAJ1996.03615995006000060018X
Testing an Artificial Neural Network for Predicting Soil Hydraulic Conductivity
S. Tamari (1996)
10.1007/3-540-63233-6_515
Examining Locally Varying Weights for Nearest Neighbor Algorithms
N. Howe (1997)
10.1029/WR023I007P01300
Nearest‐neighbor methods for nonparametric rainfall‐runoff forecasting
M. Karlsson (1987)
Soil Survey Staff. 1997. National characterization data. Soil Survey Laboratory, National Soil Survey Center, and Natural Resources Conservation Service
10.1029/2003WR002747
A resampling procedure for generating conditioned daily weather sequences
M. Clark (2004)
Nearest neighbor (NN) norms: NN pattern classification techniques
B. V. Dasarathy (1991)
10.1016/S1161-0301(02)00098-9
Wading through a swamp of complete confusion: how to choose a method for estimating soil water retention parameters for crop models
A. Gijsman (2002)
Locally weighed learning
C G Atkeson (1997)
10.2136/SSSAJ1995.03615995005900040027X
Evaluation of Soil Water Retention Models Based on Basic Soil Physical Properties
J. Kern (1995)
10.1029/2003WR002570
A nonparametric model for stochastic generation of daily rainfall amounts
T. I. Harrold (2003)
10.1029/96WR00565
A Nonparametric Wet/Dry Spell Model for Resampling Daily Precipitation
Upmanu Lall (1996)
10.2136/sssaj2002.1407a
The Neuro-m Method for Fitting Neural Network Parametric Pedotransfer Functions
B. Minasny (2002)
10.1016/S0022-1694(01)00466-8
ROSETTA: a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions
M. Schaap (2001)
10.2136/SSSAJ1996.03615995006000030007X
Artificial Neural Networks to Estimate Soil Water Retention from Easily Measurable Data
Y. Pachepsky (1996)
10.1097/00010694-199810000-00001
Database-related accuracy and uncertainty of pedotransfer functions
M. Schaap (1998)
10.1016/S0022-1694(01)00464-4
Pedotransfer functions: bridging the gap between available basic soil data and missing soil hydraulic characteristics
J. Wösten (2001)
Neurocomputing
R Hecht-Nielsen (1990)
Neural network toolbox manual. MathWorks Inc
H Demuth (1992)
10.1029/95WR02966
A Nearest Neighbor Bootstrap For Resampling Hydrologic Time Series
Upmanu Lall (1996)
10.1029/2000WR900049
Multisite disaggregation of monthly to daily streamflow
D. N. Kumar (2000)
10.1029/96WR02839
Streamflow simulation: A nonparametric approach
A. Sharma (1997)
10.1046/J.1365-2389.1999.00247.X
Neural network models to predict soil water retention
E.J.W. Koekkoek (1997)
Concept learning and flexible weighting
D W Aha (1992)
Neural network toolbox manual
H. Demuth (1992)
Neural Networks: A Comprehensive Foundation
S. Hyakin (1994)
10.1016/S0378-4754(99)00016-6
A nonparametric approach for daily rainfall simulation
A. Sharma (1999)
10.1029/2003WR002182
A nonparametric model for stochastic generation of daily rainfall occurrence
T. I. Harrold (2003)
10.1029/2002WR001769
A technique for generating regional climate scenarios using a nearest‐neighbor algorithm
D. Yates (2003)
10.1007/978-94-009-4792-4_9
Nearest Neighbor Methods for Time Series, with Application to Rainfall/Runoff Prediction
S. Yakowitz (1987)
Nearest-neighbor estimation for null-recurrent Markov time series
S Yakowitz (1993)
10.1061/(ASCE)1084-0699(1996)1:1(33)
Nonhomogeneous Markov Model for Daily Precipitation
B. Rajagopalan (1996)
10.1029/2001WR000953
A nonparametric approach for representing interannual dependence in monthly streamflow sequences
Ashish Sharma (2002)
10.1023/A:1006593614256
A Review and Empirical Evaluation of Feature Weighting Methods for a Class of Lazy Learning Algorithms
D. Wettschereck (2004)
10.2136/SSSAJ1996.03615995006000030013X
Statistical Hydraulic Conductivity Models and Scaling of Capillary Phenomena in Porous Media
V. Snyder (1996)
10.1023/A:1006559212014
Locally Weighted Learning
C. Atkeson (2004)
10.2136/SSSAJ1980.03615995004400050002X
A closed-form equation for predicting the hydraulic conductivity of unsaturated soils
Van Genuchten (1980)
10.2136/SSSAJ2001.653638X
Evaluation of Pedotransfer Functions for Predicting the Soil Moisture Retention Curve
W. Cornelis (2001)
10.1029/2002WR001373
Seasonal to interannual ensemble streamflow forecasts for Ceara
F. O. Souza (2003)
10.1007/BF02428426
Multivariate nonparametric resampling scheme for generation of daily weather variables
B. Rajagopalan (1997)
10.13031/2013.17623
DYNAMIC NEAREST-NEIGHBOR METHOD FOR ESTIMATING SOIL WATER PARAMETERS
S. Jagtap (2004)



This paper is referenced by
10.1080/08941920802064687
Using Extant Data to Determine Management Direction in Family Forests
I. Majumdar (2009)
10.1016/J.BIOSYSTEMSENG.2016.10.013
Comparison of statistical regression and data-mining techniques in estimating soil water retention of tropical delta soils.
Phuong Minh Nguyen (2017)
10.5194/HESS-14-251-2010
Uncertainty in the determination of soil hydraulic parameters and its influence on the performance of two hydrological models of different complexity
G. Baroni (2009)
10.1016/J.AGRFORMET.2009.09.006
Validation of soil moisture simulations from the PAMII model, and an assessment of their sensitivity to uncertainties in soil hydraulic parameters
J. Brimelow (2010)
10.1016/j.envsoft.2007.09.011
Weather analogue: A tool for real-time prediction of daily weather data realizations based on a modified k-nearest neighbor approach
M. Bannayan (2008)
10.7282/T3TD9XH0
A MEASURE OF SOIL STRUCTURE DERIVED FROM WATER RETENTION PROPERTIES: A KULLBACK-LEIBLER DISTANCE APPROACH
Sung Won Yoon (2009)
10.1002/2016WR019533
An estimation of the main wetting branch of the soil water retention curve based on its main drying branch using the machine learning method
K. Lamorski (2017)
10.3390/su11236669
Extracting Knowledge from Big Data for Sustainability: A Comparison of Machine Learning Techniques
R. Garg (2019)
10.2136/VZJ2010.0045
Using pedotransfer functions to estimate the van Genuchten-Mualem Soil Hydraulic Properties: a review.
H. Vereecken (2010)
HNF-34880-FP Revision 0 Development of Vadose Zone Hydraulic Parameter Values
Gerald Hans. Nieder-Westermann (2008)
10.1080/15324982.2015.1046092
Prediction of soil surface salinity in arid region of central Iran using auxiliary variables and genetic programming
R. Taghizadeh-Mehrjardi (2016)
10.1590/S0100-06832014000300001
Pedotransfer functions to predict water retention for soils of the humid tropics: a review
Y. Botula (2014)
10.1016/J.GEODERMA.2013.06.006
Assessing forest soil base cation status and availability using lake and stream sediment geochemistry: A case study in Quebec (Canada)
É. Thiffault (2013)
10.1016/j.geoderma.2020.114479
Quantification of macropore flow in Danish soils using near-saturated hydraulic properties
A. M. Kotlar (2020)
Point pedotransfer functions for estimating soil water retention curve
B. Ghanbarian-Alavijeh (2010)
10.1016/J.JHYDROL.2015.04.014
Impact of regression methods on improved effects of soil structure on soil water retention estimates
Phuong Minh Nguyen (2015)
10.1007/978-3-319-63439-5_7
Pedotransfer Functions and Soil Inference Systems
J. Padarian (2018)
10.1016/J.FCR.2009.01.007
Using pattern recognition for estimating cultivar coefficients of a
M. B. Aval (2009)
10.2136/SSSAJ2008.0298
Evaluation of the Rawls et al. (1982) Pedotransfer Functions for their Applicability at the U.S. National Scale Large scale environmental impact studies typically involve the use of simulation models and
A. Nemes (2009)
10.7745/KJSSF.2011.44.5.944
Use of the Quantitatively Transformed Field Soil Structure Description of the US National Pedon Characterization Database to Improve Soil Pedotransfer Function
Sung Won Yoon (2011)
Comparative evaluation of nearest neighbor and neural networks approach to estimate soil water retention at field capacity and permanent wilting point
N. Patil (2013)
10.1029/2018jg004589
The Sensitivity of North American Terrestrial Carbon Fluxes to Spatial and Temporal Variation in Soil Moisture: An Analysis Using Radar‐Derived Estimates of Root Zone Soil Moisture
Ke Zhang (2019)
10.1016/j.apr.2020.08.029
Evaluation of machine learning models for predicting the temporal variations of dust storm index in arid regions of Iran
Z. Ebrahimi-Khusfi (2020)
10.1080/15324982.2011.631686
Influencing Factors and Prediction of Hydraulic Conductivity in Fine-Textured Alkaline Soils
F. Candemir (2012)
10.2136/SSSAJ2016.12.0421
A soil bulk density pedotransfer function based on machine learning: a case study with the NCSS soil characterization database.
A. Ramcharan (2017)
10.1155/2018/9263296
Prediction of Soil Moisture-Holding Capacity with Support Vector Machines in Dry Subhumid Tropics
J. Kaingo (2018)
10.13031/TRANS.58.10709
Parameterization Guidelines and Considerations for Hydrologic Models
R. Malone (2015)
10.1029/2018WR024357
Using Machine Learning for Prediction of Saturated Hydraulic Conductivity and Its Sensitivity to Soil Structural Perturbations
S. N. Araya (2019)
10.1016/J.STILL.2019.02.009
Pedotransfer functions to estimate hydraulic properties of tropical Sri Lankan soils
M. Gunarathna (2019)
10.1016/j.jhydrol.2020.125770
Introducing a Kriging-based Gaussian Process approach in pedotransfer functions: Evaluation for the prediction of soil water retention with temperate and tropical datasets
J. D. Pue (2020)
Evaluation of the cropland modelling component of the U . S . national scale CEAP project : estimation of soil hydraulic properties
A. Nemes (2008)
10.1007/s12665-015-4246-5
Capability of different interpolation models and pedotransfer functions to estimate soil hydraulic properties in Büyükçay Watershed
Markéta Miháliková (2015)
See more
Semantic Scholar Logo Some data provided by SemanticScholar