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

Prediction Of Soil Moisture-Holding Capacity With Support Vector Machines In Dry Subhumid Tropics

J. Kaingo, S. Tumbo, N. Kihupi, B. Mbilinyi
Published 2018 · Mathematics

Save to my Library
Download PDF
Analyze on Scholarcy
Share
Soil moisture-holding capacity data are required in modelling agrohydrological functions of dry subhumid environments for sustainable crop yields. However, they are hardly sufficient and costly to measure. Mathematical models called pedotransfer functions (PTFs) that use soil physicochemical properties as inputs to estimate soil moisture-holding capacity are an attractive alternative but limited by specificity to pedoenvironments and regression methods. This study explored the support vector machines method in the development of PTFs (SVR-PTFs) for dry subhumid tropics. Comparison with the multiple linear regression method (MLR-PTFs) was done using a soil dataset containing 296 samples of measured moisture content and soil physicochemical properties. Developed SVR-PTFs have a tendency to underestimate moisture content with the root-mean-square error between 0.037 and 0.042 cm3·cm−3 and coefficients of determination (R2) between 56.2% and 67.9%. The SVR-PTFs were marginally better than MLR-PTFs and had better accuracy than published SVR-PTFs. It is held that the adoption of the linear kernel in the calibration process of SVR-PTFs influenced their performance.
This paper references
10.1080/10691898.2011.11889611
Measuring Skewness: A Forgotten Statistic?
D. Doane (2011)
10.3923/AJPS.2004.679.682
Pedotransfer Functions for Predicting Three Points on the Moisture Characteristic Curve of a Zimbabwean Soil
F. Mugabe (2004)
10.1155/2014/740521
Modelling Soil Water Retention Using Support Vector Machines with Genetic Algorithm Optimisation
K. Lamorski (2014)
10.2136/VZJ2015.09.0131
Modeling Soil Processes: Review, Key Challenges, and New Perspectives
H. Vereecken (2016)
International Plant Nutrition Institute (IPNI)
(2011)
10.9734/IJPSS/2015/17147
Morphology, Physicochemical Characteristics and Land Suitability in the Western Highlands of Cameroon
D. Tsozué (2015)
Soilhydraulic properties estimation by using PTFs in a northeastern semiarid zone catchment, Brazil
L.F.F. Moreira (2004)
10.1111/ejss.12192
New generation of hydraulic pedotransfer functions for Europe
B. Tóth (2015)
10.2136/VZJ2012.0123
Prediction of Water Retention of Soils from the Humid Tropics by the Nonparametric k-Nearest Neighbor Approach
Y. Botula (2013)
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)
10.1071/SR13256
Using categorical soil structure information to improve soil water retention estimates of tropical delta soils
Phuong Minh Nguyen (2014)
10.2136/SSSAJ2005.0087
Including Topography and Vegetation Attributes for Developing Pedotransfer Functions
S. Sharma (2006)
10.2136/SSSAJ2007.0280N
Using Support Vector Machines to Develop Pedotransfer Functions for Water Retention of Soils in Poland
K. Lamorski (2008)
10.17221/113/2015-SWR
Comparing different data preprocessing methods for monitoring soil heavy metals based on soil spectral features.
A. Gholizadeh (2016)
Soil Mapping and Web-GIS Development for Trans-Sec Project: Final Report
J Kaingo (2016)
10.1039/c0an00387e
Support vector machine regression (SVR/LS-SVM)--an alternative to neural networks (ANN) for analytical chemistry? Comparison of nonlinear methods on near infrared (NIR) spectroscopy data.
Roman M. Balabin (2011)
10.1007/3-540-31211-0_2
Particle-size analysis.
I. C. Edmundson (1967)
Pedotransfer Functions for the Hydraulic Properties of Layered Soils
Tekin Oztekin (2007)
10.2136/SSSAJ2006.0343
Bimodal Zone of the Soil Textural Triangle: Common in Tropical and Subtropical Regions
D. D. Condappa (2008)
A physically-based model to predict the water retention curve from basic geotechnical properties
M. Aubertin (2003)
10.1016/J.GEODERMA.2012.11.021
Soil hydraulic information for river basin studies in semi-arid regions
J.H.M. Wosten (2013)
10.1002/HYP.9398
Moisture characteristics and their point pedotransfer functions for coarse‐textured tropical soils differing in structural degradation status
S. E. Obalum (2013)
10.1016/J.JHYDROL.2012.03.036
A pseudo-continuous neural network approach for developing water retention pedotransfer functions with limited data
A. Haghverdi (2012)
10.1029/2000WR900328
Hydraulic conductivity of variably saturated porous media: Film and corner flow in angular pore space
M. Tuller (2001)
10.1371/journal.pone.0153673
Improving the Spatial Prediction of Soil Organic Carbon Stocks in a Complex Tropical Mountain Landscape by Methodological Specifications in Machine Learning Approaches
M. Ließ (2016)
Cation exchange: a review
International Plant Nutrition Institute IPNI (2011)
Soil-water interaction at high soil suction
Morteza Khorshidi (2015)
Guidelines for Soil Description
Agriculture Food (2006)
Modelsfor indirect estimation of soil hydraulic properties
M. G. Schaap (2005)
10.2136/SSSAJ1999.6361748X
Accuracy and reliability of pedotransfer functions as affected by grouping soils
Y. Pachepsky (1999)
A Practical Guide to Support Vector Classication
Chih-Wei Hsu (2008)
10.1109/TITS.2004.837813
Travel-time prediction with support vector regression
Chun-Hsin Wu (2004)
A Language and Environment for Statistical Computing, R Foundation for Statistical Computing, Vienna, Austria, 2016, http://www.R-project.org
R R Core Team (2016)
10.1556/0088.2015.64.2.4
Why do they keep rejecting my manuscript — do’s and don’ts and new horizons in pedotransfer studies
A. Nemeş (2015)
10.2136/VZJ2010.0045
Using pedotransfer functions to estimate the van Genuchten-Mualem Soil Hydraulic Properties: a review.
H. Vereecken (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)
Bulk density
G. R. Blake (1986)
10.1139/T03-054
A model to predict the water retention curve from basic geotechnical properties
M. Aubertin (2003)
10.1111/EJSS.12345
Enhanced pedotransfer functions with support vector machines to predict water retention of calcareous soil
Muhammed Khlosi (2016)
10.2136/SSSABOOKSER5.3.C34
Total carbon organic carbon and organic matter
D. Nelson (1983)
10.2136/SSSAJ2008.0021
Development of Pedotransfer Functions for Estimation of Soil Hydraulic Parameters using Support Vector Machines
N. Twarakavi (2009)
10.1097/01.PSY.0000127692.23278.A9
What You See May Not Be What You Get: A Brief, Nontechnical Introduction to Overfitting in Regression-Type Models
M. Babyak (2004)
10.1061/(ASCE)IR.1943-4774.0001094
Mapping Soil Water Retention on Agricultural Lands in Central and Eastern Parts of the Black Sea Region in Turkey
Markéta Miháliková (2016)
10.1016/J.EARSCIREV.2011.01.005
Predicting soil properties in the tropics
B. Minasny (2011)
Soil Mapping and Web-GIS Development for Trans-Sec Project: Final Report, Sokoine Univesity of Agriculture, Morogoro, Tanzania, 2016
J. Kaingo (2016)
10.1016/J.GEODERMA.2014.02.026
Revisiting the pseudo continuous pedotransfer function concept: impact of data quality and data mining method
A. Haghverdi (2014)
e1071: misc functions of the department of statistics, probability theory group (formerly: E1071), TU Wien. Applied and Environmental Soil Science 9 R package version 1.6-7
D. Meyer (2015)
10.2136/VZJ2006.0131
Artificial Neural Network Estimation of Saturated Hydraulic Conductivity
W. A. Agyare (2007)
10.1155/2014/478569
Evaluation Models for Soil Nutrient Based on Support Vector Machine and Artificial Neural Networks
H. Li (2014)
10.1016/J.GEODERMA.2009.11.005
Soil type classification and estimation of soil properties using support vector machines
M. Kovacevic (2010)
10.2134/AGRONJ2008.0140S
AquaCrop — The FAO Crop Model to Simulate Yield Response to Water: II. Main Algorithms and Software Description
D. Raes (2009)
10.1007/s11104-010-0410-6
Soil water availability for plants as quantified by conventional available water, least limiting water range and integral water capacity
Hossein Asgarzadeh (2010)
Using Pedotransfer Functions (PTFs) to Estimate Soil Water Retention Characteristics (SWRCs) in the Tropics for Sustainable Soil Water Management: Tanzania Case Study
M. Mdemu (2002)
10.5897/AJAR11.199
Forage yields and qualities of some triticale (Xtriticosecale Wittmack) genotypes
M. Sürmen (2011)
10.1371/journal.pcbi.1000173
Support Vector Machines and Kernels for Computational Biology
A. Ben-Hur (2008)
10.2136/SSSAJ2005.0128
Use of the Nonparametric Nearest Neighbor Approach to Estimate Soil Hydraulic Properties
A. Nemes (2006)
10.5539/JGG.V7N1P1
Evaluation and Development of Pedotransfer Functions for Estimating Soil Water Holding Capacity in the Tropics: The Case Of Sokoine University of Agriculture Farm in Morogoro, Tanzania
M. Mdemu (2015)
10.1016/S1464-1909(99)00091-X
Assessment and development of pedotransfer functions for semi-arid sub-Saharan Africa.
M. Young (1999)
10.1037/1082-989X.2.3.292
On the meaning and use of kurtosis.
L. Decarlo (1997)
Estimating soil specific surface area using the summation of the number of spherical particles and geometric mean particle-size diameter
Hamid Reza Fooladmand (2011)



This paper is referenced by
Semantic Scholar Logo Some data provided by SemanticScholar