Summary
In the range of volumetric water content, θ, from about 0.12 cm3 cm–3 to saturation the relation between bulk electrical conductivity, Cb, and bulk electrical permittivity, ε, of mineral soils was observed to be linear. The partial derivative ∂Cb/∂ε appeared independent of the moisture content and directly proportional to soil salinity. We found that the variable Xs = ∂Cb/∂ε determined from in situ measurements of Cb(θ > 0.2) and ε(θ > 0.2) can be considered as an index of soil salinity, and we call it the ‘salinity index’. Knowing the index and sand content for a given soil we could calculate the electrical conductivity of the soil water, Cw, which is a widely accepted measure of soil salinity. The two variables from which the salinity index can be calculated, i.e. Cb and ε, can be read simultaneously from the same sensor by time‐domain reflectometry.
Quantities and symbols
a constant /dS m–1
b constant
c constant /dS m–1
C
b electrical conductivity of bulk soil /dS m–1
C
b′ constant equal to 0.08 dS m–1
C
s electrical conductivity of a solution used to moisten soil samples /dS m–1
C
w electrical conductivity of soil water defined as the soil salinity /dS m–1
C
wref reference salinity (that truly existing) resulting from the procedure of moistening samples, expressed as Cs + Cr/dS m–1
C
r baseline value of Cs due to residual soluble salts present in the soil /dS m–1
d constant
D dry soil bulk density /g cm–3
l slope
r ratio
S sand content /% by weight
t time /s
X
s salinity index /dS m–1
X
si initial salinity index when distilled water is used to moisten soil samples /dS m–1
Y a moisture‐independent salinity‐dependent variable /dS m–1
z coordinate along direction of flow of the soil solution
ε′ constant equal to 6.2
ε relative bulk electrical permittivity (dielectric constant) of the soil
θ volumetric water content determined thermogravimetrically using oven‐drying /cm3 cm–3
Pedotransfer functions (PTFs), which estimate soil hydraulic parameters from easy to measure soil properties, are an important data source for hydrologic modeling. Recently artificial neural networks (ANNs) have become the tool of choice in PTF development. Recent developments in machine learning methods include the growing research and application of the alternative data‐driven method called Support Vector Machines (SVMs). Support Vector Machines have gained popularity in many traditionally ANN dominated fields. Using the SVM eliminates the local minimum issue—the minimum found is always the global one. The objective of this work was to see whethers using the SVM to develop PTFs may have some advantages compared with the ANN. We have used the Soil Profiles Bank of Polish Mineral Soils that includes hydraulic properties for 806 soil samples taken from 290 soil profiles. This database was repeatedly randomly split into training and testing data sets, and both SVMs and ANNs were trained and tested for each split with bulk density, sand and clay as input variables, and water contents at 11 soil water potentials as the output variables. The PTF performance was evaluated by using the test datasets to compute the coefficient of determination, the root‐mean‐squared error, and the slope and the intercept of the linear regression “predicted vs. measured water contents.” The three‐parameter SVMs performed mostly better than or with the same accuracy as the eleven‐parameter ANNs. The advantage of SVM was more pronounced at soil matric potentials where larger relative errors have been encountered and the correlation between predicted and measured soil water contents was lower. It is worthwhile to consider SVM as a tool to develop PTF.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.