Prediction of soil physical properties by optimized support vector machines

Abstract

A b s t r a c t. The potential use of optimized support vector machines with simulated annealing algorithm in developing prediction functions for estimating soil aggregate stability and soil shear strength was evaluated. The predictive capabilities of support vector machines in comparison with traditional regression prediction functions were also studied. In results, the support vector machines achieved greater accuracy in predicting both soil shear strength and soil aggregate stability properties comparing to traditional multiple-linear regression. The coefficient of correlation (R) between the measured and predicted soil shear strength values using the support vector machine model was 0.98 while it was 0.52 using the multiple-linear regression model. Furthermore, a lower mean square error value of 0.06 obtained using the support vector machine model in prediction of soil shear strength as compared to the multiple-linear regression model. The ERROR% value for soil aggregate stability prediction using the multiple-linear regression model was 14.59% while a lower ERROR% value of 4.29% was observed for the support vector machine model. The mean square error values for soil aggregate stability prediction using the multiplelinear regression and support vector machine models were 0.001 and 0.012, respectively. It appears that utilization of optimized support vector machine approach with simulated annealing algorithm in developing soil property prediction functions could be a suitable alternative to commonly used regression methods.K e y w o r d s: soft computing, support vector machines, simulated annealing algorithm, soil shear strength, aggregate stability

Soil Water Dynamic Modeling Using the Physical and Support Vector Machine Methods

“…The second group consists of machine learning models. During the past two decades various statistical models have been applied for hydrological modeling and prediction, including soil water simulation performed using artificial neural networks (ANN) (Jiang and Cotton, 2004; Ahmad and Simonovic, 2005; Elshorbagy and Parasuraman, 2008; Zou et al, 2010; Dai et al, 2011; Gorthi, 2011; Mukhlisin et al, 2011) and support vector machines (SVM) (Asefa et al, 2006; Khalil et al, 2006; Tripathi et al, 2006; Yu and Liong, 2007; Kalra and Ahmad, 2009; Lin et al, 2009; Liu et al, 2010; Deng et al, 2011; Besalatpour et al, 2012). They provide great prediction capacity and do not need soil physical properties but do require soil variable time series such as water content or matric potential along with climatic measurements for calibration (training) data.…”

Compressive response of some agricultural soils influenced by the mineralogy and moisture

“…Several parameters had been used to estimate the intrinsic strength of soils and evaluate the susceptibility or otherwise to compaction. Common parameters include the precompression stress values (Rucknage et al, 2007), penetration resistance (Almeda et al, 2012;Gao et al, 2012), shear strength parameters (Besalatpour et al, 2012;Zhang et al, 2001), packing density (Spoor et al, 2003), and rheometry parameters (Markgraf, 2011). Amongst the various parameters, the use of precompression stress for characterizing soil strength and load bearing capacity of soils is consolidated, probably because it is the only parameter that reflects the stress history of the soil.…”

Quantification of potassium concentration with Vis–SWNIR spectroscopy in fresh lettuce

“…Support vector machine regression (SVR) is a promising method proposed by Vapnik (1998) 33 . SVR is processed based on the statistical learning theory to avoid overfitting and multidimensional problem 34 , and SVR is commonly used as a good nonlinear regression method for quantitative analysis 24 . In this study, SVR was applied to build the nonlinear models for a comparison of prediction performance with linear PLS models.…”