Using support vector machines to predict cation exchange capacity of different soil horizons in Qingdao City, China

Relationships between cation exchange capacity (CEC), clay and organic carbon contents and soil pH were analyzed by way of multiple regressions for upland soils in eastern Canada (mostly Ontario, with additional data for New Brunswick). This was done by vegetation type in an attempt to explain some of the otherwise unexplained CEC variations. Data were taken from about 2000 soil horizons (organic L, F, and H horizons as well as A, B, and C mineral soil horizons) under broadleaves (mostly maples, beech, birch or aspen as dominant species), conifers (mostly fir, spruces and/or pines), and grass vegetation. For the organic forest floor horizons (or L, F, and H horizons), both organic carbon content (%) and pH were highly significant for predicting CEC, i.e.,CEC (L, F, and H of broadleaves) = −38 + 0.71 × org. C (%) + 10.3 × pH (R2 = 0.69), andCEC (L, F and H of conifers) = −31 + 0.34 × org. C (%) + 12.1 × pH (R2 = 0.58).For the mineral soil, clay and organic carbon contents (%) and pH were highly significant for predicting CEC. Soils with forest vegetation were found to have lower contributions of organic matter to CEC than grassland soils, i.e.,CEC (forest soils) = −7.0 + 0.29 × clay (%) + 0.82 × org. C (%) + 1.4 × pH (R2 = 0.72),CEC (wooded grasslands) = −6.0 + 0.31 × clay (%) + 1.31 × org. C (%) + 1.0 pH (R2 = 0.74), andCEC (grasslands) = −8.3 + 0.24 × clay (%) + 2.14 × org. C (%) + 1.3 × pH (R2 = 0.79).Relationships that were developed from Ontario data for specific vegetational types (maple sites, strongly podzolized conifer sites, grasslands/croplands) were tested by comparing CEC predictions with reported values for similar sites in New Brunswick and Quebec. The predictions were consistent with the general trends for maple sites and grasslands/croplands, but CEC values were strongly overpredicted for Podzolic subsoils on conifer sites.Literature information of the CEC dependency on in situ pH is sparse. Existing information that is based on buffering grassland/cropland soil samples from pH 2.5 to 8 appears to mimic this dependency quite well. Key words: Cation exchange capacity, clay, organic carbon, soil pH, forests, grasslands

Download Full-text

Soil Cation Exchange Capacity Predicted by Learning From Multiple Modelling

Advances in Computational Intelligence and Robotics - Handbook of Research on Predictive Modeling and Optimization Methods in Science and Engineering ◽

10.4018/978-1-5225-4766-2.ch021 ◽

2018 ◽

pp. 465-480 ◽

Cited By ~ 2

Author(s):

Rahman Khatibi ◽

Mohammad Ali Ghorbani ◽

Rasoul Jani ◽

Moslem Servati

Keyword(s):

Cation Exchange ◽

Cation Exchange Capacity ◽

Prediction Models ◽

Soil Management ◽

Exchange Capacity ◽

Support Vector ◽

Soil Conditions ◽

Balanced Approach ◽

Target Values ◽

Solution Methods

Prediction models of cation exchange capacity (CEC) in soil management is investigated by using artificial intelligence for a balanced approach between advantageous CEC-rich and negative CEC-deficient soil conditions. The modelling strategy formed here comprises: (1) artificial neural networks based on feedforward multi-layer perceptron (MLP) and their backpropagation using Levenburg-Marquardt (LM) algorithm; (2) FireFly algorithm (FFA) to replace LM; (3) learn the dependency of CEC on soil characteristics (clay, silt, sand, gypsum, organic matter) by both models to produce outputs; and (4) feed these outputs as inputs to support vector machine using the least squares algorithms (SVM-LS) together with observed values as target values. This is referred to as multiple models (MM-SVM) strategy. The results of a study area with 380 soil samples collected from different horizons of 80 soil profiles show that the learning by MM-SVM is considerable and capable of reducing inherent uncertainty with benefits to CEC soil management by reducing uncertainty due to solution methods.

Download Full-text

New hybrid nature-based algorithm to integration support vector machine for prediction of soil cation exchange capacity

Soft Computing ◽

10.1007/s00500-021-06095-4 ◽

2021 ◽

Author(s):

Samad Emamgholizadeh ◽

Babak Mohammadi

Keyword(s):

Support Vector Machine ◽

Cation Exchange ◽

Hybrid Model ◽

Cation Exchange Capacity ◽

Exchange Capacity ◽

Multivariate Adaptive Regression Splines ◽

Support Vector ◽

Physical Parameters ◽

Invasive Weed ◽

Soil Cation Exchange Capacity

AbstractSoil cation exchange capacity (CEC) strongly influences the chemical, physical, and biological properties of soil. As the direct measurement of the CEC is difficult, costly, and time-consuming, the indirect estimation of CEC from chemical and physical parameters has been considered as an alternative method by researchers. Accordingly, in this study, a new hybrid model using a support vector machine (SVM), coupling with particle swarm optimization (PSO), and integrated invasive weed optimization (IWO) algorithm is developed for estimating the soil CEC. The physical and chemical data (i.e., clay, organic matter (OM), and pH) from two field sites of Taybad and Semnan in Iran were used for validating the new proposed approach. The ability of the proposed model (SVM-PSOIWO) was compared with the individual model (SVM) and the hybrid model (SVM-PSO). The results of the SVM-PSOIWO model were also compared with those of existing studies. Different performance evaluation criteria such as RMSE, R2, MAE, RRMSE, and MAPE, Box plots, and scatter diagrams were used to test the ability of the proposed models for estimation of the CEC values. The results showed that the SVM-PSOIWO model with the RMSE (R2) of 0.229 Cmol + kg−1 (0.924) was better than those of the SVM and SVM-PSO models with the RMSE (R2) of 0.335 Cmol + kg−1 (0.843) and 0.279 Cmol + kg−1 (0.888), respectively. Furthermore, the ability of the SVM-PSOIWO model compared with existing studies, which used the genetic expression programming, artificial neural network, and multivariate adaptive regression splines models. The results indicated that the SVM-PSOIWO model estimates the CEC more accurately than existing studies.

Download Full-text

Learning to Generate Optimized Term Weighting for Web Documents Classification - A Parallel Mimetic Approach Based on Support Vector Machines

International Review on Computers and Software (IRECOS) ◽

10.15866/irecos.v11i12.10964 ◽

2016 ◽

Vol 11 (12) ◽

pp. 1147

Author(s):

Abderrahmane Bendahmane ◽

Abdelkader Benyettou

Keyword(s):

Support Vector Machines ◽

Support Vector ◽

Term Weighting ◽

Web Documents ◽

Vector Machines

Download Full-text

EVALUASI PERUBAHAN KUALITAS TANAH PADA LAHAN BEKAS PENAMBANGAN NIKEL DI PULAU GEBE

Jurnal Rekayasa Lingkungan ◽

10.29122/jrl.v4i1.1849 ◽

2018 ◽

Vol 4 (1) ◽

Author(s):

Mardi Wibowo

Keyword(s):

Organic Carbon ◽

Cation Exchange ◽

Cation Exchange Capacity ◽

Exchange Capacity ◽

Mining Activity ◽

Evaluation Activity ◽

Land Quality ◽

Environment Quality

Since year 1977 until 2005, PT. ANTAM has been exploited nickel ore resources at Gebe Island – Center ofHalmahera District – North Maluku Province. Mining activity, beside give economically advantages also causedegradation of environment quality espicially land quality. Therefore, it need evaluation activity for change ofland quality at Gebe Island after mining activity.From chemical rehabilitation aspect, post mining land and rehabilitation land indacate very lack and lackfertility (base saturated 45,87 – 99,6%; cation exchange capacity 9,43 – 12,43%; Organic Carbon 1,12 –2,31%). From availability of nutrirnt element aspect, post mining land and rehabilitation land indicate verylack and lack fertility (nitrogen 0,1 – 1,19%). Base on that data, it can be concluded that land reclamationactivity not yet achieve standart condition of chemical land.Key words : land quality, post mining lan

Download Full-text