Artificial Neural Network Approach for Predicting Cation Exchange Capacity in Soil Based on Physico-Chemical Properties
- 1 January 2009
- journal article
- research article
- Published by Mary Ann Liebert Inc in Environmental Engineering Science
- Vol. 26 (1), 137-146
- https://doi.org/10.1089/ees.2007.0238
Abstract
Cation exchange capacity (CEC) of soil is an important characteristic that determines the soil buffering capacity to maintain cationic nutrients and pollutants against leaching to the subsurface layers. Radial basis function neural networks (RBFN) were applied into the estimation of cation exchange capacity (CEC) from soil physicochemical properties. A total of 457 soil samples collected from surface to deep underground horizons under various climatic and geographic conditions were successfully compiled in the comprehensive modelling research. Soil horizon; pH; organic carbon content; and clay, silt, and sand contents were taken as the input variables. Four RBFN models applied in CEC estimates for A, B, C horizons as well as the aggregate soils from all horizons were developed, with high correlation coefficients of 0.9397, 0.8368, 0.8014, and 0.8335 between the predicted and measured values of the external test samples, respectively, after optimization of the network architectures. Furthermore, the influence of each input variable on the soil CEC was particularly evaluated and sequenced by sensitivity analysis, confirming that clay content, organic carbon content, and soil horizons are the most important determinants of CEC estimate. Due to the existing nonlinear and uncertain characteristics of natural soil properties demonstrated in this paper, the optimized RBFN models showed high superiority in large-scale data simulation of complicated soil samples compared with multiple linear regressions (MLR). All the results confirm that an artificial neural network is a precise, sensitive, and robust method in the quantitative study of CEC in widely distributed soil samples in the complex ecosystem.Keywords
This publication has 33 references indexed in Scilit:
- Modelling fungal growth using radial basis function neural networks: The case of the ascomycetous fungus Monascus ruber van TieghemInternational Journal of Food Microbiology, 2007
- Simultaneous amperometric determination of lignin peroxidase and manganese peroxidase activities in compost bioremediation using artificial neural networksAnalytica Chimica Acta, 2006
- A New Method for the Simultaneous Measurement of pH‐Dependent Cation Exchange Capacity and pH Buffering CapacitySoil Science Society of America Journal, 2004
- Variable charge characteristics of selected Andisols from the Azores, PortugalCATENA, 2004
- Cation exchange capacities of soil organic matter fractions in a Ferric Lixisol with different organic matter inputsAgriculture, Ecosystems & Environment, 2003
- Cation and anion exchange properties of Andisols from the Azores, Portugal, as determined by the compulsive exchange and the ammonium acetate methodsGeoderma, 2003
- The Neuro‐m Method for Fitting Neural Network Parametric Pedotransfer FunctionsSoil Science Society of America Journal, 2002
- A pH‐Dependence Implicit Formulation of Cation‐ and Anion‐exchange Capacities of Variable‐charge SoilsSoil Science Society of America Journal, 2002
- Effect of Aging of Chemicals in Soil on Their Biodegradability and ExtractabilityEnvironmental Science & Technology, 1995
- Desorption of Copper from Some New Zealand SoilsSoil Science Society of America Journal, 1993