Adaptive neuro-fuzzy inference system (ANFIS) and multiple linear regression (MLR) modelling of Cu, Cd, and Pb adsorption onto tropical soils.

Soils interact in many ways with metal ions thereby modifying their mobility, phase distribution, plant availability, speciation, and so on. The most prominent of such interactions is sorption. In this study, we investigated the sorption of Pb, Cd, and Cu in five natural soils of Nigerian origin. A relatively sparsely used method of modelling soil-metal ion adsorption, i.e. adaptive neuro-fuzzy inference system (ANFIS), was applied comparatively with multiple linear regression (MLR) models. The isotherms were well described by Freundlich and Langmuir equations (R2 ≥ 0.95) and the kinetics by nonlinear two-stage kinetic model, TSKM (R2 ≥ 0.81). Based on the values delivered by the Langmuir equation, the maximum adsorption capacities (Qm*) were found to be in the ranges 10,000-20,000, 12,500-50,000, and 4929-35,037 µmol kg-1 for Cd, Cu, and Pb, respectively. The study revealed significant correlations between Qm* and routinely determined soil parameters such as soil organic carbon (Corg), cation exchange capacity (CEC), amorphous Fe and Mn oxides, and percentage clay content. These soil parameters, combined with operational variables (i.e. solution/soil pH, initial metal concentration (Co), and temperature), were used as input vectors in ANFIS and MLR models to predict the adsorption capacities (Qe) of the soil-metal ion systems. A total of 255 different ANFIS and 255 different MLR architectures/models were developed and compared based on three performance metrics: MAE (mean absolute error), RMSE (root mean square errors), and R2 (coefficient of determination). The best ANFIS returned MAEtest 0.134, RMSEtest 0.164, and R2test 0.76, while the best MLR returned MAEtest 0.158, RMSEtest 0.199, and R2test 0.66, indicating the predictive advantage of ANFIS over MLR. Thus, ANFIS can fairly accurately predict the adsorption capacity and/or distribution coefficient of a soil-metal ion system a priori. Nevertheless, more investigation is required to further confirm the robustness/generalisation of the proposed ANFIS.

Adsorption of phenylurea herbicides by tropical soils.

The distribution of pesticides in soils with consequences for their mobility, bioavailability and water contamination is mainly ruled by sorption processes. Such processes are seldom investigated in tropical soils. Thus, specific interactions between tropical soils and most pesticides are widely unknown. Furthermore, the question arises whether the same factors govern adsorption in tropical and temperate soils. Thus, the sorption behaviour of five phenylurea herbicides (PUHs) was studied in eighteen differently composed soils originating from southwestern Nigeria. Sorption data were obtained by equilibrating the soil samples with 0.01 M CaCl2 solutions spiked with increasing concentrations of the target PUHs. The equilibrium data fitted well to the Freundlich isotherm equation (R2 ≥ 0.96), delivering the corresponding parameters (Kf and n). Linear distribution coefficients (Kd) were also calculated. The Pearson correlation was used to identify the specific soil and herbicide properties that have statistically significant correlations with sorption parameters. High correlations were established for various soil properties (pH, cation exchange capacity, organic carbon content, content of amorphous Fe and Mn oxides, clay/silt mass proportions) as well as molecular descriptors (octanol-water partition coefficient (log Kow) and molecular mass (Mw)) of the moderately hydrophobic herbicides. Monuron, chlorotoluron and isoproturon showed higher affinities for soil than previously reported. The gathered knowledge might assist in the assessment and in the precautionary avoidance of potential risks generated by these compounds in tropical soils.