Adaptive neuro-fuzzy inference system (ANFIS) and multiple linear regression (MLR) modelling of Cu, Cd, and Pb adsorption onto tropical soils
Open Access
- 28 November 2022
- journal article
- research article
- Published by Springer Nature in Environmental Science and Pollution Research
- Vol. 30 (11) , 31085-31101
Abstract
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.Keywords
Funding Information
- Alexander von Humboldt-Stiftung
- Universität Trier
This publication has 40 references indexed in Scilit:
- Adsorption isotherms of copper, lead, nickel, and zinc in two Chilean soils in single- and multi-component systems: sewage sludge impact on the adsorption isotherms of Diguillin soilSoil Research, 2008
- A comparative study of artificial neural networks and neuro-fuzzy in continuous modeling of the daily and hourly behaviour of runoffJournal of Hydrology, 2007
- Comparison of data-driven Takagi–Sugeno models of rainfall–discharge dynamicsJournal of Hydrology, 2005
- Biosolids and heavy metals in soilsScientia Agricola, 2003
- EFFECTS OF METAL CATIONS ON SORPTION AND DESORPTION OF ORGANIC COMPOUNDS IN HUMIC ACIDSSoil Science, 2001
- Factors influencing metal bioavailability in soils: preliminary investigations for the development of a critical loads approach for metalsChemical Speciation & Bioavailability, 1998
- Chemistry and Phytotoxicity of Soil Trace Elements from Repeated Sewage Sludge ApplicationsJournal of Environmental Quality, 1996
- ANFIS: adaptive-network-based fuzzy inference systemIEEE Transactions on Systems, Man, and Cybernetics, 1993
- Chemical extractability of heavy metals during and after long‐term applications of sewage sludge to soilEuropean Journal of Soil Science, 1992
- ADSORPTION BEHAVIOR OF COPPER AND ZINC IN SOILSSoil Science, 1990