Neural Network Modeling of Heavy Metal Sorption on Lignocellulosic Biomasses: Effect of Metallic Ion Properties and Sorbent Characteristics

Abstract

This study reports the application of a neural network approach for modeling and analyzing the sorption performance of different lignocellulosic wastes, namely jacaranda fruit, plum kernels, and nutshell, for the removal of heavy metal ions (Pb 2+ , Cd 2+ , Ni 2+ , and Zn 2+ ) from aqueous solutions. This artificial neural networks (ANNs) model was used to determine the relevance and importance of both sorbent and pollutant characteristics on the metal sorption kinetics and isotherms. Results of this study highlighted the role of acidic functional groups, lignin composition of tested biomasses, and the pollutant molecular weight in the sorption of heavy metals. The nutshell biomass showed the best sorption properties for heavy metal removal, where its monolayer sorption capacities ranged from 1.0 to 7.0 mg/g. In summary, this study highlights the capabilities of ANN-based models for analyzing and understanding complex but relevant sorption processes for environmental protection and wastewater treatment.

Experimental and theoretical consideration of the factors influencing cationic pollutants retention by seashell waste

“…ANNs are an advanced mathematical modeling procedure, which mimics a biological neuron system . Prediction of sorption of heavy metals from aqueous solution using ANN has been performed successfully in several studies . There are a number of distinct ANN architectures among which the general regression neural network (GRNN) is especially useful if only a small and sparse dataset is available .…”

“…29 Prediction of sorption of heavy metals from aqueous solution using ANN has been performed successfully in several studies. [30][31][32] There are a number of distinct ANN architectures among which the general regression neural network (GRNN) 33 is especially useful if only a small and sparse dataset is available. 34 The GRNN is used for non-parametric estimation of the probability density of data, it does not require iterative training and is useful for relatively non-linear data processing.…”

Application of neural network in metal adsorption using biomaterials (BMs): a review

“…Some studies also included the inuence of lingo-cellulosic functional groups, particle size, and calcination temperature used to optimise biomaterial adsorbents' fabrication. 52,65,66,91,92 Table 4 illustrates recent developments of ANN-based optimization methods for modelling biomaterial adsorption systems.…”

“…56,200 The possibility of overtting is the second major issue that needs to be addressed by researchers while applying ANN algorithms to predict biomaterial systems' efficacy for wastewater treatments. 91,92 To prevent the over-parameterization and over-training of the ANN system, researchers have advocated the implementation of emerging activation functions (e.g., SeLU, ReLU). 201,202 Using simple models (e.g., AdaBoost) ensures the generalizability of output in the small dataset.…”

A Review of the Modeling of Adsorption of Organic and Inorganic Pollutants from Water Using Artificial Neural Networks

“…Mendoza-Castillo et al [125] implemented a classical BP-ANN for modeling the adsorption isotherms and kinetics of four heavy metals (i.e., lead, cadmium zinc, and nickel) on several lignocellulosic wastes (i.e., jacaranda fruit, plum kernels, and nut shells). These authors discussed that the heavy metal adsorption on lignocellulosic biomasses was a complex process with highly nonlinear interactions among the adsorbent characteristics, the physicochemical properties of adsorbates, and the removal operating conditions.…”