Prediction of the sorption efficiency of heavy metal onto biochar using a robust combination of fuzzy C-means clustering and back-propagation neural network

Abstract

Heavy metal adsorption onto biochar is an effective method for the treatment of the heavy metal contamination of water and wastewater. This study aims to evaluate the heavy metals sorption efficiency of different biochar characteristics and propose a novel intelligence method for predicting the sorption efficiency of heavy metal onto biochar with high accuracy based on the back-propagation neural network (BPNN) and fuzzy C-means clustering algorithm (FCM), named as FCM-BPNN. Accordingly, the FCM algorithm was used to simulate the properties of metal adsorption data and divide them into clusters with similar features. The clustering results showed that the FCM algorithm simulated metal adsorption data's properties very well and classified them based on biochar characteristics and adsorption conditions. Afterward, BPNN models were well-developed based on these clusters, and their outcomes were then combined (i.e., FCM-BPNN). The results indicated that the FCM-BPNN model could predict heavy metal's sorption efficiency onto biochar with a promising result (i.e., RMSE of 0.036, R² of 0.987, RSE of 0.006, MAPE of 0.706, and VAF of 98.724). Whereas the BPNN model, without optimizing the FCM algorithm, was proved with lower performance (RMSE = 0.050, R² = 0.977, RSE = 0.011, MAPE = 0.802, and VAF = 97.662). These findings revealed that the FCM algorithm's presence impressively improved the BPNN model's accomplishment in predicting heavy metal's sorption efficiency onto biochar, and the proposed FCM-BPNN model can improve water/wastewater treatment plants' quality and provide a more efficient process for heavy metals with performance superiority.

Keywords: Biochar sorption; Fuzzy C-Mean clustering; Heavy metal; Hybrid machine learning model; Neural networks; Wastewater.