Predicting the sorption efficiency of heavy metal based on the biochar characteristics, metal sources, and environmental conditions using various novel hybrid machine learning models.

Heavy metals in water and wastewater are taken into account as one of the most hazardous environmental issues that significantly impact human health. The use of biochar systems with different materials helped significantly remove heavy metals in the water, especially wastewater treatment systems. Nevertheless, heavy metal's sorption efficiency on the biochar systems is highly dependent on the biochar characteristics, metal sources, and environmental conditions. Therefore, this study implicates the feasibility of biochar systems in the heavy metal sorption in water/wastewater and the use of artificial intelligence (AI) models in investigating efficiency sorption of heavy metal on biochar. Accordingly, this work investigated and proposed 20 artificial intelligent models for forecasting the sorption efficiency of heavy metal onto biochar based on five machine learning algorithms and bagging technique (BA). Accordingly, support vector machine (SVM), random forest (RF), artificial neural network (ANN), M5Tree, and Gaussian process (GP) algorithms were used as the key algorithms for the aim of this study. Subsequently, the individual models were bagged with each other to generate new ensemble models. Finally, 20 intelligent models were developed and evaluated, including SVM, RF, M5Tree, GP, ANN, BA-SVM, BA-RF, BA-M5Tree, BA-GP, BA-ANN, SVM-RF, SVM-M5Tree, SVM-GP, SVM-ANN, RF-M5Tree, RF-GP, RF-ANN, M5Tree-GP, M5Tree-ANN, GP-ANN. Of those, the hybrid models (i.e., BA-SVM, BA-RF, BA-M5Tree, BA-GP, BA-ANN, SVM-RF, SVM-M5Tree, SVM-GP, SVM-ANN, RF-M5Tree, RF-GP, RF-ANN, M5Tree-GP, M5Tree-ANN, GP-ANN) are introduced as the novelty of this study for estimating the heavy metal's sorption efficiency on the biochar systems. Also, the biochar characteristics, metal sources, and environmental conditions were comprehensively assessed and used, and they are considered as a novelty of the study as well. For this aim, a dataset of sorption efficiency of heavy metal was collected and processed with 353 experimental tests. Various performance indexes were applied to evaluate the models, such as RMSE, R2, MAE, color intensity, Taylor diagram, box and whiskers plots. This study's findings revealed that AI models could predict heavy metal's sorption efficiency onto biochar with high reliability, and the efficiency of the ensemble models is higher than those of individual models. The results also reported that the SVM-ANN ensemble model is the most superior model among 20 developed models. The predictive model proposed that heavy metal's efficiency sorption on biochar can be accurately forecasted and early warning for the water pollution by heavy metal.

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

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.

Prediction of slope failure in open-pit mines using a novel hybrid artificial intelligence model based on decision tree and evolution algorithm.

In this study, the objective was to develop a new and highly-accurate artificial intelligence model for slope failure prediction in open-pit mines. For this purpose, the M5Rules algorithm was combined with a genetic algorithm (GA) in a novel hybrid technique, named M5Rules-GA model, for slope stability estimation and analysis and 450-slope observations in an open-pit mine in Vietnam were modeled using the Geo-Studio software based on essential parameters. The factor of safety was used as the model outcome. Artificial neural networks (ANN), support vector regression (SVR), and previously introduced models (such as FFA-SVR, ANN-PSO, ANN-ICA, ANN-GA, and ANN-ABC) were also developed for evaluating the proposed M5Rules-GA model. The evaluation of the model performance involved applying and computing the determination coefficient, variance account for, and root mean square error, as well as a general ranking and color scale. The results confirmed that the proposed M5Rules-GA model is a robust tool for analyzing slope stability. The other investigated models yielded less robust performance under the evaluation metrics.

Predicting Blast-Induced Ground Vibration in Open-Pit Mines Using Vibration Sensors and Support Vector Regression-Based Optimization Algorithms.

In this study, vibration sensors were used to measure blast-induced ground vibration (PPV). Different evolutionary algorithms were assessed for predicting PPV, including the particle swarm optimization (PSO) algorithm, genetic algorithm (GA), imperialist competitive algorithm (ICA), and artificial bee colony (ABC). These evolutionary algorithms were used to optimize the support vector regression (SVR) model. They were abbreviated as the PSO-SVR, GA-SVR, ICA-SVR, and ABC-SVR models. For each evolutionary algorithm, three forms of kernel function, linear (L), radial basis function (RBF), and polynomial (P), were investigated and developed. In total, 12 new hybrid models were developed for predicting PPV in this study, named ABC-SVR-P, ABC-SVR-L, ABC-SVR-RBF, PSO-SVR-P, PSO-SVR-L, PSO-SVR-RBF, ICA-SVR-P, ICA-SVR-L, ICA-SVR-RBF, GA-SVR-P, GA-SVR-L and GA-SVR-RBF. There were 125 blasting results gathered and analyzed at a limestone quarry in Vietnam. Statistical criteria like R2, RMSE, and MAE were used to compare and evaluate the developed models. Ranking and color intensity methods were also applied to enable a more complete evaluation. The results revealed that GA was the most dominant evolutionary algorithm for the current problem when combined with the SVR model. The RBF was confirmed as the best kernel function for the GA-SVR model. The GA-SVR-RBF model was proposed as the best technique for PPV estimation.

A Novel Hybrid Model for Predicting Blast-Induced Ground Vibration Based on k-Nearest Neighbors and Particle Swarm Optimization.

In this scientific report, a new technique of artificial intelligence which is based on k-nearest neighbors (KNN) and particle swarm optimization (PSO), named as PSO-KNN, was developed and proposed for estimating blast-induced ground vibration (PPV). In the proposed PSO-KNN, the hyper-parameters of the KNN were searched and optimized by the PSO. Accordingly, three forms of kernel function of the KNN were used, Quartic (Q), Tri weight (T), and Cosine (C), which result in three models and abbreviated as PSO-KNN-Q, PSO-KNN-T, and PSO-KNN-C models. The valid of the proposed models was surveyed through comparing with those of benchmarks, random forest (RF), support vector regression (SVR), and an empirical technique. A total of 152 blasting events were recorded and analyzed for this aim. Herein, maximum explosive per blast delay (W) and the distance of PPV measurement (R), were used as the two input parameters for predicting PPV. RMSE, R2, and MAE were utilized as performance indicators for evaluating the models' accuracy. The outcomes instruct that the PSO algorithm significantly improved the efficiency of the PSO-KNN-Q, PSO-KNN-T, and PSO-KNN-C models. Compared to the three benchmarks models (i.e., RF, SVR, and empirical), the PSO-KNN-T model (RMSE = 0.797, R2 = 0.977, and MAE = 0.385) performed better; therefore, it can be introduced as a powerful tool, which can be used in practical blasting for reducing unwanted elements induced by PPV in surface mines.