Investigating Landfill Leachate and Groundwater Quality Prediction Using a Robust Integrated Artificial Intelligence Model: Grey Wolf Metaheuristic Optimization Algorithm and Extreme Learning Machine

The likelihood of surface water and groundwater contamination is higher in regions close to landfills due the possibility leachate percolation, which a potential source pollution. Therefore, proposing reliable framework for monitoring parameters an essential task managers authorities quality control. For this purpose, efficient hybrid artificial intelligence model based on grey wolf metaheuristic optimization algorithm extreme learning machine (ELM-GWO) used predicting landfill (COD BOD5) (turbidity EC) at Saravan landfill, Rasht, Iran. In study, samples were collected from wells. Moreover, concentration different physico-chemical heavy metal (Cd, Cr, Cu, Fe, Ni, Pb, Mn, Zn, turbidity, Ca, Na, NO3, Cl, K, COD, EC, TDS, pH, K). results obtained ELM-GWO compared with four models: multivariate adaptive regression splines (MARS), (ELM), multilayer perceptron neural network (MLPANN), integrated (MLPANN-GWO). study confirm that considerably enhanced predictive performance MLPANN-GWO, ELM, MLPANN, MARS models terms root-mean-square error, respectively, by 43.07%, 73.88%, 74.5%, 88.55% COD; 23.91%, 59.31%, 62.85%, 77.71% BOD5; 14.08%, 47.86%, 53.43%, 57.04% turbidity; 38.57%, 59.64%, 67.94%, 74.76% EC. can be applied as robust approach investigating sites.