Application of artificial neural network and multi-linear regression techniques in groundwater quality and health risk assessment around Egbema, Southeastern Nigeria

This paper examined the efficiency of artificial neural network (ANN) and multivariate linear regression (MLR) models in prediction groundwater quality parameters such as ecological risk index (ERI), pollution load (PLI), metal (MPI), Nemerow (NPI), geoaccumulation (Igeo). 40 samples were collected systematically analyzed for mainly heavy metals. Results revealed that adopting measured is effective modeling with high level accuracy. Contamination factor results reveal Ni, Zn, Pb, Cd, Cu have relatively low values < 1 within region while Iron ranged from contamination to very (> 6). PLI, MPI, ERI indicated pollution. NPI majority heavily polluted. Quantification most sample's was geogenically influenced. Igeo had extreme The health assessment children are substantially prone more than adults. ANN MLR showed a tendency ERI, Igeo. Principal component analysis appreciable variable loadings correlation matrix there exists weak positive amongst elements. Based on outcome this study, research recommends use they yielded positive, reliable, acceptable, appropriate accuracy performances.