Performances of MLR, RBF-NN, and MLP-NN in the evaluation and prediction of water resources quality for irrigation purposes under two modeling scenarios

Abstract

Listen

Translate article

One of the pivotal decision-making tools for sustainable management of water resources for various uses is accurate prediction of water quality. In the present paper, multiple linear regression (MLR), radial basis function neural network (RBF-NN), and multilayer perceptron neural network (MLP-NN) models were developed for the monitoring and management of irrigation water quality (IWQ) in Ojoto area, southeastern Nigeria. This paper is the first to integrate and simultaneously implement these predictive methods for the modeling of sodium absorption ratio, permeability index, Kelly’s ratio, percentage sodium, residual sodium carbonate, magnesium hazard, and potential salinity. Moreover, two modeling scenarios were considered. Scenario 1 represents predictions that utilized the specific physicochemical parameters for calculating the IWQ indices as input variables while Scenario 2 represents predictions that utilized pH, EC, Na+, K+, Mg2+, Ca2+, Cl-, SO42-, and HCO3- as inputs. In terms of salinity hazard, most of the water resources are unsuitable/poor for irrigation. However, in terms of carbonate and bicarbonate impact and magnesium hazard, majority of the samples have good and excellent IWQ. Seven agglomerative Q-mode dendrograms spatiotemporally classified the water resources based on the IWQ indices. Model validation metrics showed that the MLR, RBF-NN, and MLP-NN models developed in the two scenarios performed well. In Scenario 1, the R2 range for MLR, RBF-NN, and MLP-NN was 0.721-1.000, 0.814-0.989, and 0.924-0.983, respectively. However, in Scenario 2, the R2 range was 0.778-1.000, 0.881-0.947, and 0.872-0.987, respectively. This paper would significantly contribute to literature for the advancement of IWQ prediction and management.