The Use of Artificial Neural Networks to Predict the Physicochemical Characteristics of Water Quality in Three District Municipalities, Eastern Cape Province, South Africa

Abstract

Reliable prediction of water quality changes is a prerequisite for early water pollution control and is vital in environmental monitoring, ecosystem sustainability, and human health. This study uses Artificial Neural Network (ANN) technique to develop the best model fits to predict water quality parameters by employing multilayer perceptron (MLP) neural network and the radial basis function (RBF) neural network, using data collected from three district municipalities. Two input combination models, MLP-4-5-4 and MLP-4-9-4, were trained, verified, and tested for their predictive performance ability, and their physicochemical prediction accuracy was compared by using each model’s observed data with the predicted data. The MLP-4-5-4 model showed a better understanding of the data sets and water quality predictive ability giving an MSE of 39.06589 and a correlation coefficient (R2) of the observed and the predicted water quality of 0.989383 compared to the MLP-4-9-4 model (R2 = 0.993532, MSE = 39.03087). These results apply to natural water resources management in South Africa and similar catchment systems. The MLP-4-5-4 system can be scaled up for future water quality prediction of the Waste Water Treatment Plants (WWTPs), groundwater, and surface water while raising awareness among the public and industry on future water quality.

Neurocomputing Modelling of Hydrochemical and Physical Properties of Groundwater Coupled with Spatial Clustering, GIS, and Statistical Techniques

“…For instance; Bokde et al [52] estimated TDS (mg/L) using SVM, forest (RF), and gradient boosted decision tree (GBDT) and the best accuracy was found within the range of 80-85%. Setshedi et al [53] studied different types of ANN such as multilayer perceptron (MLP) neural network and the radial basis function (RBF) neural network for the physicochemical characteristic of GW in South Africa. The finding indicated the capability of AI-based models but with less accuracy than the current analysis using HW models.…”

Agarwood—The Fragrant Molecules of a Wounded Tree

“…Many endophytic fungal species have been reported to play a vital role in agarwood resin production in the Aquilaria and Gyrinops species [ 23 ]. Table 2 describes the various fungal endophytes known to induce agarwood formation in the Aquilaria and Gyrinops species.…”

Added Value of CCTA-Derived Features to Predict MACEs in Stable Patients Undergoing Coronary Computed Tomography

“…There is also increasing evidence that pericoronary fat inflammation (pFAI) measured in the right coronary artery (RCA) is an independent predictor of cardiovascular events and mortality [ 12 , 13 , 14 , 15 , 16 , 17 ]. In addition, other evidence exists about the role of elevated pFAI in patients with myocarditis, myocardial infarction with nonobstructive coronary arteries (MINOCA) and Takotsubo syndrome [ 13 , 14 ].…”

“…In addition, other evidence exists about the role of elevated pFAI in patients with myocarditis, myocardial infarction with nonobstructive coronary arteries (MINOCA) and Takotsubo syndrome [ 13 , 14 ]. Indeed, pericoronary adipose tissue releases proinflammatory cytokines that can alter the structure of the coronary wall, leading to CAD [ 15 ]. Previous studies indicated that pFAI correlates with plaque attenuation components in patients with non-ST-elevation acute coronary syndrome [ 16 ].…”