Simulation, evaluation and prediction modeling of river water quality properties (case study: Ireland Rivers)

Abstract

In this analysis, three input parameters temperature, pH and electrical conductivity were chosen due to their easy and less costly measurement technique, and a package of six models were presented for estimating the concentrations of dissolved oxygen, DO percentage, biological oxygen demand, chloride, alkalinity and total hardness. 3001 data sets (a 3001 × 8 data array) were used to training the models. The models have been tested in order to verify their prediction values, and the resulted R factor (the rate of precision) for each model equals to 0.93, 0.95, 0.77, 0.82, 0.85 and 0.92, respectively. This proves that the package can be used to estimate the concentrations of water quality parameters with accuracy close to the reality. The River data collected from 210 monitoring stations located in all over Ireland have been used. The data set covers different conditions and makes the model applicable in many different places and conditions. For development of all models, feed-forward algorithm used for training, as well as the Levenberg–Marquardt and tansign(x) functions as learning and transfer functions.