A Case Study of Using Artificial Neural Networks to Predict Heavy Metal Pollution in Lake Iznik

Abstract

Abstract Since high levels of heavy metals cause serious complications for water resources, plants, animals and human health, determining their presence and concentration is very important for the sustainability of the ecosystem. In recent years, rapid advances in the field of artificial neural networks (ANNs) brought them the forefront in water quality prediction. In this paper, various experiments were conducted with a model for predicting the presence of heavy metals using IBM SPSS statistics 23 software. In order to assess the water quality of Lake Iznik –an important source of water– in terms of heavy metals, water quality parameters of samples taken in the period 2015–2021 from five different water sources flowing into the lake were analyzed. A number of psychochemical were measured in samples taken from Karasu, Kırandere, Olukdere, and Sölöz streams flowing into the lake, and were used as input data for modeling, while fifteen heavy metal concentrations in Karsak stream flowing out of the lake were used as output data of the model. The analyses showed that the R2 coefficients for heavy metals were mostly close to 1. Considering the importance of the independent variable in heavy metal pollution prediction, the most effective parameters for streams stood out to be conductivity, COD, COD, and temperature, respectively. It was seen that ANN model is a good prediction tool method that can be used effectively to determine heavy metal pollution in the lake in terms of ecological sustainability in order to conservation the water quality of Lake Iznik and to eliminate the existing pollution.