A collaborative research effort, featuring researcher Nourani from Near East University, has explored the assessment of groundwater quality near a waste landfill site in Tychy-Urbanowice, southern Poland. The study investigates the influence of factors such as air and water temperature, groundwater table position, and precipitation on groundwater electrical conductivity within a chosen piezometer. Utilizing twenty neural network architectures of a Multilayer Perceptron Model (MLP), the research identified three models exhibiting the highest learning quality and minimal validation and test errors.
The study’s significance lies in its utilization of sensors in boreholes for continuous monitoring of groundwater quality parameters. By structuring an artificial neural network, researchers aimed to assess water’s electrical conductivity, specifically using the P19 piezometer at the Tychy landfill site. The findings underscore the applicability of artificial neural networks in determining the influence of temperature, precipitation, and groundwater table position on water conductivity in the landfill area.
Error values obtained from the neural networks indicated the models’ efficacy in capturing the introduced variables, demonstrating their reliability in assessing water quality parameters. The research specifically focused on the structures of multilayer perceptron neural networks, emphasizing the importance of water temperature and groundwater table position as key factors influencing the models’ outcomes.
In conclusion, the analysis affirms the utility of artificial neural networks in monitoring changes in selected water quality parameters over time. The study’s findings provide valuable insights for environmental monitoring and management, showcasing the practical application of advanced modeling techniques. The collaboration with Near East University enhances the study’s credibility and contributes to the global understanding of groundwater quality dynamics. The researchers underscore the importance of continuous monitoring using advanced technologies to inform sustainable water resource management practices.
The research serves as a robust contribution to the field, highlighting the role of artificial neural networks in assessing groundwater quality and offering practical implications for environmental monitoring and conservation efforts.
More Information:
https://sciendo.com/article/10.2478/environ-2023-0013
