Development of Operation Management Model of Groundwater According to Nitrate Contamination

Nitrate is one of the most important groundwater pollutants with such different sources as chemical fertilizers, pesticides, or domestic and industrial wastewater. In this research, the optimal operation of groundwater wells in aquifers with nitrate pollution is investigated using simulation and optimization techniques. For the simulation part, an artificial neural network (ANN) model is developed, and for the optimization model, the particle swarm optimization (PSO) is used. Considering the high nitrate concentration in Karaj area and its increase in recent years, the northern part of this aquifer is selected as a case study to apply the proposed methodology. A seasonal ANN model is developed with input layers including well discharge in the current and previous seasons, nitrate concentration in the previous season, aquifer thickness, and well coordinates, all selected based on sensitivity analysis. The results of PSO algorithm shows that nitrate concentration can be controlled by increasing or decreasing well discharge in different zones. Therefore, it is possible to reduce nitrate concentration in critical areas by changing the spatial distribution of groundwater extractions in different zones keeping the total discharge constant.