- This study introduces an intelligent Decision Support System (DSS) designed to improve groundwater management by linking theoretical concepts to practical applications using advanced data analysis methods.
- The research utilizes telemetry data from selected wells to create a database of key groundwater parameters, allowing for statistical analysis that identifies critical thresholds for factors like water pressure and electrical current.
- A machine learning model using the Random Forest algorithm enables real-time monitoring and forecasting of well performance, while expert insights from water management professionals enhance the system's effectiveness, leading to optimized and sustainable groundwater management practices.
* Eight machine learning methods were tested to predict water flow rates in Mashhad City, with CART, RF, and LR showing the best accuracy according to performance metrics like MSE and RMSE.
* The research introduces a Petri net model to visualize the smart management framework and includes an alarm system for monitoring purposes.