A forecast model of the Ebro river streamflow and impacts of damming up in Tudela
The project objectives are to build a one day ahead forecast model of the river streamflow and to discuss the impacts of damming up the river; different types of models are evaluated in order to find the best one.
The model applied are the following: Auto-regressive model (AR), Auto-regressive model with exogenous variable (ARX), Classification and regression trees (CART), random forest (RF).
The Sequent Peak Analysis method is applied to define the capacity of the dam. The regulation policy of the dam is designed to satisfy the requirements of all the stakeholders. The policy’s shape is set a priori to later optimise it by minimizing some choosen indicators. The algorithm applied for the optimization is Non-dominated Sorting Genetic Algorithm (NSGA)