An evolutionary multiobjective strategy for the effective management of groundwater resources

This paper introduces a modelling approach aimed at the management of groundwater re-sources based on a hybrid multiobjective paradigm, namely the Evolutionary Polynomial Re-gression. Multiobjective modelling in hybrid evolutionary computing enables the user (a) to find a set of feasible symbolic models, (b) to make a robust choice of models and (c) to improve the computational efficiency developing simultaneously a set of models with diverse structural parsimony levels. Moreover the methodology here presented proves to be particularly fit to those cases where the input to the process and the boundary conditions are not easily accessible. The multiobjective approach is based on the Pareto dominance criterion and it is fully integrated into the Evolutionary Polynomial Regression paradigm. This approach proves to be effective for modelling groundwater systems, which usually requires (a) accurate analyses of the underlying physical phenomena, (b) reliable forecasts under different hypothetical sce-narios and (c) good generalisation features of the models identified. For these reasons it is important to construct easily interpretable models which are specialized for well defined pur-poses. The introduced methodology is tested on a case study concerned with the determination of the dynamical relationship between rainfall height and groundwater levels for a shallow unconfined aquifer located in southeast of Italy, which is climatically a Mediterranean zone.