Prediction of urban water consumption can help to improve the performance of water distribution systems. Despite the obvious presence of uncertainty in measurements and in assumed model types/structures, most of the existing water consumption prediction models are developed and used in a deterministic context. Methods for more realistic assessment of parameter and model prediction uncertainties have begun to appear in literature only recently. A novel application of the Shuffled Complex Evolution Metropolis algorithm (SCEM-UA) for the calibration of a water consumption prediction model is proposed here. The model is applied to a case study of the city of Catania (Italy) with the aim to predict daily water consumption. The SCEM-UA algorithm is used to calibrate the parameters of the artificial neural network based prediction model and in turn to determine the associated parameter and model prediction uncertainties. The results obtained using the SCEM-UA ANN approach were compared to the corresponding results obtained using other predictive models developed recently by the authors of the paper. When compared to the these models, the SCEM-UA ANN based water consumption prediction model shows similar predictive capability but also the ability to identify simultaneously the prediction uncertainty bounds associated with the posterior distribution of the parameter estimates.

The assessment of water resources in a region usually must cope with a general lack of data, both in time (short observed series) as well as in space (ungauged basins). Such a lack of data is generally overcome by combining rainfall-runoff models with regionalization techniques in order to transfer information to sites without or with short available observed series. The present paper aims to analyze applicability and limitations of two regionalization procedures for estimating the parameters of simple rainfall-runoff models respectively based on a "two-step" and on a "one-step" approach, for the estimation of monthly streamflow series in ungauged basins. In particular, an application to a Sicilian river basin of multiple regression equations according to a "two-step" and a "one-step" approaches and of a "one-step" approach based on neural networks is reported. For the investigated region, results indicate that models based on the "one-step" approach appear to be robust and adequate for estimating the streamflows in ungauged basins.

No abstract

No abstract

No abstract