Short‐term forecasting of water demand is a crucial process for managing efficiently water supply systems. This paper proposes to develop a novel graph convolutional recurrent neural network (GCRNN) to predict time series of water demand related to some water supply systems or district metering areas that belong to the same geographical area. The aim is to build a graph‐based model able to capture the dependence among the different water demand time series both in spatial and in temporal terms. This model is built on a set of different graphs, and its performance is compared to two methods, including a state‐of‐the‐art deep long short‐term memory (LSTM) neural network and a traditional seasonal autoregressive moving average model. Additionally, the forecasting model is tested in a condition when a sensor has a malfunction. The results show the ability of the GCRNN to produce accurate and reliable forecasting, especially when based on graph built while accounting for both time‐series correlation and spatial criteria. The GCRNN consistently outperforms the LSTM during the fault test, showing its ability to generate a robust prediction for days after a sensor malfunction, given the GCRNN's ability to benefit from the other time series of the graph.

Water distribution system monitoring is currently carried out using advanced real-time control technologies to achieve a higher operational efficiency. Data analysis techniques can be implemented for condition estimation, which are crucial tools for managing, developing, and operating water networks using the monitored flow rate and pressure data at some network pipes and nodes. This work proposes a state estimation methodology that enables one to infer the hydraulic state of the operating speed of pumping systems from these pressure and flow measurements. The presented approach suggests using graph convolutional neural network theory linked to hydraulic models for generating a digital twin of the water system. It is validated on two benchmark hydraulic networks: the Patios-Villa del Rosario, Colombia, and the C-Town networks. The results show that the proposed model effectively predicts the state estimation in the two hydraulic networks used. The results of the evaluation metrics indicate low values of mean squared error and mean absolute error and high values of the coefficient of determination, reflecting high predictive ability and that the prediction results adequately represent the real data.

Sustainable management of water resources is a key challenge nowadays and in the future. Water distribution systems have to ensure fresh water for all users in an increasing demand scenario related to the long-term effects due to climate change. In this context, a reliable short-term water demand forecasting model is crucial for the optimal management of water resources. This study proposes a novel deep learning model based on long short-term memory (LSTM) neural networks to forecast hourly water demand. Due to the limitations of using multiple input sequences with different time lengths using LSTM, the proposed deep learning model is developed with two modules that process different temporal sequences of data: a first module aimed at dealing with short-term meteorological information and a second module aimed at representing the longer-term information of the water demand. The proposed dual-module structure allows a multivariate selection of the inputs with sequences of a different time length. The performance of the proposed deep learning model is compared to a conventional multi-layer perceptron (MLP) and a seasonal integrated moving average (SARIMA) model in a real case study. The results highlight the potential of the proposed multivariate approach in short-term water demand prediction, outperforming the more conventional approaches.

Proper hydraulic simulation models, which are fundamental to analyse a water distribution system, require a calibration procedure. This paper proposes a multi-objective procedure to calibrate water demands and pipe roughness distribution in the context of an ill-posed problem, where the number of measurements is smaller than the number of variables. The proposed methodology consists of a two-steps procedure based on a genetic algorithm. Firstly, several runs of the calibrator are performed and the corresponding pressure and flow-rates values are averaged to overcome the non-uniqueness of the solutions problem. Secondly, the final calibrated model is achieved using the calibrator with the average values of the previous step as the reference condition. Therefore, the procedure enables to obtain physically based hydraulic parameters. Moreover, several hydraulic models are investigated to assess their performance on this optimisation procedure. The considered models are based either on concentrated at nodes or distributed along pipes demands approach, but also either on demand driven or pressure driven approach. Results show the reliability of the final calibrated model in the context of the ill-posed problem. Moreover, it is observed the overall better performance of the pressure driven approach with distributed demand in scarce pressure condition.