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.

Hydropower is commonly considered a renewable energy source. Nevertheless, this does not imply an absence of impacts on the riverine ecosystem, the extent of which is expected to increase in the coming years due to the energy transition from fossil fuels to renewable sources and for the climate change. A common consequence of hydroelectric power generation is hydropeaking, which causes rapid and frequent fluctuations in the water flow downstream of hydropower plants. The review incorporates 155 relevant studies published up until November 2023 and follows a systematic review method, Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA), which is a multi-stage systematic procedure for the identification and selection of research documents. The selected studies highlighted several prominent impacts of hydropeaking on aquatic environments. The primary effects include alterations in flow patterns, modification of water temperature, changes in sediment dynamics and fluctuations in dissolved gas levels. These alterations have been found to affect various aspects of aquatic ecosystems, including fish growth, behavior, reproductive success, habitat, and migration patterns, and benthic macroinvertebrate communities. Furthermore, hydropeaking can also lead to habitat fragmentation, erosion, and loss of riparian vegetation, thereby impacting terrestrial ecosystems that depend on the aquatic environment. Despite the body of literature reviewed, several knowledge gaps were identified, underscoring the need for further research. There is limited understanding of the long-term ecological consequences of hydropeaking and its cumulative effects on aquatic ecosystems. Additionally, there is lack of consensus regarding the quantification of ecosystem services, economic impact, soil moisture content, and weighted usable area due to flow fluctuation and global evolution of energy production from renewable energy sources. Addressing the identified research gaps is crucial for achieving a balance between energy production and the conservation of freshwater ecosystems in the context of a rapidly changing global climate.

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.