Extreme weather events, combined with human-induced factors, such as expanding impervious surfaces and inadequate drainage infrastructure, are driving escalating urban flood risks worldwide. In this study, we present a novel spatiotemporal Long Short-Term Memory (LSTM)-based surrogate of the U.S. Environmental Protection Agency (EPA)’s Storm Water Management Model (SWMM) to predict maximum water depth and inflow at the asset level within urban drainage networks. The high-resolution SWMM model, encompassing the full network of conduits and manholes, was first calibrated and validated using U.S. Geological Survey (USGS) observations. The LSTM surrogate was then trained on data from 5,000 rainfall events across seven Annual Recurrence Intervals (ARIs) ranging from 1 to 100 years. The SWMM-LSTM surrogate model consistently achieves high predictive performance for both water depth and inflow, highlighting its robustness across diverse storm scenarios and ARI conditions. Hyperparameter optimization via grid search revealed task-specific configurations: larger hidden layers with moderate dropout improved water depth predictions, while deeper network architectures with minimal dropout optimized inflow forecasts. By providing rapid, computationally efficient predictions without compromising accuracy, the SWMM-LSTM surrogate offers a practical tool for real-time flood risk assessment, scenario evaluation and actionable decision-making in complex urban drainage systems.

In water distribution networks (WDNs), pressure limitation represents an effective strategy to reduce water losses. This goal can be achieved by means of pressure reducing valves (PRVs), which dissipate exceeding hydraulic energy. For more sustainable management of water systems within a circular economy framework, PRVs can be replaced with energy-producing devices, such as pumps as turbines (PATs). This study presents a general approach for the selection of the optimal PAT to install in a given WDN. The approach assesses the techno-economic feasibility of a fleet of turbomachines by evaluating the rate of energy recovery, the levelized cost of electricity and the payback period of each PAT. Two PAT regulation strategies are accounted for, namely hydraulic and electrical regulations. The approach is applied to a real-world case study consisting of a WDN in Northern Italy that supplies approximately 5,000 users. In addition, a fleet of 16 turbomachines is considered, of which the experimental characteristic curves are available in both pump and turbine modes. The analyses carried out in this article allow selecting the optimal PAT to install within the considered WDN, which recovers 44.1 % of the hydraulic energy of the network with a maximum investment cost of € 24,500.

Aquatic ecosystem monitoring is important for supporting biodiversity and environmental stability, yet it faces increasing threats from pollution, climate change and human activities. This study presents the development and deployment of a low-cost multi-sensor data logging system for real-time monitoring of Lagos Lagoon. The system integrates temperature sensors, hydrophones, and imaging devices to collect environmental data. Results showed that temperature variations ranged from ~28.5 to 31.5 °C, with fluctuations influenced by partial and full submersion. Acoustic analysis revealed dominant frequencies below 500 Hz, indicative of biological and anthropogenic activity in the lagoon. Machine learning models trained on 31 species closely agreed with the environmental dataset despite some noticeable deviations, suggesting potential improvements through data augmentation and model refinement. Despite challenges such as signal attenuation in submerged conditions and image degradation due to water turbidity, the system successfully recorded and logged environmental parameters. This study demonstrates the feasibility of using artificial intelligence-powered, cost-effective sensor technology for continuous aquatic monitoring, with implications for biodiversity conservation and water resource management. Future research should focus on enhancing wireless communication, refining species detection algorithms and improving sensor resilience in harsh aquatic conditions.