ABSTRACT An accurately calibrated hydraulic model of a water distribution network (WDN) is crucial for tasks such as leakage detection, resilience assessment, and rehabilitation planning. Since model calibration relies on real data, increasing monitoring locations for pressure and flow raises both accuracy and cost. Therefore, selecting suitable data collection points is crucial for efficient calibration. This research proposes a practical, graph-theory-inspired approach for determining pressure sensor locations based on the network topology and the demand distribution in the WDN. The method employs a customized metric of Node Demand Betweenness Centrality (NDBC) as a criterion to estimate flow distribution, and thereby identifies influential paths within WDNs. Sensor locations are then optimized using the nondominated sorting genetic algorithm II (NSGA-II), which identifies nodes located along the most influential paths in WDNs while maximizing network coverage by increasing the graph-based hydraulic distance between sensors. This methodology is further supported by additional graph analysis methods, which serve as a faster alternative and are compared against a widely utilized hydraulic model-based approach. The proposed approach was applied to both the Modena and L-Town WDNs. In both case studies, the calibrated models based on pressure data from the sensor locations proposed in this research demonstrated satisfactory accuracy.

ABSTRACT Urban areas are increasingly vulnerable to flooding due to rapid urbanization, inadequate stormwater infrastructure, and the intensifying impacts of climate change. To manage these challenges, reliable hydrological models are essential for mitigating the adverse impacts of hydrometeorological events. In data-scarce regions, the calibration of such models is hindered by limited field data. This study presents a practical methodology for calibrating a 1D–2D Stormwater Management Model (SWMM) for tropical urban catchments through a case study in Udon Thani City, Thailand. An iterative calibration process was applied to address major flooding identified in initial simulations, leading to improved runoff routing that ensured compliance with the 5-year, 1-h design storm of the system. The detailed one-factor-at-a-time (OAT) sensitivity analysis identified Curve Number (CN) and Imperviousness as the most influential parameters, followed by sub-catchment width and slope. The findings underscore the importance of prioritizing these parameters for calibration, particularly in regions with limited data availability. The proposed approach provides a scalable and transferable framework for flood risk assessment and management in similar tropical urban catchments globally. By integrating sensitivity analysis into the planning and optimization of green-grey infrastructure, the study contributes to the development of resilient and sustainable stormwater management strategies in vulnerable urban areas.

ABSTRACT The combined effects of climate change and urbanization have led to an increase in urban flooding due to extreme precipitation events, which show significant spatial variation within cities. Therefore, the development of a fine community-scale flooding model is crucial for urban flood prevention and control. This study presents the Urban Flood Inundation Model (UFIM), a refined model that integrates high-resolution topographic data, dynamic real-time 1D–2D coupling, and backflow effects to simulate flood inundation at community scale. The key findings are as follows: (1) Due to its built-in one-to-two-dimensional (1D–2D) connection modeling approach, the model can consider backflow effects, rendering water accumulation simulation more realistic and enhancing simulation accuracy. (2) UFIM achieved high accuracy with a precision of 0.81, recall of 0.77, Probability of Detection (POD) of 94%, and Nash-Sutcliffe Efficiency (NSE) between 0.785 and 0.800 under various actual precipitation events. (3) The model effectively simulated urban flood inundation for different return periods (1-, 5-, 10-, 20-, and 50-years), and different community types (including residential, functional and comprehensive communities). These results highlight the UFIM's potential to support refined flood risk assessment across diverse community types, inform adaptive urban drainage design, and enhance decision-making for resilient planning and emergency response.

ABSTRACT Underwater fish detection faces significant challenges due to lighting variations, water turbidity, and scale differences. This paper proposes a novel fish detection model, FishMP, which integrates an efficient Multi-Scale Parallel Perception Module (MPPM) with a P2 multi-branch cascaded sequence fusion network. The MPPM employs a multi-branch feature extraction strategy and attention mechanisms to capture features at different levels, effectively preventing the loss of critical information during downsampling and improving detection accuracy for blurred targets. To mitigate information loss during feature integration, the P2 multi-branch network is optimized using triple-feature serial modules and an ordered fusion pathway. Furthermore, an additional P2 low-level spatial information branch is introduced to enrich fish morphological and spatial position features, ensuring robust performance in complex underwater environments. Experimental results on the underwater datasets DeepFish and Fishway demonstrate that FishMP achieves an outstanding balance between speed and accuracy.

ABSTRACT It is a recognised problem that the structure and parameters of hydrological models are often not transferable in time. This may reduce model performance, with negative implications for applications in water resources modelling or flood forecasting. We hypothesise that integration of time-varying model parameters has the potential to better account for different active meteorological or hydrological processes that lead to different flood event types. To enhance flood forecasting the parameter sets should therefore be weighted dynamically according to the event type. In addition, ensemble approaches can be employed to reduce parameter uncertainty and to increase simulations accuracy for both continuous and event-based flood forecast models. Here, we introduce a machine learning based flood-type specific dynamic parameter weighting for ensemble flood forecasting. The potential of this method is demonstrated for an example case study application, employing five different machine learning approaches. Four types of flood events were considered, heavy-rainfall floods, long-duration-rainfall floods, sequence-of-rain floods and minor events with no clear generating processes. The results show that applying flood-type-specific parameter sets outperforms the other methods. Moreover, the performance consistently matched or exceeded the benchmark models. This improved performance is particularly relevant for practical applications in operational flood forecasting.

ABSTRACT Streamflow predictions are essential for flood risk prevention and long-term water resource management. Extensive research has been dedicated to forecasting river discharge for gauged rivers, where discharge data is readily available. However, accurately predicting discharge in ungauged rivers continues to pose a substantial challenge. Recent advances in machine learning (ML) offer opportunities to develop and refine predictive models for ungauged rivers. This study addresses two key limitations of existing ML models: the exclusion of sensitive physical features and overconfidence in predictions. By integrating principles of mass conservation and robust uncertainty quantification (UQ) methods, we aim to enhance the reliability of ML-based streamflow forecasts. We propose a hybrid modeling approach that leverages insights from calibrated physics-based river-routing models, considers the causal effects of carefully selected features, and integrates UQ methods to obtain probabilistic discharge predictions in ungauged rivers. Three different UQ methods within the ML models are investigated. The results of a Colorado River upper basin demonstrate that our approach outperforms existing methods (i.e., purely data-driven method), reducing the prediction error by about 40% and offering credible uncertainty bounds for risk-informed decision making.

ABSTRACT This paper presents a novel multi-agent framework for adaptive, fair water allocation under varying hydrological conditions (severe drought, dry, normal, and wet). The framework aims to (1) optimize reservoir water allocation to maximize net benefits, (2) enhance fairness among users, and (3) minimize scarcity-driven conflicts. Precipitation forecasts from numerical weather prediction (NWP) models are bias-corrected and fed into the soil and water assessment tool (SWAT) to simulate long-term reservoir inflows. A probability density function (PDF) of stored water volume, derived from a long-term optimization model, constrains the adaptive reservoir operation (ARO) model. The ARO comprises two sub-models: one allocates monthly reservoir water mid-term, while the other distributes water to individual agents. For dry/normal/wet conditions, a penalty-based approach guides allocation; severe droughts employ bankruptcy methods, including classical (PRO, CEA, CEL, PIN) and novel strategies (FPS, PPS, PIS). The methodology is applied to Iran's Zarrinehrud Basin, critical for Lake Urmia. Key findings: (1) Novel strategies FPS ($6.55M) and PPS ($6.53M) outperform traditional methods in profitability; (2) PRO achieves the highest fairness but lower profit ($4.76M), highlighting equity-efficiency trade-offs; (3) FPS/PPS boost profitability while redistributing gains to vulnerable agents. The framework balances efficiency, fairness, and conflict mitigation in water-scarce regions.

ABSTRACT Ample studies exist on water governance in Palestine, but none have specifically examined the influence of governance fragmentation on water data management, which is associated with inconsistent data collection and reporting practices, isolated databases, and poor coordination among actors. This paper investigates the factors that cause fragmentation in data management in the Palestinian water sector. Using the criteria of extent and coherence, we assess the practices of key water-related databases and identify governance factors regarding fragmentation. The assessment results reveal mostly low scores for both extent and coherence, indicating a high degree of fragmentation driven by financial and human resource constraints, which perpetuate competition over limited resources instead of collaboration. Power asymmetries in the organizational structure grant certain actors a privileged access to data while excluding others. The lack of standardized data management practices and a shared digital strategy intensify the fragmentation, as actors operate in silos which further complicate integration efforts. The wider political context, including mainly the Israeli–Palestinian conflict, adds to these challenges through control over data, restrictions on data collection, and technology embargoes, leading to a multi-layered fragmentation.

ABSTRACT Leakages in water supply networks can be minimized through pressure reduction or by repairing the resulting damage. The effective implementation of the latter approach necessitates the localization of leaks, for which various methods exist. This paper presents a specific software and hardware configuration for constructing a digital twin of pressurized piping systems that can be utilized for this purpose. The proposed method can identify both the flow and position of leaks and is based on solving an equivalent optimization problem, where the objective function depends on the difference between the measured pressure values at specific points and those predicted at the same points under the same boundary conditions by a computational model. Given the multimodality of the formulated problem, particle swarm optimization is implemented for this task. To enable real-time localization, the measured pressure values are transmitted to a microcontroller, which processes the data and sends it to a Python script. This script employs a while loop to continuously monitor the criteria for leak detection, and when these criteria are met, it initiates a procedure for leak localization. The theoretical aspect of the procedure, as well as its practical implementation, is presented below as an example.