Santa Cruz Island (Galápagos Archipelago), like many other tourist islands, is currently experiencing an exponential increase in tourism and local population growth, jeopardizing current and future water supply. An accurate assessment of the future water supply/demand balance is crucial to capital investment for water infrastructure. This paper aims to present five intervention strategies, which are suggested to solve the future water crisis. The strategies combined include environmentally sustainable options such as rainwater harvesting, greywater recycling and water demand management, as well as desalination. These strategies were evaluated under four population growth scenarios (very fast, fast, moderate and slow growths) by using several Key Performance Indicators (KPI's) including water demand, leakage levels, total costs, energy consumption, rainwater delivered and greywater recycled. Moreover, it also aims to develop a methodology for similar islands, using the WaterMet2 modelling approach, a tool for integrated of sustainable-based performance of urban water systems. The results obtained show that by 2044 only a small portion of the future water demand can be covered assuming business as usual. Therefore, desalination seems to be the most viable option in order to mitigate the lack of water at the end of the planning period considering the growth trends. However, strategies comprising more environmentally friendly alternatives may be sufficient, but only under slow population growth scenarios.@en

Cutting-edge digital visualisation tools (CDVT) are playing an increasingly important role in improving urban flood risk management. However, there is a paucity of comprehensive research examining their role across all stages of urban flood risk management. To address, this study conducts an integrated critical review to identify the application of CDVT and assess their contribution to the prevention, mitigation, preparation, response, and recovery stages of flood risk management. The results show that virtual reality, augmented reality, and digital twin technologies are the primary CDVT used in urban flood visualisation, with virtual reality being the most frequently used. The focus of urban flood visualisation studies has been primarily on preparation and mitigation stages. However, there is a need to investigate the application of these technologies in the entire urban water cycle. Furthermore, there is potential for greater adoption of digital twin, especially in simulating urban flood inundation and flood evacuation routes. Integrating real-time data, data-driven modeling, and CDVT can significantly improve real-time flood forecasting. This benefits stakeholders and the public by enhancing early warning systems, preparedness, and flood resilience, leading to more effective flood risk management and reduced impacts on communities.@en

This paper presents a multi-criteria risk-based approach for managing urban flood hazards by using a combination of conventional measures and contemporary Sustainable Drainage Systems (SuDS). A multi-objective optimisation model coupled with a simulation model of UDS in the SWMM software is developed with the three objectives of minimising total costs, the risk of flooding and pollution discharged into receiving waters. K-means clustering technique is used to group the optimal solutions. A few optimal solutions and individual SuDS solutions are then ranked together by using the compromise programming (CP) method. The methodology is demonstrated by its application on a case study of the Golestan city UDS in Iran. The results obtained show there are indirect correlations between non-dominated solutions that minimise the risk of either flooding or pollution. The results also show the selected optimal solutions can provide cost-effective strategies that reduce both flood and pollution risks by at least 27% and 50%, respectively.@en

This study presents a novel approach for urban flood forecasting in drainage systems using a dynamic ensemble-based data mining model which has yet to be utilised properly in this context. The proposed method incorporates an event identification technique and rainfall feature extraction to develop weak learner data mining models. These models are then stacked to create a time-series ensemble model using a decision tree algorithm and confusion matrix-based blending method. The proposed model was compared to other commonly used ensemble models in a real-world urban drainage system in the UK. The results show that the proposed model achieves a higher hit rate compared to other benchmark models, with a hit rate of around 85% vs 70 % for the next 3 h of forecasting. Additionally, the proposed smart model can accurately classify various timesteps of flood or non-flood events without significant lag times, resulting in fewer false alarms, reduced unnecessary risk management actions, and lower costs in real-time early warning applications. The findings also demonstrate that two features, “antecedent precipitation history” and “seasonal time occurrence of rainfall,” significantly enhance the accuracy of flood forecasting with a hit rate accuracy ranging from 60 % to 10 % for a lead time of 15 min to 3 h.@en

Urban flooding is a major problem for cities around the world, with significant socio-economic consequences. Conventional real-time flood forecasting models rely on continuous time-series data and often have limited accuracy, especially for longer lead times than 2 hrs. This study proposes a novel event-based decision support algorithm for real-time flood forecasting using event-based data identification, event-based dataset generation, and a real-time decision tree flowchart using machine learning models. The results of applying the framework to a real-world case study demonstrate higher accuracy in forecasting water level rise, especially for longer lead times (e.g., 2–3 hrs), compared to traditional models. The proposed framework reduces root mean square error by 50%, increases accuracy of flood forecasting by 50%, and improves normalised Nash–Sutcliffe error by 20%. The proposed event-based dataset framework can significantly enhance the accuracy of flood forecasting, reducing the occurrences of both false alarms and flood missing and improving emergency response systems.@en

Although rainwater harvesting (RWH) schemes have gradually gained more credibility and popularity in recent times, efficient utilisation and larger scale implementation of multi-purpose RWH are still a challenging task. This paper aims to explore the potential of using smart RWH schemes and their impact on the efficiency improvement in integrated urban water systems (UWS). The smart RWH scheme analysed here is capable of proactively controlling the tank water level to ensure sufficient spare storage is maintained at all times that accommodates the runoff from storm events. The multi-purpose RWH tank can mitigate local floods during rainfall events and supply harvested rainwater to non-potable residential water consumption. Optimal design parameters of the smart RWH scheme are also identified to achieve the best operational performance of the UWS. WaterMet2 model is used to assess the performance of the UWS with smart RWH schemes. The efficiency of the proposed methodology is demonstrated through modelling a real case of integrated UWS. The results obtained indicate that utilisation of smart RWH with an optimally sized tank, compared to the corresponding conventional RWH, is able to significantly improve the UWS efficiency in terms of mitigation of local flooding and reliability of water supply from harvested rainwater.@en