Abstract: Rainwater harvesting (RWH) systems have been developed to compensate for shortage in the water supply worldwide. Such systems are not very common in arid areas, particularly in the Gulf Region, due to the scarcity of rainfall and their reduced efficiency in covering water demand and reducing water consumption rates. In spite of this, RWH systems have the potential to reduce urban flood risks, particularly in densely populated areas. This study aimed to assess the potential use of RWH systems as urban flood mitigation measures in arid areas. Their utility in the retention of stormwater runoff and the reduction of water depth and extent were evaluated. The study was conducted in a residential area in Bahrain that experienced waterlogging after heavy rainfall events. The water demand patterns of housing units were analyzed, and the daily water balance for RWH tanks was evaluated. The effect of the implementation of RWH systems on the flood volume was evaluated with a two-dimensional hydrodynamic model. Flood simulations were conducted in several rainfall scenarios with different probabilities of occurrence. The results showed significant reductions in the flood depth and flood extent, but these effects were highly dependent on the rainfall intensity of the event. RWH systems are effective flood mitigation measures, particularly in urban arid regions short of proper stormwater control infrastructure, and they enhance the resilience of the built environment to urban floods.

Abstract: Combined large-scale rainwater harvesting (RWH) and flood mitigation systems are promising as a sustainable water management strategy in urban areas. These are multi-purpose infrastructure that not only provide a secondary, localised water resource, but can also reduce discharge and hence loads on any downstream wastewater networks if these are integrated into the wider water network. However, the performance of these systems is dependent on the specific design used for its local catchment which can vary significantly between different implementations. A multitude of design strategies exist, however there is no universally accepted standard framework. To tackle these issues, this paper presents a two-player optimisation framework which utilises a stochastic design optimisation model and a competing, high-intensity rainfall design model to optimise passively-operated RWH systems. A customisable tool set is provided, under which optimisation models specific to a given catchment can be built quickly. This reduces the barriers to implementing computationally complex sizing strategies and encouraging more resource-efficient systems to be built. The framework was applied to a densely populated high-rise residential estate, eliminating overflow events from historical rainfall. The optimised configuration resulted in a 32% increase in harvested water yield, but its ability to meet irrigation demands was limited by the operational levels of the treatment pump. Hence, with the inclusion of operational levels in the optimisation model, the framework can provide an efficient large-scale RWH system that is capable of simultaneously meeting water demands and reducing stresses within and beyond its local catchment.

Abstract: The crucial role which groundwater resource plays in our environment and the overall well-being of all living things can not be underestimated. Nonetheless, mismanagement of resources, over-exploitation, inadequate supply of surface water and pollution have led to severe drought and an overall drop in groundwater resources’ levels over the past decades. To address this, a groundwater flow model and several mathematical data-driven models have been developed for forecasting groundwater levels. However, there is a problem of unavailability and scarcity of the on-site input data needed by the data-driven models to forecast the groundwater level. Furthermore, as a result of the dynamics and stochastic characteristics of groundwater, there is a need for an appropriate, accurate and reliable forecasting model to solve these challenges. Over the years, the broad application of Machine Learning (ML) and Artificial Intelligence (AI) models are gaining attraction as an alternative solution for forecasting groundwater levels. Against this background, this article provides an overview of forecasting methods for predicting groundwater levels. Also, this article uses ML models such as Regressions Models, Deep Auto-Regressive models, and Nonlinear Autoregressive Neural Networks with External Input (NARX) to forecast groundwater levels using the groundwater region 10 at Karst belt in South Africa as a case study. This was done using Python Mx. Version 1.9.1., and MATLAB R2022a machine learning toolboxes. Moreover, the Coefficient of Determination (R2);, Root Mean Square Error (RMSE), Mutual Information gain, Mean Absolute Percentage Error (MAPE), Mean Squared Error (MSE), Mean Absolute Error (MAE), and the Mean Absolute Scaled Error (MASE)) models were the forecasting statistical performance metrics used to assess the predictive performance of these models. The results obtained showed that NARX and Support Vector Machine (SVM) have higher performance metrics and accuracy compared to other models used in this study.