Abstract: Cities have experienced rapid urbanization-induced harsh climatic events, especially flooding, inevitably resulting in negative and irreversible consequences for urban resilience and endangering residents’ lives. Numerous studies have analyzed the effects of anthropogenic practices (land use changes and urbanization) on flood forecasting. However, non-structural mitigation’s effectiveness, like Nature-Based Solutions (NBS), has yet to receive adequate attention, particularly in the Middle East and North Africa (MENA) region, which have become increasingly significant and indispensable for operationalizing cities efficiently. Therefore, our study investigated the predictive influence of incorporating one of the most common NBS strategies called low-impact development tools (LID) (such as rain gardens, bio-retention cells, green roofs, infiltration trenches, permeable pavement, and vegetative swale) during the urban planning of Alexandria, Egypt, which experiences the harshest rainfall annually and includes various urban patterns. City characteristics-dependent 14 LID scenarios were simulated with recurrence intervals ranging from 2 to 100 years using the LID Treatment Train Tool (LID TTT), depending on calibrated data from 2015 to 2020, by the Nash-Sutcliffe efficiency index and deterministic coefficient, and root-mean-square error with values of 0.97, 0.91, and 0.31, respectively. Our findings confirmed the significant effectiveness of combined LID tools on total flood runoff volume reduction by 73.7%, revealing that different urban patterns can be used in flood-prone cities, provided LID tools are considered in city planning besides grey infrastructure to achieve optimal mitigation. These results, which combined multiple disciplines and were not explicitly mentioned in similar studies in developing countries, may assist municipalities’ policymakers in planning flood-resistant, sustainable cities.

Abstract: Groundwater resources around the world required periodic monitoring in order to ensure the safe and sustainable utilization for humans by keeping the good status of water quality. However, this could be a daunting task for developing countries due to the insufficient data in spatiotemporal resolution. Therefore, this research work aimed to assess groundwater quality in terms of drinking and irrigation purposes at the adjacent part of the Rooppur Nuclear Power Plant (RNPP) in Bangladesh. For the purposes of achieving the aim of this study, nine groundwater samples were collected seasonally (dry and wet season) and seventeen hydro-geochemical indicators were analyzed, including Temperature (Temp.), pH, electrical conductivity (EC), total dissolved solids (TDS), total alkalinity (TA), total hardness (TH), total organic carbon (TOC), bicarbonate (HCO3−), chloride (Cl−), phosphate (PO43−), sulfate (SO42−), nitrite (NO2−), nitrate (NO3−), sodium (Na+), potassium (K+), calcium (Ca2+) and magnesium (Mg2+). The present study utilized the Canadian Council of Ministers of the Environment water quality index (CCME-WQI) model to assess water quality for drinking purposes. In addition, nine indices including EC, TDS, TH, sodium adsorption ratio (SAR), percent sodium (Na%), permeability index (PI), Kelley’s ratio (KR), magnesium hazard ratio (MHR), soluble sodium percentage (SSP), and Residual sodium carbonate (RSC) were used in this research for assessing the water quality for irrigation purposes. The computed mean CCME-WQI score found higher during the dry season (ranges 48 to 74) than the wet season (ranges 40 to 65). Moreover, CCME-WQI model ranked groundwater quality between the “poor” and “marginal” categories during the wet season implying unsuitable water for human consumption. Like CCME-WQI model, majority of the irrigation index also demonstrated suitable water for crop cultivation during dry season. The findings of this research indicate that it requires additional care to improve the monitoring programme for protecting groundwater quality in the RNPP area. Insightful information from this study might be useful as baseline for national strategic planners in order to protect groundwater resources during the any emergencies associated with RNPP.

Abstract: Predicting groundwater levels is pivotal in curbing overexploitation and ensuring effective water resource governance. However, groundwater level prediction is intricate, driven by dynamic nonlinear factors. To comprehend the dynamic interaction among these drivers, leveraging machine learning models can provide valuable insights. The drastic increase in computational capabilities has catalysed a substantial surge in the utilisation of machine learning-based solutions for effective groundwater management. The performance of these models highly depends on the selection of hyperparameters. The optimisation of hyperparameters is a complex process that often requires application-specific expertise for a skillful prediction. To mitigate the challenge posed by hyperparameter tuning’s problem-specific nature, we present an innovative approach by introducing the automated machine learning (AutoML-GWL) framework. This framework is specifically designed for precise groundwater level mapping. It seamlessly integrates the selection of best machine learning model and adeptly fine-tunes its hyperparameters by using Bayesian optimisation. We used long time series (1997-2018) data of precipitation, temperature, evaporation, soil type, relative humidity, and lag of groundwater level as input features to train the AutoML-GWL model while considering the influence of Land Use Land Cover (LULC) as a contextual factor. Among these input features, the lag of groundwater level emerged as the most relevant input feature. Once the model is trained, it performs well over the unseen data with a strong correlation of coefficient (R = 0.90), low root mean square error (RMSE = 1.22), and minimal bias = 0.23. Further, we compared the performance of the proposed AutoML-GWL with sixteen benchmark algorithms comprising baseline and novel algorithms. The AutoML-GWL outperforms all the benchmark algorithms. Furthermore, the proposed algorithm ranked first in Friedman’s statistical test, confirming its reliability. Moreover, we conducted a spatial distribution and uncertainty analysis for the proposed algorithm. The outcomes of this analysis affirmed that the AutoML-GWL can effectively manage data with spatial variations and demonstrates remarkable stability when faced with small uncertainties in the input parameters. This study holds significant promise in revolutionising groundwater management practices by establishing an automated framework for simulating groundwater levels for sustainable water resource management.