Editor’s Choice Articles

The aim of the study was to investigate the utility of artificial neural networks (ANNs) for the estimation of reference evapotranspiration (ETo) on the Peloponnese Peninsula in Greece for two representative months of wintertime and summertime during 2016–2019 and to test if using fewer inputs could lead to satisfactory predictions. Datasets from sixty-two meteorological stations were employed. The available inputs were mean temperature (Tmean), sunshine (N), solar radiation (Rs), net radiation (Rn), vapour pressure deficit (es-ea), wind speed (u₂) and altitude (Z). Nineteen Multi-layer Perceptron (MLP) and Radial Basis Function (RBF) models were tested and compared against the corresponding FAO-56 Penman Monteith (FAO PM) estimates of a previous study, via statistical indices. The MLP1 7-2 model with all the variables as inputs outperformed the rest of the models (RMSE = 0.290 mm d⁻¹, R² = 98%). The results indicate that even ANNs with simple architecture can be very good predictive models of ETo for the Peloponnese, based on the literature standards. The MLP1 model determined Tmean, followed by u_2, as the two most influential factors for ETo. Moreover, when one input was used (Tmean, Rn), RBFs slightly outperformed MLPs (RMSE < 0.385 mm d⁻¹, R² ≥ 96%), which means that even a sole-input ANN resulted in satisfactory predictions of ETo. Full article

The Red River of the North is vulnerable to floods, which have caused significant damage and economic loss to inhabitants. A better capability in flood-event prediction is essential to decision-makers for planning flood-loss-reduction strategies. Over the last decades, classical statistical methods and Machine Learning (ML) algorithms have greatly contributed to the growth of data-driven forecasting systems that provide cost-effective solutions and improved performance in simulating the complex physical processes of floods using mathematical expressions. To make improvements to flood prediction for the Red River of the North, this paper presents effective approaches that make use of a classical statistical method, a classical ML algorithm, and a state-of-the-art Deep Learning method. Respectively, the methods are seasonal autoregressive integrated moving average (SARIMA), Random Forest (RF), and Long Short-Term Memory (LSTM). We used hourly level records from three U.S. Geological Survey (USGS), at Pembina, Drayton, and Grand Forks stations with twelve years of data (2007–2019), to evaluate the water level at six hours, twelve hours, one day, three days, and one week in advance. Pembina, at the downstream location, has a water level gauge but not a flow-gauging station, unlike the others. The floodwater-level-prediction results show that the LSTM method outperforms the SARIMA and RF methods. For the one-week-ahead prediction, the RMSE values for Pembina, Drayton, and Grand Forks are 0.190, 0.151, and 0.107, respectively. These results demonstrate the high precision of the Deep Learning algorithm as a reliable choice for flood-water-level prediction. Full article

The many hydrodynamic implications associated with the geomorphological evolution of braided rivers are still not profoundly examined in both experimental and numerical analyses, due to the generation of three-dimensional turbulence structures around sediment bars. In this experimental research, the 3D velocity fields were measured through an acoustic Doppler velocimeter during flume-scale laboratory experimental runs over an emerging sand bar model, to reproduce the hydrodynamic conditions of real braided rivers, and the 3D Turbulent Kinetic Energy (TKE) components were analyzed and discussed here in detail. Given the three-dimensionality of the examined water flow in the proximity of the experimental bar, the statistical analysis of the octagonal bursting events was applied to analyze and discuss the different flume-scale 3D turbulence structures. The main novelty of this study is the proposal of the 3D Hole Size (3DHS) analysis, used for separating the extreme events observed in the experimental runs from the low-intensity events. Full article

Groundwater irrigation has a critical role in the sustainability of arable farming in many developing countries including Pakistan. Groundwater irrigation is generally practiced to supplement surface water supplies in Pakistan. Nevertheless, uninterrupted and extensive use of groundwater irrigation has raised several concerns about its sustainability and resultant environmental implications. Due to the scarcity of groundwater and heterogeneity in farmers’ resources, informal groundwater markets have emerged in Pakistan, where farmers trade water using a contractual system. Yet, the effects of these markets on agricultural productivity and equity remain largely unknown. This paper aims to analyze the impact of participation in the groundwater market on farmland utilization, cropping patterns, water access, and income. We analyze these impacts using primary data collected from 360 farmers in three different zones of the country’s largest province. The farmers were categorized as buyers, sellers, and self-users of water. Results indicate that participation in water markets increased agricultural land utilization, evinced by a higher cropping intensity among participants. A horizontal and vertical equity analysis of water markets shows that although large farmers have better access to groundwater irrigation, water market participation improves equity to water access. Based on income inequality measures such as the Gini coefficient and the Lorenz curve, water market participation also improves farmer incomes regardless of farm size. Propensity score matching revealed that wheat yield and income among water-market participants went up by approximately 150 kg and PKR 4503 per acre compared with non-participants. Groundwater market participants’ higher crop productivity and income level suggest that water markets need a thorough revisit in terms of policy focus and institutional support to ensure sustainable rural development. Full article

Due to the increased demand for clothes by the growing population, the dye-based sectors have seen fast growth in the recent decade. Among all the dyes, methylene blue dye is the most commonly used in textiles, resulting in dye effluent contamination. It is carcinogenic, which raises the stakes for the environment. The numerous sources of methylene blue dye and their effective treatment procedures are addressed in the current review. Even among nanoparticles, photocatalytic materials, such as TiO₂, ZnO, and Fe₃O₄, have shown greater potential for photocatalytic methylene blue degradation. Such nano-sized metal oxides are the most ideal materials for the removal of water pollutants, as these materials are related to the qualities of flexibility, simplicity, efficiency, versatility, and high surface reactivity. The use of nanoparticles generated from waste materials to remediate methylene blue is highlighted in the present review. Full article

Nowadays, many major copper mining projects in desert areas with extremely dry climates, as in northern Chile and the southern coast of Peru, process sulfide ores at high production rates; in some cases over 100,000 metric tonnes per day (mtpd), generating large amounts of tailings, that are commonly managed and transported to tailings storage facilities (TSF) hydraulically using fresh water. Considering the extremely dry climate, water scarcity, community demands, and environmental constraints in these desert areas, the efficient use of water in mining is being strongly enforced. For this reason, water supply is recognized as one of the limiting factors for the development of new mining projects and for the expansion of the existing ones in these areas. New water supply alternatives, such as sea water desalinization, direct use of sea water, or water recovery from tailings, represent the strategy developed by the mining industry to deal with this growing scarcity. The focus of this paper is the possibility of applying different water supply technologies or a combination of these, implementing improved water management strategies that consider: environmental issues, technical issues, stringent regulatory frameworks, community requests and cost-effective strategies, that result in a reduction of freshwater make-up water requirements for mining (m³ per metric tonnes of treated ore). Full article

Arsenic (As) is a non-metallic element, which is widely distributed in nature. Due to its toxicity, arsenic is seriously harmful to human health and the environment. Therefore, it is particularly important to effectively remove arsenic from water. Biochar is a carbon-rich adsorption material with advantages such as large specific surface area, high porosity, and abundant functional groups, but the original biochar has limitations in application, such as limited adsorption capacity and adsorption range. The modified biochar materials have largely enhanced the adsorption capacity of As in water due to their improved physicochemical properties. In this review, the changes in the physicochemical properties of biochar before and after modification were compared by SEM, XRD, XPS, FT-IR, TG, and other characterization techniques. Through the analysis, it was found that the adsorbent dosage and pH are the major factors that influence the As adsorption capacity of the modified biochar. The adsorption process of As by biochar is endothermic, and increasing the reaction temperature is conducive to the progress of adsorption. Results showed that the main mechanisms include complexation, electrostatic interaction, and precipitation for the As removal by the modified biochar. Research in the field of biochar is progressing rapidly, with numerous achievements and new types of biochar-based materials prepared with super-strong adsorption capacity for As. There is still much space for in-depth research in this field. Therefore, the future research interests and applications are put forward in this review. Full article

The increase in heavy metal contamination has led to an increase in studies investigating alternative sustainable ways to treat heavy metals. Nanotechnology has been shown to be an environmentally friendly technology for treating heavy metals and other contaminants from contaminated water. However, this technology is not widely used in wastewater treatment plants (WWTPs) due to high operational costs. The increasing interest in reducing costs by applying nanotechnology in wastewater treatment has resulted in an increase in studies investigating sustainable ways of producing nanoparticles. Certain researchers have suggested that sustainable and cheap raw materials must be used for the production of cheaper nanoparticles. This has led to an increase in studies investigating the production of nanoparticles from plant materials. Additionally, production of nanoparticles through biological methods has also been recognized as a promising, cost-effective method of producing nanoparticles. Some studies have shown that the recycling of nanoparticles can potentially reduce the costs of using freshly produced nanoparticles. This review evaluates the economic impact of these new developments on nanotechnology in wastewater treatment. An in-depth market assessment of nanoparticle application and the economic feasibility of nanoparticle applications in WWTPs is presented. Moreover, the challenges and opportunities of using nanoparticles for heavy metal removal are also discussed. Full article

In recent years, China has been committed to strengthening environmental governance and trying to build a sustainable society in which humans and nature develop in harmony. As a new urban construction concept, sponge city uses natural and ecological methods to retain rainwater, alleviate flooding problems, reduce the damage to the water environment, and gradually restore the hydrological balance of the construction area. The paper presents a review of sponge city construction from its inception to systematic demonstration. In this paper, research gaps are discussed and future efforts are proposed. The main contents include: (1) China’s sponge city construction includes but is not limited to source control or a drainage system design. Sponge city embodies foreign experience and the wisdom of ancient Chinese philosophy. The core of sponge city construction is to combine various specific technologies to alleviate urban water problems such as flooding, water environment pollution, shortage of water resources and deterioration of water ecology; (2) this paper also introduces the sponge city pilot projects in China, and summarizes the achievements obtained and lessons learned, which are valuable for future sponge city implementation; (3) the objectives, corresponding indicators, key contents and needs of sponge city construction at various scales are different. The work at the facility level is dedicated to alleviating urban water problems through reasonable facility scale and layout, while the work at the plot level is mainly to improve the living environment through sponge city construction. The construction of urban and watershed scales is more inclined to ecological restoration and blue-green storage spaces construction. Besides, the paper also describes the due obligations in sponge city construction of various stakeholders. Full article

Basin ecohydrological processes are essential for informing policymaking and social development in response to growing environmental problems. In this paper, we review watershed ecohydrology, focusing on the interaction between watershed ecological and hydrological processes. Climate change and human activities are the most important factors influencing water quantity and quality, and there is a need to integrate watershed socioeconomic activities into the paradigm of watershed ecohydrological process studies. Then, we propose a new framework for integrated watershed management. It includes (1) data collection: building an integrated observation network; (2) theoretical basis: attribution analysis; (3) integrated modeling: medium- and long-term prediction of ecohydrological processes by human–nature interactions; and (4) policy orientation. The paper was a potential solution to overcome challenges in the context of frequent climate extremes and rapid land-use change. Full article

More frequent and more intense heat waves and greater drought stress will occur in the future climate environment. Short-term extreme heat and drought stress often occur simultaneously after winter wheat anthesis, which has become the major constraint threatening future wheat yield. In this study, short-term heat, drought and their combination stress were applied to wheat plants after anthesis, and all wheat plants were restored to the outdoor normal temperature and full watering after stress treatment. The aim of the current study was to evaluate the role of nitrogen (N) in modulating the effects of post-anthesis short-term heat, drought and their combination stress on photosynthesis, N metabolism-related enzymes, the accumulation of N and protein and growth, as well as on the yield and water (WUE) and N use efficiency (NUE) of wheat after stress treatment. The results showed that compared with low N application (N1), medium application (N2) enhanced the activities of nitrate reductase (NR) and glutamine synthase (GS) in grains under post-anthesis heat and drought stress alone, which provided a basis for the accumulation of N and protein in grains at the later stage of growth. Under post-anthesis individual stresses, N2 or high application (N3) increased the leaf photosynthetic rate (A_n), PSII photochemical efficiency and instantaneous WUE compared with N1, whereas these parameters were usually significantly improved by N1 application under post-anthesis combined stress. The positive effect of increased A_n by N application on growth was well represented in a higher green leaf area, aboveground dry mass and plant height, and the variation in A_n can be explained more accurately by the N content per unit leaf area. Short-term heat, drought and combined stress after anthesis resulted in a pronounced decrease in yield by reducing grain number per spike and thousand kernel weight. The reduction in NUE under combined stress was higher than that under individual heat and drought stress. Compared with N1, N2 or N3 application significantly prevented the decrease in yield and NUE caused by post-anthesis heat and drought stress alone. However, N1 application was conducive to improving the productivity, WUE and NUE of wheat when exposed to post-anthesis combined stress. The current data indicated that under short-term individual heat and drought stress after anthesis, appropriately increasing N application effectively improved the growth and physiological activity of wheat compared with N1, alleviating the reduction in yield, WUE and NUE. However, under combined stress conditions, reducing N application (N1) may be a suitable strategy to compensate for the decrease in yield, WUE and NUE. Full article

Artificial-intelligence methods and machine-learning models have demonstrated their ability to optimize, model, and automate critical water- and wastewater-treatment applications, natural-systems monitoring and management, and water-based agriculture such as hydroponics and aquaponics. In addition to providing computer-assisted aid to complex issues surrounding water chemistry and physical/biological processes, artificial intelligence and machine-learning (AI/ML) applications are anticipated to further optimize water-based applications and decrease capital expenses. This review offers a cross-section of peer reviewed, critical water-based applications that have been coupled with AI or ML, including chlorination, adsorption, membrane filtration, water-quality-index monitoring, water-quality-parameter modeling, river-level monitoring, and aquaponics/hydroponics automation/monitoring. Although success in control, optimization, and modeling has been achieved with the AI methods, ML models, and smart technologies (including the Internet of Things (IoT), sensors, and systems based on these technologies) that are reviewed herein, key challenges and limitations were common and pervasive throughout. Poor data management, low explainability, poor model reproducibility and standardization, as well as a lack of academic transparency are all important hurdles to overcome in order to successfully implement these intelligent applications. Recommendations to aid explainability, data management, reproducibility, and model causality are offered in order to overcome these hurdles and continue the successful implementation of these powerful tools. Full article

The lack of valuable baseline information about groundwater availability hinders the robust decision-making process of water management in humid, arid, and semi-arid climate regions of the world. In sustainable groundwater management, identifying the spatiotemporal and extrapolative monitoring of potential zone is crucial. Thus, the present study focused on determining potential aquifer recharge zones using geospatial techniques for proxy data of the Gilgel Gibe catchment, Ethiopia. Proxy data are site information derived from satellite imageries or conventional sources that are operated as a layer attribute in the geographical information system (GIS) to identify groundwater occurrence. First, GIS and analytical hierarchy process (AHP) were applied to analyze ten groundwater recharge controlling factors: slope, lithology, topographic position index lineament density, rainfall, soil, elevation, land use/cover, topographic wetness index, and drainage density. Each layer was given relative rank priority depending on the predictive implication of groundwater potentiality. Next, the normalized weight of thematic layers was evaluated using a multi-criteria decision analysis AHP algorithm with a pairwise comparison matrix based on aquifer infiltration relative significance. Lithology, rainfall, and land use/cover were dominant factors covering a weight of 50%. The computed consistency ratio (CR = 0.092, less than 10%) and consistency index (CI = 0.1371) revealed the reliability of input proxy layers’ in the analysis. Then, a GIS-based weighted overlay analysis was performed to delineate very high, high, moderate, low, and very low potential aquifer zones. The delineated map ensures very high (29%), high (25%), moderate (28%), low (13%), and very low (5%) of the total area. According to validation, most of the inventory wells are located in very high (57%), high (32), and moderate (12%) zones. The validation results realized that the method affords substantial results supportive of sustainable development and groundwater exploitation. Therefore, this study could be a vigorous input to enhance development programs to alleviate water scarcity in the study area. Full article

Owing to environmental pollution and increasingly strict regulations, heavy metals have attracted the attention of many researchers in various disciplines. Alginate and chitosan derivatives have gained popularity as biosorbents for water treatment. An increase in the number of publications on modified biosorbents for the biosorption of toxic compounds reveals widespread interest in examining the requirements and positive contribution of each modification type. This paper reviews the advantages and disadvantages of using alginate and chitosan for adsorption. Well-known modifications based on chitosan and alginate, namely, grafting, functionalization, copolymerization and cross-linking, as well as applications in the field of adsorption processes, especially amino acid functionalization, are reviewed. The selection criteria for the best biosorbents and their effectiveness and proposed mechanism of adsorption are discussed critically. In the conclusion, the question of why these adsorbents need modification before use is addressed. Full article

Nowadays, in the management of water distribution networks (WDNs), particular attention is paid to digital transition and the improvement of the energy efficiency of these systems. New technologies have been developed in the recent years and their implementation can be crucial to achieve a sustainable level of water networks, namely, in water and energy losses. In particular, Digital Twins (DT) represents a very innovative technology, which relies on the integration of virtual network models, optimization algorithms, real time data collection, and smart actuators information with Geographic Information System (GIS) data. This research defines a new methodology for an efficient application of DT expertise within water distribution networks. Assuming a DMA of a real water distribution network as a case study, it was demonstrated that a fast detection of leakage along with an optimal setting of pressure control valves by means of DT together with an optimization procedure can ensure up to 28% of water savings, contributing to significantly increase the efficiency of the whole system. Full article

Algal blooms have various effects on drinking water supply systems; thus, proper monitoring is essential. Traditional visual identification using a microscope is a time-consuming method and requires extensive labor. Recently, advanced machine learning algorithms have been increasingly applied for the development of object detection models. The You-Only-Look-Once (YOLO) model is a novel machine learning algorithm used for object detection; it has been continuously improved in newer versions, and a tiny version of each standard model presented. The tiny versions applied a less complicated architecture using a smaller number of convolutional layers to enable faster object detection than the standard version. This study compared the applicability of the YOLO models for algal image detection from a practical aspect in terms of classification accuracy and inference time. Therefore, automated algal cell detection models were developed using YOLO v3 and YOLO v4, in which a tiny version of each model was also applied. The cell images of 30 algal genera were used for training and testing the models. The model performances were compared using the mean average precision (mAP). The mAP values of the four models were 40.9, 88.8, 84.4, and 89.8 for YOLO v3, YOLO v3-tiny, YOLO v4, and YOLO v4-tiny, respectively, demonstrating that YOLO v4 is more precise than YOLO v3. The tiny version models presented noticeably higher model accuracy than the standard models, allowing up to ten times faster object detection time. These results demonstrate the practical advantage of tiny version models for the application of object detection with a limited number of object classes. Full article

This review focuses on the use of Interpretable Artificial Intelligence (IAI) and eXplainable Artificial Intelligence (XAI) models for data imputations and numerical or categorical hydroclimatic predictions from nonlinearly combined multidimensional predictors. The AI models considered in this paper involve Extreme Gradient Boosting, Light Gradient Boosting, Categorical Boosting, Extremely Randomized Trees, and Random Forest. These AI models can transform into XAI models when they are coupled with the explanatory methods such as the Shapley additive explanations and local interpretable model-agnostic explanations. The review highlights that the IAI models are capable of unveiling the rationale behind the predictions while XAI models are capable of discovering new knowledge and justifying AI-based results, which are critical for enhanced accountability of AI-driven predictions. The review also elaborates the importance of domain knowledge and interventional IAI modeling, potential advantages and disadvantages of hybrid IAI and non-IAI predictive modeling, unequivocal importance of balanced data in categorical decisions, and the choice and performance of IAI versus physics-based modeling. The review concludes with a proposed XAI framework to enhance the interpretability and explainability of AI models for hydroclimatic applications. Full article

Sluice gates are common hydraulic structures for controlling and regulating flow in open channels. This study investigates five models’ performance in distinguishing conditions of flow regimes, estimating the discharge coefficient ($C_d$) and flow rate. Experiments were conducted for different gate openings, flow rates, upstream and downstream conditions. New equation forms and methods are proposed to determine $C_d$ for energy–momentum considering losses (EML) and HEC-RAS models. For distinguishing the flow regimes, results indicated a reasonable performance for energy–momentum (EM), EML, and Swamee’s models. For flow rate and discharge coefficient performance of EM, EML, and Henry’s models in free flow and for EM and EML in submerged flow were reasonable. The effects of physical scale on models were investigated. There were concerns about the generality and accuracy of Swamee’s model. Scaling effects were observed on loss factor k in EML. A new equation and method were proposed to calibrate k that improved the EML model’s accuracy. This study facilitates the application and analysis of the studied models for the design or calibration of sluice gates and where the flow in open channels needs to be controlled or measured using sluice gates such as irrigation channels or water delivery channels of small run-of-river hydropower plants. Full article

Routine maintenance of fishing vessels and wastewater discharges are primary sources of heavy metals in fishing ports. Sediment pollution assessment is necessary in fishing port management, including sediment dredging and disposal, sewage treatment facility construction, and pollution source control. In this study, sediment heavy metal contents in Qianzhen Fishing Port, the largest pelagic fishery port in Taiwan, were investigated to assess the contamination levels and related potential ecological risks using multiple sediment pollution indices. Normalization methods were applied to identify the potential sources of heavy metals in fishing port sediments. Results showed that Cu, Zn, Pb, and Cr contents in the sediments of the inner fishing port (averages of 276, 742, 113, and 221 mg/kg, respectively) were 3–5 times greater compared to those along the port entrance and outside, indicating the strong impacts of anthropogenic pollution (EF_Cu: 5.6–12.5; EF_Zn: 2.8–4.3; EF_Pb: 2.4–5.4; EF_Cr: 1.1–3.2). Copper pollution was more severe, with high maxima contamination factor (CF_Cu: 15.1–24.8), probably contributed by copper-based antifouling paints used in fishing vessels. The sediments in the inner fishing port are categorized as having considerable ecological risk and toxicity (mERMq: 0.61–0.91; ΣTU: 7.5–11.7) that can potentially cause adverse effects on benthic organisms. Qianzhen Fishing Port sediments can be characterized as high Cu/Fe and Pb/Fe, moderate Zn/Fe, and high total grease content, indicating that the potential sources of heavy metals are primarily antifouling paints and oil spills from the fishing vessels. This study provides valuable data for pollution control, remediation, and environmental management of fishing ports. Full article

Water is an imperative part of the Earth and an essential resource in human life and production. Under the effects of climate change and human activities, the spatial and temporal distribution of water bodies has been changing, and the shortage of water resources is becoming increasingly serious worldwide. Therefore, the monitoring of water bodies is indispensable. Remote sensing has the advantages of real time, wide coverage, and rich information and has become a brand-new technical means to quickly obtain water information. This study summarizes the current common methods of water extraction based on optical and radar images, including the threshold method, support vector machine, decision tree, object-oriented extraction, and deep learning, as well as the advantages and disadvantages of each method. These methods were applied to the Huai River Basin in China and Nam Co on the Qinghai-Tibet Plateau. The extraction results show that all the aforementioned approaches can obtain reliable results. Among them, the threshold segmentation method based on normalized difference water index is more robust than others. In the water extraction process, there are still many problems that restrict the accuracy of the results. In the future, researchers will continue to search for more automatic, extensive, and high-precision water extraction methods. Full article

Urban flooding poses risks to the safety of drivers and pedestrians, and damages infrastructures and lifelines. It is important to accommodate cities and local agencies with enhanced rapid flood detection skills and tools to better understand how much flooding a region may experience at a certain period of time. This results in flood management orders being announced in a timely manner, allowing residents and drivers to preemptively avoid flooded areas. This research combines information received from ground observed data derived from road closure reports from the police department, with remotely sensed satellite imagery to develop and train machine-learning models for flood detection for the City of San Diego, CA, USA. For this purpose, flooding information are extracted from Sentinel 1 satellite imagery and fed into various supervised and unsupervised machine learning models, including Random Forest (RF), Support Vector Machine (SVM), and Maximum Likelihood Classifier (MLC), to detect flooded pixels in images and evaluate the performance of these ML models. Moreover, a new unsupervised machine learning framework is developed which works based on the change detection (CD) approach and combines the Otsu algorithm, fuzzy rules, and iso-clustering methods for urban flood detection. Results from the performance evaluation of RF, SVM, MLC and CD models show 0.53, 0.85, 0.75 and 0.81 precision measures, 0.9, 0.85, 0.85 and 0.9 for recall values, 0.67, 0.85, 0.79 and 0.85 for the F1-score, and 0.69, 0.87, 0.83 and 0.87 for the accuracy measure, respectively, for each model. In conclusion, the new unsupervised flood image classification and detection method offers better performance with the least required data and computational time for enhanced rapid flood mapping. This systematic approach will be potentially useful for other cities at risk of urban flooding, and hopefully for detecting nuisance floods, by using satellite images and reducing the flood risk of transportation design and urban infrastructure planning. Full article

On 11 March 2020, the World Health Organization declared the new COVID-19 disease a pandemic. Most countries responded with a lockdown to reduce its effects, which brought beneficial consequences to the environment in many regions, but the pandemic also raised a series of challenges. This review proposes an assessment of the COVID-19 pandemic positive and negative impacts on water bodies on different continents. By applying a search protocol on the Web of Science platform, a scientific bank of 35 compatible studies was obtained out of the 62 open-access articles that were initially accessible. Regarding the positive impacts, the SARS-CoV-2 monitoring in sewage waters is a useful mechanism in the promptly exposure of community infections and, during the pandemic, many water bodies all over the world had lower pollution levels. The negative impacts are as follows: SARS-CoV-2 presence in untreated sewage water amplifies the risk to human health; there is a lack of adequate elimination processes of plastics, drugs, and biological pollution in wastewater treatment plants; the amount of municipal and medical waste that pollutes water bodies increased; and waste recycling decreased. Urgent preventive measures need to be taken to implement effective solutions for water protection. Full article

The precipitation phase (i.e., rain and snow) is important for the global hydrologic cycle and climate system. The objective of this study is to evaluate the precipitation-phase partitioning capabilities of remote sensing and reanalysis modeling methods on the global scale. Specifically, observation data from the National Centers for Environmental Prediction (NCEP) Automated Data Processing (ADP), from 2000 to 2007, are used to evaluate the rain–snow discrimination accuracy of the Integrated Multi-Satellite Retrievals for Global Precipitation Measurement (IMERG) and the fifth-generation reanalysis product of the European Centre for Medium Range Weather Forecasts (ERA5). The results show that: (1) the ERA5 performs better than the IMERG at distinguishing rainfall and snowfall events, overall. (2) The ERA5 has high accuracy in all continents except for South America, while the IMERG performs well only in Antarctica and North America. (3) Compared with the IMERG, the ERA5 can more effectively capture snowfall events at high latitudes but shows worse performance at mid-low latitude regions. Both the IMERG and ERA5 have lower accuracy for rain–snow partitioning under heavy precipitation. Overall, the results of this study provide references for the application and improvement of global rain–snow partitioning products. Full article

To provide real-time prediction of wastewater treatment plant (WWTP) effluent water quality, a machine learning (ML) model was developed by combining an improved feedforward neural network (IFFNN) with an optimization algorithm. Data used as input variables of the IFFNN included hourly influent water quality parameters, influent flow rate and WWTP process monitoring and operational parameters. Additionally, input variables included historical effluent water quality parameters for future prediction. The model was demonstrated in a WWTP in Jiangsu Province, China, where prediction of effluent chemical oxygen demand (COD) and total nitrogen (TN) with large variations were tested. Relative to the traditional feedforward neural network (FFNN) model without considering historical effluent water quality parameter input, the IFFNN enhanced prediction performance by 52.3% (COD) and 72.6% (TN) based on the mean absolute percentage errors of test datasets, after its model structure was optimized with a genetic algorithm (GA). The problem of over-fitting could also be overcome through the use of the IFFNN, with the determination of coefficient increased from 0.20 to 0.76 for test datasets of effluent COD. The GA-IFFNN model, which was efficient in capturing complex non-linear relationships and extrapolation, could be a useful tool for real-time direction of regulatory changes in WWTP operations. Full article

Exploring alternative freshwater resources other than those surrounding the Nile is critical to disperse Egypt’s population to other uninhabited desert areas. This study aims to locate groundwater potential zones (GWPZs) in the water-scarce desert between the Qina and Safga-Bir Queh regions to build groundwater wells, thereby attracting and supporting people’s demand for water, food, and urban development. Multi-criteria evaluation (MCE) and analytical hierarchical process (AHP) techniques based on remote sensing (RS) and Geographic Information System (GIS) were used to map GWPZs. The outcome of the GWPZs map was divided into six different classes. High and very-high aquifer recharge potentials were localized in the middle and western parts, spanning 19.3% and 17% (16.4% and 15.7%) by MCE (AHP). Low and very low aquifer recharge potentials were distributed randomly in the eastern part over an area of 29% and 14.3% (26.9% and 6.1%) by MCE (AHP). Validation has been undertaken between the collected Total Dissolved Solid (TDS) and with the calculated GWPZs, indicating that the highest and lowest TDS concentrations of most aquifers are correlated with low to very low and high to very high aquifer potential, respectively. The study is promising and can be applied anywhere with similar setups for groundwater prospect and management. Full article

Although machine learning (ML) techniques are increasingly used in rainfall-runoff models, most of them are based on one-dimensional datasets. In this study, a rainfall-runoff model with deep learning algorithms (CNN-LSTM) was proposed to compute runoff in the watershed based on two-dimensional rainfall radar maps directly. The model explored a convolutional neural network (CNN) to process two-dimensional rainfall maps and long short-term memory (LSTM) to process one-dimensional output data from the CNN and the upstream runoff in order to calculate the flow of the downstream runoff. In addition, the Elbe River basin in Sachsen, Germany, was selected as the study area, and the high-water periods of 2006, 2011, and 2013, and the low-water periods of 2015 and 2018 were used as the study periods. Via the fivefold validation, we found that the Nash–Sutcliffe efficiency (NSE) and Kling–Gupta efficiency (KGE) fluctuated from 0.46 to 0.97 and from 0.47 to 0.92 for the high-water period, where the optimal fold achieved 0.97 and 0.92, respectively. For the low-water period, the NSE and KGE ranged from 0.63 to 0.86 and from 0.68 to 0.93, where the optimal fold achieved 0.86 and 0.93, respectively. Our results demonstrate that CNN-LSTM would be useful for estimating water availability and flood alerts for river basin management. Full article

Understanding salinity and fertilizer interaction is of great importance to improve crop production and fertilizer use efficiency in saline areas. To evaluate the interactive effects of different soil salinity levels and nitrogen (N) applications rates on the sunflower photosynthetic characteristics of N uptake and N use efficiency, a two-year field experiment was conducted in Hetao Irrigation District, China. The experiment consisted of three initial salinity (IS) levels expressed as the electrical conductivity of a saturated soil extract (EC_e) (S0: 1.72–2.61 dS/m; S1: 4.73–5.90 dS/m; S2: 6.85–9.04 dS/m) and four N rates (45, 90, 135, and 180 kg/ha), referred as N0–N3, respectively. The results indicated that the net photosynthetic rate (Pn) of sunflowers treated with S0 and S1 levels both had a significant decrease in the bud stage, and then reached their maximum at anthesis. However, during the crop cycle, the Pn at S2 level only had small fluctuations and still remained at a high level (>40 μmol CO₂/(m² s)) at the early mature stage. When increasing IS levels from S0 to S1, the plant N uptake (PNU) under the same N rates were only decreased by less than 10% at maturity, whereas the decline was expanded to 17.2–45.7% from S1 to S2. Additionally, though applying the N2 rate could not increase sunflower PNU at the S0 and S1 levels, its N use efficiency was better than those under N3. Meanwhile, at the S2 level, the application of the N0 rate produced a higher N productive efficiency (NPE) and N uptake efficiency (NUPE) than the other N rates. Therefore, our study proposed recommended rates of N fertilizer (S0 and S1: 135 kg/ha, S2: 45 kg/ha) for sunflowers under different saline conditions. Full article

Antibiotics are the most common pharmaceutical compounds, and they have been extensively used for the prevention and treatment of bacterial diseases for more than 50 years. However, merely a small fraction of antibiotics is metabolized in the body, while the rest is discharged into the environment through excretion, which can cause potential ecological problems and human health risks. In this study, the elimination of seventeen antibiotics from real livestock wastewater effluents was investigated by UV/TiO₂ advanced oxidation process. The effect of process parameters, such as TiO₂ loadings, solution pHs, and antibiotic concentrations, on the efficiency of the UV/TiO₂ process was assessed. The degradation efficiency was affected by the solution pH, and higher removal efficiency was observed at pH 5.8 and 9.9, while the catalyst loading had no significant effect on the degradation efficiency at these experimental conditions. UV photolysis showed a good removal efficiency of the antibiotics. However, the highest removal efficiency was shown by the UV/photocatalyst system due to their synergistic effects. The results showed that more than 90% of antibiotics were removed by UV/TiO₂ system during the 60 min illumination, while the corresponding TOC and COD removal was only 10 and 13%, respectively. The results of the current study indicated that UV/TiO₂ advanced oxidation process is a promising method for the elimination of various types of antibiotics from real livestock wastewater effluents. Full article

Antibiotic resistance is a global concern for human, animal, and environmental health. Many studies have identified wastewater treatment plants and surface waters as major reservoirs of antibiotic resistant bacteria (ARB) and genes (ARGs). Yet their prevalence in urban karst groundwater systems remains largely unexplored. Considering the extent of karst groundwater use globally, and the growing urban areas in these regions, there is an urgent need to understand antibiotic resistance in karst systems to protect source water and human health. This study evaluated the prevalence of ARGs associated with resistance phenotypes at 10 urban karst features in Bowling Green, Kentucky weekly for 46 weeks. To expand the understanding of prevalence in urban karst, a spot sampling of 45 sites in the Tampa Bay Metropolitan area, Florida was also conducted. Specifically, this study considered tetracycline and extended spectrum beta-lactamase (ESBLs) producing, including third generation cephalosporin, resistant E. coli, and tetracycline and macrolide resistant Enterococcus spp. across the 443 Kentucky and 45 Florida samples. A consistent prevalence of clinically relevant and urban associated ARGs were found throughout the urban karst systems, regardless of varying urban development, karst geology, climate, or landuse. These findings indicate urban karst groundwater as a reservoir for antibiotic resistance, potentially threatening human health. Full article

Groundwater is a vital source of freshwater, supporting the livelihood of over two billion people worldwide. The quantitative assessment of groundwater resources is critical for sustainable management of this strained resource, particularly as climate warming, population growth, and socioeconomic development further press the water resources. Rapid growth in the availability of a plethora of in-situ and remotely sensed data alongside advancements in data-driven methods and machine learning offer immense opportunities for an improved assessment of groundwater resources at the local to global levels. This systematic review documents the advancements in this field and evaluates the accuracy of various models, following the protocol developed by the Center for Evidence-Based Conservation. A total of 197 original peer-reviewed articles from 2010–2020 and from 28 countries that employ regression machine learning algorithms for groundwater monitoring or prediction are analyzed and their results are aggregated through a meta-analysis. Our analysis points to the capability of machine learning models to monitor/predict different characteristics of groundwater resources effectively and efficiently. Modeling the groundwater level is the most popular application of machine learning models, and the groundwater level in previous time steps is the most employed input data. The feed-forward artificial neural network is the most employed and accurate model, although the model performance does not exhibit a striking dependence on the model choice, but rather the information content of the input variables. Around 10–12 years of data are required to develop an acceptable machine learning model with a monthly temporal resolution. Finally, advances in machine and deep learning algorithms and computational advancements to merge them with physics-based models offer unprecedented opportunities to employ new information, e.g., InSAR data, for increased spatiotemporal resolution and accuracy of groundwater monitoring and prediction. Full article

Coal slurry is an essential component of mining operations, accounting for more than half of operating costs. Dewatering technology is simultaneously confronted with obstacles and possibilities, and it may yet be improved as the crucial step for reducing the ultimate processing cost. Coagulation/flocculation is used as a dewatering process that is reasonably cost-effective and user-friendly. This paper reviews application of different coagulants/flocculants and their combinations in dewatering mechanisms. In this context, various polymeric flocculants are discussed in the coal slurry in depth. Many operational parameters that influence the performance of coal slurry flocculation are also presented. Furthermore, a discussion is provided on the mechanism of flocculants’ interaction, the strategy of combining flocculants, and efficient selection methods of flocculants. Finally, coagulation/flocculation remaining challenges and technological improvements for the better development of highly efficient treatment methods were highlighted, focusing on the intricate composition of slurry and its treatment difficulties. Full article

The source region of the Yellow River Basin (SRYRB) is not only sensitive to climate change and the vulnerable region of the ecological environment but also the primary runoff generating region of the Yellow River Basin (YRB). Its changes of drought and wetness profoundly impact water resources security, food production and ecological environment in the middle and downward reaches of YRB. In the context of global warming, based on daily precipitation, maximum and minimum temperature of 12 national meteorological stations around and within SRYRB during 1960–2015, this study obtained standardized precipitation index (SPI) and reconnaissance drought index (RDI) on 1-, 3-, 6- and 12-month scales, and then compared the consistency of SPI and RDI in many aspects. Finally, the temporal and spatial variation characteristics of drought and wetness in the SRYRB during 1960–2015 were analyzed in this study. The results showed that SPI and RDI have high consistency on different time scales (correlation coefficient above 0.92). According to the average distribution and change trend of the RDI, SRYRB presented an overall wetness state on different time scales. We found an increasing trend in wetness since the early 1980s. In terms of wetness events of different magnitudes, the highest frequency for moderate and severe ones was in June (12.7%) and February (5.5%), respectively, and for extreme wetness events, both September and January had the highest frequency (1.8%). Among the four seasons, the change rate of RDI in spring was the largest with a value of 0.38 decade⁻¹, followed by winter (0.36 decade⁻¹) and autumn (0.2 decade⁻¹) and the smallest in summer (0.1 decade⁻¹). There was a greater consistency between RDI values of larger time scales such as annual and vegetation growing seasonal (VGS) scales in SRYRB. There was generally a growing trend in wetness in the VGS time scale. These findings presented in this study can provide data support for drought and wetness management in SRYRB. Full article

Globally, the use of untreated, often diluted, or partly treated wastewater in agriculture covers about 30 million ha, far exceeding the area under the planned use of well-treated (reclaimed) wastewater which has been estimated in this paper at around 1.0 million ha. This gap has likely increased over the last decade despite significant investments in treatment capacities, due to the even larger increases in population, water consumption, and wastewater generation. To minimize the human health risks from unsafe wastewater irrigation, the WHO’s related 2006 guidelines suggest a broader concept than the previous (1989) edition by emphasizing, especially for low-income countries, the importance of risk-reducing practices from ‘farm to fork’. This shift from relying on technical solutions to facilitating and monitoring human behaviour change is, however, challenging. Another challenge concerns local capacities for quantitative risk assessment and the determination of a risk reduction target. Being aware of these challenges, the WHO has invested in a sanitation safety planning manual which has helped to operationalize the rather academic 2006 guidelines, but without addressing key questions, e.g., on how to trigger, support, and sustain the expected behaviour change, as training alone is unlikely to increase the adoption of health-related practices. This review summarizes the perceived challenges and suggests several considerations for further editions or national adaptations of the WHO guidelines. Full article

Freshwater is a scarce resource that continues to be at high risk of pollution from anthropogenic activities, requiring remediation in such cases for its continuous use. The agricultural and mining industries extensively use water and nitrogen (N)-dependent products, mainly in fertilizers and explosives, respectively, with their excess accumulating in different water bodies. Although removal of NO₃ from water and soil through the application of chemical, physical, and biological methods has been studied globally, these methods seldom yield N₂ gas as a desired byproduct for nitrogen cycling. These methods predominantly cause secondary contamination with deposits of chemical waste such as slurry brine, nitrite (NO₂), ammonia (NH₃), and nitrous oxide (N₂O), which are also harmful and fastidious to remove. This review focuses on complete denitrification facilitated by bacteria as a remedial option aimed at producing nitrogen gas as a terminal byproduct. Synergistic interaction of different nitrogen metabolisms from different bacteria is highlighted, with detailed attention to the optimization of their enzymatic activities. A biotechnological approach to mitigating industrial NO₃ contamination using indigenous bacteria from wastewater is proposed, holding the prospect of optimizing to the point of complete denitrification. The approach was reviewed and found to be durable, sustainable, cost effective, and environmentally friendly, as opposed to current chemical and physical water remediation technologies. Full article

Heavy rainfall leads to severe flooding problems with catastrophic socio-economic impacts worldwide. Hydrologic forecasting models have been applied to provide alerts of extreme flood events and reduce damage, yet they are still subject to many uncertainties due to the complexity of hydrologic processes and errors in forecasted timing and intensity of the floods. This study demonstrates the efficacy of using eXtreme Gradient Boosting (XGBoost) as a state-of-the-art machine learning (ML) model to forecast gauge stage levels at a 5-min interval with various look-out time windows. A flood alert system (FAS) built upon the XGBoost models is evaluated by two historical flooding events for a flood-prone watershed in Houston, Texas. The predicted stage values from the FAS are compared with observed values with demonstrating good performance by statistical metrics (RMSE and KGE). This study further compares the performance from two scenarios with different input data settings of the FAS: (1) using the data from the gauges within the study area only and (2) including the data from additional gauges outside of the study area. The results suggest that models that use the gauge information within the study area only (Scenario 1) are sufficient and advantageous in terms of their accuracy in predicting the arrival times of the floods. One of the benefits of the FAS outlined in this study is that the XGBoost-based FAS can run in a continuous mode to automatically detect floods without requiring an external starting trigger to switch on as usually required by the conventional event-based FAS systems. This paper illustrates a data-driven FAS framework as a prototype that stakeholders can utilize solely based on their gauging information for local flood warning and mitigation practices. Full article

The increase in population growth and demand is rapidly depleting natural resources. Irrigation plays a vital role in the productivity and growth of agriculture, consuming no less than 75% of fresh water utilization globally. Irrigation, being the largest consumer of water across the globe, needs refinements in its process, and because it is implemented by individuals (farmers), the use of water for irrigation is not effective. To enhance irrigation management, farmers need to keep track of information such as soil type, climatic conditions, available water resources, soil pH, soil nutrients, and soil moisture to make decisions that resolve or prevent agricultural complexity. Irrigation, a data-driven technology, requires the integration of emerging technologies and modern methodologies to provide solutions to the complex problems faced by agriculture. The paper is an overview of IoT-enabled modern technologies through which irrigation management can be elevated. This paper presents the evolution of irrigation and IoT, factors to be considered for effective irrigation, the need for effective irrigation optimization, and how dynamic irrigation optimization would help reduce water use. The paper also discusses the different IoT architecture and deployment models, sensors, and controllers used in the agriculture field, available cloud platforms for IoT, prominent tools or software used for irrigation scheduling and water need prediction, and machine learning and neural network models for irrigation. Convergence of the tools, technologies and approaches helps in the development of better irrigation management applications. Access to real-time data, such as weather, plant and soil data, must be enhanced for the development of effective irrigation management applications. Full article

Population increase has placed ever-increasing demands on the available groundwater (GW) resources, particularly for intensive agricultural activities. In India, groundwater is the backbone of agriculture and drinking purposes. In the present study, an assessment of groundwater reserves was carried out in the Udaipur district, Aravalli range, India. It was observed that the principal aquifer for the availability of groundwater in the studied area is quartzite, phyllite, gneisses, schist, and dolomitic marble, which occur in unconfined to semi-confined zones. Furthermore, all primary chemical ingredients were found within the permissible limit, including granum. We also found that the average annual rainfall days in a year in the study area was 30 from 1957 to 2020, and it has been found that there are chances to receive surplus rainfall once in every five deficit rainfall years. Using integrated remote sensing, GIS, and a field-based spatial modeling approach, it was found that the dynamic GW reserves of the area are 637.42 mcm/annum, and the total groundwater draft is 639.67 mcm/annum. The deficit GW reserves are 2.25 mcm/annum from an average rainfall of 627 mm, hence the stage of groundwater development is 100.67% and categorized as over-exploited. However, as per the relationship between reserves and rainfall events, surplus reserves are available when rainfall exceeds 700 mm. We conclude that enough static GW reserves are available in the studied area to sustain the requirements of the drought period. For the long-term sustainability of groundwater use, controlling groundwater abstraction by optimizing its use, managing it properly through techniques such as sprinkler and drip irrigation, and achieving more crop-per-drop schemes, will go a long way to conserving this essential reserve, and create maximum groundwater recharge structures. Full article

Clean water is an indispensable essential resource on which humans and other living beings depend. Therefore, the establishment of a water quality prediction model to predict future water quality conditions has a significant social and economic value. In this study, a model based on an artificial neural network (ANN), discrete wavelet transform (DWT), and long short-term memory (LSTM) was constructed to predict the water quality of the Jinjiang River. Firstly, a multi-layer perceptron neural network was used to process the missing values based on the time series in the water quality dataset used in this research. Secondly, the Daubechies 5 (Db5) wavelet was used to divide the water quality data into low-frequency signals and high-frequency signals. Then, the signals were used as the input of LSTM, and LSTM was used for training, testing, and prediction. Finally, the prediction results were compared with the nonlinear auto regression (NAR) neural network model, the ANN-LSTM model, the ARIMA model, multi-layer perceptron neural networks, the LSTM model, and the CNN-LSTM model. The outcome indicated that the ANN-WT-LSTM model proposed in this study performed better than previous models in many evaluation indices. Therefore, the research methods of this study can provide technical support and practical reference for water quality monitoring and the management of the Jinjiang River and other basins. Full article

Bangladesh is in the floodplains of the Ganges, Brahmaputra, and Meghna River delta, crisscrossed by an intricate web of rivers. Although the country is highly prone to flooding, the use of state-of-the-art deep learning models in predicting river water levels to aid flood forecasting is underexplored. Deep learning and attention-based models have shown high potential for accurately forecasting floods over space and time. The present study aims to develop a long short-term memory (LSTM) network and its attention-based architectures to predict flood water levels in the rivers of Bangladesh. The models developed in this study incorporated gauge-based water level data over 7 days for flood prediction at Dhaka and Sylhet stations. This study developed five models: artificial neural network (ANN), LSTM, spatial attention LSTM (SALSTM), temporal attention LSTM (TALSTM), and spatiotemporal attention LSTM (STALSTM). The multiple imputation by chained equations (MICE) method was applied to address missing data in the time series analysis. The results showed that the use of both spatial and temporal attention together increases the predictive performance of the LSTM model, which outperforms other attention-based LSTM models. The STALSTM-based flood forecasting system, developed in this study, could inform flood management plans to accurately predict floods in Bangladesh and elsewhere. Full article

The Yangtze River has been the primary support of the resources and transportation of China. The Three Gorges Dam and Reservoir on the Yangtze River is one of the world’s largest dams. The influence caused by the dam and reservoir on the river system has been overwhelming and destructive. For better water resource use and flood-prevention planning, more understanding is needed regarding the dam’s impact on river discharge, regional precipitation, and frequency of extreme rainfall events. This study aims to analyze the changes in river discharge and regional precipitation records before and after the construction of the Three Gorges Dam. This research examines temporal correlations among these data by collecting daily dam injection and dam discharge records, the precipitation from ground stations, and river discharge. The time series are analyzed with the wavelet analysis. The precipitation datasets decrease in wavelet magnitude after 1998 when the dam was built in the wavelet analysis. The annual cycle, shown as a bright year line through the time range, still exists in the analysis result after 1998, but the magnitude of the annual cycle has reduced. The river discharge shows a decrease of wavelet magnitude at the three downstream locations. The possible explanation of this pattern could be the human-controlled dam discharge. The constant water level maintained in the reservoir by human control would slow down the flow speed and stabilize it. Full article

Water body feature extraction using a remote sensing technique represents an important tool in the investigation of water resources and hydrological drought assessment. Nuntasi-Tuzla Lake, a component of the Danube Delta Natural Reserve, is located on the Romanian Black Sea littoral. On account of an event in summer 2020, when the lake surface water decreased significantly, this study aims to identify the variation of the Nuntasi-Tuzla Lake surface water over a long-term period in correlation with human intervention and climate change. To this end, it provides an analysis in the period 1965–2021 via hydrological drought indices and data mining classification. The latter approach is based on several water indices derived from Landsat TM/ETM+/OLI and MODIS full-time series datasets: Normalized Difference Vegetation Index (NDVI), Normalized Difference Vegetation Index (NDVI), Modified NDWI (MNDWI), Weighted Normalized Difference Water Index (WNDWI), and Water Ratio Index (WRI). The experimental results indicate that the proposed classification methods can extract relevant features from waterbodies using remote sensing imagery with a high accuracy. Moreover, the study shows a similarity in the evolution of surface water cover identified with the data mining classification and the drought periods detected in the flow data series for the Nuntasi and Sacele Rivers that supply the Nuntasi-Tuzla Lake. Overall, the results of our investigation show that human intervention and hydrological drought had an extensive impact on the long-term changes in surface water of the Nuntasi-Tuzla Lake. Full article

Water distribution system monitoring is currently carried out using advanced real-time control technologies to achieve a higher operational efficiency. Data analysis techniques can be implemented for condition estimation, which are crucial tools for managing, developing, and operating water networks using the monitored flow rate and pressure data at some network pipes and nodes. This work proposes a state estimation methodology that enables one to infer the hydraulic state of the operating speed of pumping systems from these pressure and flow measurements. The presented approach suggests using graph convolutional neural network theory linked to hydraulic models for generating a digital twin of the water system. It is validated on two benchmark hydraulic networks: the Patios-Villa del Rosario, Colombia, and the C-Town networks. The results show that the proposed model effectively predicts the state estimation in the two hydraulic networks used. The results of the evaluation metrics indicate low values of mean squared error and mean absolute error and high values of the coefficient of determination, reflecting high predictive ability and that the prediction results adequately represent the real data. Full article

The prediction of monthly rainfall is greatly beneficial for water resources management and flood control projects. Machine learning (ML) techniques, as an increasingly popular approach, have been applied in diverse climatic regions, showing their respective superiority. On top of that, the ensemble learning model that synthesizes the advantages of different ML models deserves more attention. In this study, an ensemble learning model based on stacking approach was proposed. Four prevalent ML models, namely k-nearest neighbors (KNN), extreme gradient boosting (XGB), support vector regression (SVR), and artificial neural networks (ANN) are taken as base models. To combine the outputs from the base models, the weighting algorithm is used as second-layer learner to generate predictions. Large-scale climate indices, large-scale atmospheric variables, and local meteorological variables were used as predictors. R², RMSE and MAE, were used as evaluation metrics. The results show that the performance of base models varied among the nine stations in the Taihu Basin, while the stacking approach generally performed better than the four base models. The stacking model showed better performance in spring and winter than in summer and autumn. During wet months, the accuracy of model prediction varied more significantly. On the whole, based on performance evaluation measures, it is concluded that the proposed stacking ensemble multi-ML model can provide a flexible and reasonable prediction framework applicable to other regions. Full article

Since predicting rapidly fluctuating water levels is very important in water resource engineering, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) were used to evaluate water-level-prediction accuracy at Hangang Bridge Station in Han River, South Korea, where seasonal fluctuations were large and rapidly changing water levels were observed. The hydrological data input to each model were collected from the Water Resources Management Information System (WAMIS) at the Hangang Bridge Station, and the meteorological data were provided by the Seoul Observatory of the Meteorological Administration. For high-accuracy high-water-level prediction, the correlation between water level and collected hydrological and meteorological data was analyzed and input into the models to determine the priority of the data to be trained. Multivariate input data were created by combining daily flow rate (DFR), daily vapor pressure (DVP), daily dew-point temperature (DDPT), and 1-hour-max precipitation (1HP) data, which are highly correlated with the water level. It was possible to predict improved high water levels through the training of multivariate input data of LSTM and GRU. In the prediction of water-level data with rapid temporal fluctuations in the Hangang Bridge Station, the accuracy of GRU’s predicted water-level data was much better in most multivariate training than that of LSTM. When multivariate training data with a large correlation with the water level were used by the GRU, the prediction results with higher accuracy ($R^2=0.7480–0.8318$; $NSE=0.7524–0.7965$; $MRPE=0.0807–0.0895$) were obtained than those of water-level prediction results by univariate training. Full article

In this paper, the authors use remote-sensing images to monitor the water quality of reservoirs located in the semiarid region of Northeast Brazil. Sentinel-2 MSI TOA Level 1C reflectance images were used to remotely estimate the concentration of chlorophyll-a (chl-a), the main indicator of the trophic state of aquatic environments, in five reservoirs in the state of Ceará, Brazil. A three-spectral band retrieval model was calibrated using 171 water samples, collected from November 2015 through July 2018 in 5 reservoirs. For validation, 71 additional samples, collected from August 2018 through December 2019, were used to ensure a robust accuracy assessment. The TOA Level 1C products performed very well, achieving a relative RMSE of 28% and R² = 0.80. Data on wind direction and speed, solar radiation and reservoir volume were used to generate a conceptual model to analyze the behavior of chl-a in the surface waters of the Castanhão reservoir. During 2019, the reservoir water quality showed strong variation, with concentration fluctuating from 30 to 95 µg/L We showed that the end of the dry season is marked by strong eutrophic conditions corresponding to very low water inflows into the reservoir. During the rainy season there is a large decrease in the chl-a concentration following the increase of the lake water storage. During the following dry season, satellite data show a progressive improvement of the trophic state controlled by wind intensity that promotes a better mixing of the reservoir waters and inhibiting the development of most phytoplankton. Full article

Forecasting meteorological and hydrological drought using standardized metrics of rainfall and runoff (SPI/SRI) is critical for the long-term planning and management of water resources at the global and regional levels. In this study, various machine learning (ML) techniques including four methods (i.e., ANN, ANFIS, SVM, and DT) were utilized to construct hydrological drought forecasting models in the Wadi Ouahrane basin in the northern part of Algeria. The performance of ML models was assessed using evaluation criteria, including RMSE, MAE, NSE, and R². The results showed that all the ML models accurately predicted hydrological drought, while the SVM model outperformed the other ML models, with the average RMSE = 0.28, MAE = 0.19, NSE = 0.86, and R² = 0.90. The coefficient of determination of SVM was 0.95 for predicting SRI at the 12-months timescale; as the timescale moves from higher to lower (12 months to 3 months), R² starts decreasing. Full article

This study utilized MIKE 11 to quantify the spatio-temporal dynamics of water quality parameters (Biochemical Oxygen Demand (BOD₅), Dissolved Oxygen (DO) and temperature) in the Long Xuyen Quadrangle area of the Vietnamese Mekong Delta. Calibrated for the year of 2019 and validated for the year of 2020, the developed model showed a significant agreement between the observed and simulated values of water quality parameters. Locations near to cage culture areas exhibited higher BOD₅ values than sites close to pond/lagoon culture areas due to the effects of numerous point sources of pollution, including upstream wastewater and out-fluxes from residential and tourism activities in the surrounding areas, all of which had a direct impact on the quality of the surface water used for aquaculture. Moreover, as aquacultural effluents have intensified and dispersed over time, water quality in the surrounding water bodies has degraded. The findings suggest that the effective planning, assessment and management of rapidly expanding aquaculture sites should be improved, including more rigorous water quality monitoring, to ensure the long-term sustainable expansion and development of the aquacultural sector in the Long Xuyen Quadrangle in particular, and the Vietnamese Mekong Delta as a whole. Full article

Under a warming climate, permafrost degradation has resulted in profound hydrogeological consequences. Here, we mainly review 240 recent relevant papers. Permafrost degradation has boosted groundwater storage and discharge to surface runoffs through improving hydraulic connectivity and reactivation of groundwater flow systems, resulting in reduced summer peaks, delayed autumn flow peaks, flattened annual hydrographs, and deepening and elongating flow paths. As a result of permafrost degradation, lowlands underlain by more continuous, colder, and thicker permafrost are getting wetter and uplands and mountain slopes, drier. However, additional contribution of melting ground ice to groundwater and stream-flows seems limited in most permafrost basins. As a result of permafrost degradation, the permafrost table and supra-permafrost water table are lowering; subaerial supra-permafrost taliks are forming; taliks are connecting and expanding; thermokarst activities are intensifying. These processes may profoundly impact on ecosystem structures and functions, terrestrial processes, surface and subsurface coupled flow systems, engineered infrastructures, and socioeconomic development. During the last 20 years, substantial and rapid progress has been made in many aspects in cryo-hydrogeology. However, these studies are still inadequate in desired spatiotemporal resolutions, multi-source data assimilation and integration, as well as cryo-hydrogeological modeling, particularly over rugged terrains in ice-rich, warm (>−1 °C) permafrost zones. Future research should be prioritized to the following aspects. First, we should better understand the concordant changes in processes, mechanisms, and trends for terrestrial processes, hydrometeorology, geocryology, hydrogeology, and ecohydrology in warm and thin permafrost regions. Second, we should aim towards revealing the physical and chemical mechanisms for the coupled processes of heat transfer and moisture migration in the vadose zone and expanding supra-permafrost taliks, towards the coupling of the hydrothermal dynamics of supra-, intra- and sub-permafrost waters, as well as that of water-resource changes and of hydrochemical and biogeochemical mechanisms for the coupled movements of solutes and pollutants in surface and subsurface waters as induced by warming and thawing permafrost. Third, we urgently need to establish and improve coupled predictive distributed cryo-hydrogeology models with optimized parameterization. In addition, we should also emphasize automatically, intelligently, and systematically monitoring, predicting, evaluating, and adapting to hydrogeological impacts from degrading permafrost at desired spatiotemporal scales. Systematic, in-depth, and predictive studies on and abilities for the hydrogeological impacts from degrading permafrost can greatly advance geocryology, cryo-hydrogeology, and cryo-ecohydrology and help better manage water, ecosystems, and land resources in permafrost regions in an adaptive and sustainable manner. Full article

Online monitoring of wastewater quality parameters is vital for an efficient and stable operation of wastewater treatment plants (WWTP). Several WWTPs rely on daily/weekly analysis of water samples rather than online automated wet-analyzers due to their high capital and maintenance costs. Soft-sensors are emerging as a viable alternative for real-time monitoring of parameters that either lack a reliable measuring principle or are measured using expensive online sensors. This paper presents the development, implementation, and validation of a hybrid soft sensor used to estimate Total Phosphorus (TP) and Chemical Oxygen Demand (COD) in the influent and effluent streams of a full-scale WWTP. A systematic method for cleaning and processing sensor data, identifying statistically significant correlations, and developing a mathematical model, is discussed. A non-intrusive Industrial Internet of Things (IIoT) infrastructure for soft-sensor deployment and a web-based GUI for data visualization are also presented in this work. The values of TP and COD estimated by the soft sensor are validated by comparing the estimated values to the daily average of their corresponding lab measurements. The data validation results demonstrate the potential of soft sensors in providing real-time values of essential wastewater quality parameters with an acceptable degree of accuracy. Full article

One of the most serious effects of micropollutants in the environment is biological magnification, which causes adverse effects on humans and the ecosystem. Among all of the micro-pollutants, antibiotics are commonly present in the aquatic environment due to their wide use in treating or preventing various diseases and infections for humans, plants, and animals. Therefore, an aluminum-based electrocoagulation unit has been used in this study to remove cephalexin antibiotics, as a model of the antibiotics, from water. Computational and statistical models were used to optimize the effects of key parameters on the electrochemical removal of cephalexin, including the initial cephalexin concentration (15–55 mg/L), initial pH (3–11), electrolysis time (20–40 min), and electrode type (insulated and non-insulated). The response surface methodology-central composite design (RSM-CCD) was used to investigate the dependency of the studied variables, while the artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) methods were applied for predicting the experimental training data. The results showed that the best experimental and predicted removals of cephalexin (CEX) were 88.21% and 93.87%, respectively, which were obtained at a pH of 6.14 and electrolysis time of 34.26 min. The results also showed that the ANFIS model predicts and interprets the experimental results better than the ANN and RSM-CCD models. Sensitivity analysis using the Garson method showed the comparative significance of the variables as follows: pH (30%) > electrode type (27%) > initial CEX concentration (24%) > electrolysis time (19%). Full article