GIS, Applied Computing and Data Science for Water Management

Water is an essential resource for food, agriculture, health and industry. It is currently facing challenges posed by demographic, economic and climate change. Meanwhile, advances in artificial intelligence and machine learning (AI-ML) offer an opportunity to process large volumes of data to understand complex water-related phenomena better. This study aims to analyse the intersection of Water and AI-ML research, identifying trends shaping current research and giving insights about the future. It uses bibliometric analysis to examine Scopus data, with an incremental, heuristic approach. By the end, the analysis, based on Scival, is also crosschecked with Web of Science (WOS) data. The findings show a great dynamism in this field, with a focus on engineering approaches like “Remote Sensing,” “Optical Engineering,” and “Photogrammetry.“ Research topics emphasise detecting, measuring, modelling, and predicting hydrological, geological, and climatic phenomena. There is also a growing cross-disciplinary emphasis on energy, thermodynamics, materials, and chemistry. On the other hand, AI-ML techniques, such as “Artificial Neural Networks”, “Random Forest” and “Long Short-Term Memory”, are increasingly used. It also seems that the trend is towards studying parameters related to “Water Quality”, “Ground Water” and “Water Levels”. This particularly benefit the fields of “Agriculture” and “Water Resources Management”. At the level of international collaboration, an accentuated concentration is noted with a small number of prolific countries (China, USA, India). However, industrial collaboration remains relatively weak, presenting both opportunities and challenges. Finally, this research seems to be taking a direction that is still in its infancy, due to its precocity. Nevertheless, it presents considerable potential for development, particularly in terms of international and industrial collaboration. As a perspective, the expert information comparison would certainly be beneficial to enrich this bibliometric analysis and improve the robustness of the conclusions.

Water scarcity has become a major global concern due to climate change, excessive use and pollution. Establishing and developing strategies and approaches to manage available water resources is challenging under the current natural and anthropogenic pressures. The present study analyzes the current research trend on Water Resource Management (WRM) by conducting a bibliometric analysis using Vosviewer software (version 1.6.20). The study also analyzes the research categories based on the 17 Sustainable Development Goals (17SDGs) and the Australian and New Zealand Standard Research Classification (ANZSRC). Based on the two classifications, the sustainable and effective management of water resources at the scientific level requires the integration of interdisciplinary research projects, while at the societal, economic, and strategic levels, the 17 SDGs must all be taken into account when establishing WRM projects. The results of the bibliometric analysis show that the current focus is on climate variability and its impact on food security. China is found to be the hotspot country with the highest number of publications, followed by the United States, while a lack of publications on WRM was found in developing countries that reported suffering from water scarcity and climate impacts. These findings are crucial for future research on WRM as they provide the basic knowledge about research trends in this research field.

The infiltration of saltwater into groundwater sources along coastal areas can cause a substantial rise in salinity, impacting the main water supply in these areas. The purpose of this paper is to deliver a comprehensive examination of contemporary research patterns in groundwater intrusion. The study concentrates on the period spanning 2000–2022, and it involved analyzing 1908 papers from the Scopus database utilizing the ‘bibliometrix’ package in the R programming language. The study's findings, which were visualized using ‘biblioshiny’ and ‘VOSviewer’, demonstrate that research on marine intrusion is on the rise. Interdisciplinary teams of researchers from various countries are working together to attain integrated outcomes. As evidenced by the investigation, the utilization of spatial data science and remote sensing has experienced a significant surge in this field. This paper aims to provide valuable insights to inspire researchers by presenting the current state of research on this topic, including popular research methods, the involvement of authors, and directions for future research.

In the face of a global food crisis and climate change, ensuring access to water resources becomes a critical concern for human activities. The Maghreb region, including Morocco, Tunisia and Algeria, is particularly exposed to ecological vulnerabilities. The environmental degradation in this region has already led to adverse effects on the well-being of populations and hindered economic development. While demographic projections provide some clarity, the uncertainties surrounding climate change projections persist due to inadequate climatological data, both in terms of quantity and quality. Nonetheless, numerous climate projections for Southern Europe indicate a worrisome trend of increasing temperatures and decreasing precipitation. The Maghreb countries, due to their geographical proximity, are expected to face significant repercussions. This challenge is further compounded by the presence of the hyper-arid Sahara, which exacerbates the impact of climate change. Consequently, the Maghreb states recognize the imminent climate evolution as a major concern. This study aims to present an overview of the current climate evolution projections in the Maghreb region and explore their potential consequences on water resources. It encompasses an analysis of the various aspects of climate change, while emphasizing the necessity of implementing adaptation strategies to mitigate the adverse impacts on water resources.

Morocco has been experiencing droughts in the last three decades. Furthermore, drought frequency and severity are expected to increase due to climate change. So, a performant drought monitoring is needed to contribute to the adaptation of more efficient measures to mitigate the opposite impacts. The monitoring of the drought is generally presented by the use of drought indices, which are based on different climatic and hydrological variables. In this study, the monthly. Standardized Precipitation Evapotranspiration Index (SPEI) data for the whole of Morocco is calculated Using ERA5 Reanalysis data relies on air temperature and precipitation. The SPEI is estimated by the time scale of 6 months depending on accumulated water balance for the six previous months. This work has two main objectives; firstly, an evaluation of ERA5 Reanalysis, to choose it as an alternative data of the ground observations using statistical metrics. Secondly, this work assesses the spatial and temporal features of drought obtained from the monthly SPEI. The results show that the drought irregularly appears in Morocco and that it is possible to distinguish drought years clearly using the SPEI. In addition, the Moroccan climate experienced a significant drying tendency with increasing spatial extent, concurrently drought events have also increased in terms of frequency, duration and intensity across Morocco examined by the comparison of the two 22-year periods 1979–2000 and 2001–2022.

Water resource management in arid regions requires the provision of decision support tools that consider the impact of climate change as a structural reality. In the Laâyoune region, located in the south of Morocco, the Foum El Oued aquifer serves as a significant fresh water reservoir in a coastal area and plays a vital role in supplying water to the city of Laâyoune and neighboring municipalities. This study focuses on understanding and preserving this essential water resource, which is extensively utilized for drinking water supply, agriculture, and industrial purposes. However, due to the combination of reduced natural replenishment from the infiltration of Oued floods and increased pumping activities, groundwater has been overexploited, leading to the degradation of water quality and a considerable decline in the piezometric level. Consequently, an imbalance has emerged at the natural saltwater interface, resulting in seawater intrusion into the freshwater to compensate for the created depression. To address this issue, the objective of this work is to develop a finite difference hydrodynamic and seawater model that considers the effects of future climate change on the Foum El Oued aquifer, based on available hydrogeological data. The simulation results reveal that by 2050, under the projected conditions, the interface toe would have advanced by a distance of 6.5 km. At this time, the concentration of 10 g/l will reach a distance of 6.2 km, and the highest concentration (35 g/l) will extend to 5.8 km. This GW model serves as a crucial decision support system for water resource management, particularly for the population of Laâyoune and the irrigation of the Foum El Oued agriculture area. By implementing effective management strategies, the coastal area can be protected from contamination, ensuring its sustainable use and preventing abandonment due to increasing salinity levels in irrigation and pumping wells.

The study area covers the Ghis-Nekkor plain on the Mediterranean coast located in the north of Morocco. This groundwater aquifer is a typical example of a coastal aquifer whose water resources are exposed to severe overexploitation combined with increasingly low water supplies. The Ghis-Nekkor aquifer is an area highly vulnerable to seawater intrusion (SWI), firstly, because of less natural recharge, mean sea level rise due to climate change combined to groundwater overexploitation. The Regional Climate Models (RCMs) indicate a decrease in precipitation (18%) and an increase of average temperature (0.5 °C) in the Ghis-Nekkor area by 2050 under the RCP4.5 scenarios. These changes would have a direct impact on groundwater recharge of the aquifer. The results of the predicted groundwater recharge show a reduction of the mean annual recharge of 14% for (2021–2050) following the RCP4.5 scenario. Moreover, predicted values of future groundwater recharge under the RCP8.5 scenario would decrease more and would reach 30% less for the period (2055–2084). In view of the limited fresh water resources and degradation of water quality by sea water intrusion, effective management of ground water resources in this aquifer is necessary and can be made by developing a groundwater flow model taking into account seawater intrusion. Indeed, the outputs of RCMs for precipitation and SLR were used to assess the impact of pumping and climate change on the Ghis-Nekkor aquifer under the RCP4.5 and RCP 8.5 scenarios (2020–2040). The results show that the N-W sector of the coastal area would be more vulnerable to SWI. By 2040, the length of inland encroachment would reach 1 km, with a significant salinity (25 g/l) and a significant drop in hydraulic head (−15 m) following the RCP4.5 scenario. The extreme case of groundwater recharge and SLR under the RCP8.5 scenario will cause more severe impacts. By 2040, the length of inland encroachment would be around 1.23 km in the N-W part, at a distance of 0.55 km from the nearest ONEE well field. The salinity would reach 33 g/l and the SWI volume would increase by 48% (1.78Mm³/year) compared to the results under the RCP4.5 scenario.

The hydrodynamic modeling of the Berrechid aquifer using the MODFLOW code enables the understanding of the aquifer's hydrodynamic functioning, including the estimation of lateral exchanges between the aquifer and the Settat plateau, Oued Mellah, and the Chaouia coastal aquifer. Calibration of the mathematical model under steady-state conditions using piezometric state at 1980 enhances the spatial distribution of hydraulic conductivities across the entire domain and enables an assessment of the aquifer resevoir under steady-state conditions. While calibration of the model under transient conditions refines the spatial distribution of the aquifer's storage coefficient. Results from this simulation indicate a water deficit, with an average drawdown of 2 m per year. Recent droughts in the area have significantly impacted water supplies for both the population and agriculture, underscoring the need for a tool to manage water withdrawal and intervention directly at user levels to protect groundwater against overexploitation. A management groundwater withdrawal tool has been developed for the Berrechid aquifer, using a Decision Support System (DSS) based on coupling ArcGIS to MODFLOW to calculate drawdown caused by groundwater withdrawals at specific areas.

The present research is focused on the evaluation of springs water suitability for human consumption based on water quality parameters. Because of the rising level of human activity, pollutants, especially trace elements, are entering the aquatic system, posing harm to humans. The objectives of this study is: (i) to analyse the water quality variables, (ii) to compare their impact on water quality status of natural springs, and (iii) to display the Water Quality Index (WQI) results using Geographical Information System (GIS). The concentrations of water variables for investigated springs were analyzed adopting the Rodier standard method in the field using Multiparameter and in lab using a visible spectrophotometer and ICP-MS (ICPE-9000).The measured physico-chemical parameters were analyzed using a principal component analysis (PCA). A total of 24 water samples were taken from 12 springs to evaluate their suitability for human consumption. From the analysis of principal components (PCA), 73.87%. The variation was explained by the first three main factors. The variables pH, TDS, HCO₃⁻, Na⁺, Ca²⁺, Mg²⁺ and Zn showed a strong correlation with F1. Following this, NO₃⁻, Pb, Mn and Cu showed a strong correlation with F2, while SO₄⁻, CO, B, Ni and Cr showed a notable correlation with F3. The water quality index (WQI) was ranged from 49.66 to 95.10, averaging 76.52. About 17% of water samples were classified as excellent quality (WQI < 50), while the remaining 83% fell under the classification of good quality (50 < WQI < 100). This suggests that all the natural spring waters examined are suitable for human consumption.

In regions facing the dynamic challenges of environmental change, the sustainable development of water management strategies is paramount. In the Moroccan landscape, where the increase in water demand, driven by population growth and intensified by the adverse effects of climate change accentuating the siltation of reservoirs, the importance of dams in the management of water resources requires a thorough understanding of spatiotemporal siltation models. This research work presents an in-depth investigation of siltation phenomena within Moroccan dams, over a long period. Using an integrative methodology, the research combines century-old bathymetric data with Geographic Information System (GIS) technologies. The resulting interactive maps make it possible to identify regions most sensitive to dam siltation and provide a complete overview of temporal changes. The analysis highlights the omnipresence of siltation in all Moroccan watersheds. The Moulouya basin is distinguished by its unique pedological characteristics and its arid climate, exacerbated by intense rainfall and deforestation. The results provide valuable information for decision-makers and water resource managers, offering essential information for strategic planning and the implementation of targeted measures to mitigate the impact of siltation.

Precipitation forecasts for the future are crucial for the efficient management of water resources. These forecasts are often made using global circulation models (GCMs). Therefore, this paper examined the impact of climate change on precipitation for Damaturu, Yobe State, Nigeria between 2050 and 2080 using GCM variables. To achieve this, an artificial neural network (ANN) was utilized to downscale observed precipitation data using the BNU-ESM GCMs under the emission scenario RCP 4.5. The mutual information (MI) technique was used to rank various climate predictors based on their influence on precipitation. In order to downscale the precipitation data, five distinct predictor combinations were used to create the ANN models. Next, the Root Mean Square Error (RMSE) and Determination Coefficient (DC) performance metrics were used to identify the best downscaling model. It was discovered that M1, which combined the top 8 ranked predictors, performed the best throughout both the projection and downscaling phases. The final M1 results indicated that a decrease in precipitation will likely be experienced in the Damaturu region within the given period. In the months with the highest amounts of precipitation, the decrease will be more pronounced with the greatest amount of up to 20% occurring during the wettest month of August, near the end of the twenty-first century.

Communities and industries rely heavily on accurate precipitation forecasts, which are essential for planning and decision-making across various sectors. Conventional methodologies for predicting weather entail a comprehensive understanding of physical phenomena, historical climate patterns, and the application of statistical models. Nevertheless, the intricate and nonlinear rainfall nature poses significant challenges to achieving precise predictions. In recent years, Machine Learning (ML) techniques have appeared as advantageous methods for enhancing the accuracy of rainfall forecasts. This article offers an extensive and comparative examination of classic techniques and evolved ML models relevant to precipitation estimation. By identifying the strengths and limitations of each approach, the study sheds light on the progress made in rainfall prediction using these innovative techniques. In addition, the study emphasizes the importance of pre-processing in improving predictive capabilities, exploring careful steps such as data cleaning, handling missing values, and scaling. Leveraging a comprehensive dataset collected from the Ziz Basin region, incorporating historical weather data spanning numerous climatic variables (precipitation, humidity, wind, temperature, and evaporation), our objective is to conduct a rigorous comparative analysis to assess the effectiveness of various ML models in enhancing rainfall estimation accuracy within this specific geographic area.

Surface water resources are subject to climate change, particularly in arid zones such as Morocco's central plateau, and to the massive demand placed on water by human activities, which calls for equitable management of water potential, In this sense, hydraulic engineering is a solution for better storage and management of surface water, as well as for mitigating and adapting to climate variability. This is the aim of the Ain Kwaachia dam on the Ykem river in the northwestern part of the central plateau of Morocco. While the use of remote sensing technology, based on the acquisition of satellite images, is a kind of machine learning to quantify spatio-temporal variations in water potential, so the processing and the analysis of these image data, based on a GIS geographic information system, and this, from the Land Use index for land cover, with an unsupervised classification from 2008, the year of commissioning of the dam subject of this research, and a supervised classification around the year 2021. The results obtained show that the variations affecting the study area have been noticeable in recent years, from 9.78 km² for 2016, to 4.23 km² for 2021, as a result of the repercussions of climate change, with falling rainfall on the one hand, and in the other hand rising temperatures.

The issue of water management is at the heart of debates in many international forums. To meet the growing demand for water due to the current global crisis, it is essential to focus more on water management techniques applied in different applications. Taking into account population density, it becomes imperative to implement intelligent water management mechanisms for efficient distribution, preservation of water quality, and its use for various purposes. Our work addresses several key areas required for efficient water management, including wastewater recycling, water distribution, rainwater harvesting and irrigation, using artificial intelligence (AI) models. The data required for these applications is unique and varies according to context, so it is crucial to use a versatile model or algorithm capable of providing solutions for all these cases. AI, deep learning and Internet of Things techniques can facilitate the design of an intelligent water management system for the sustainable use of natural resources. Our work explores different approaches to water management using AI, DL and IoT, drawing on case studies and statistical analysis to develop a successful water management system.