Introduction

In the last decades, many models that use AI techniques, including knowledge-based systems, neural networks, evolutionary systems, fuzzy logic, genetic algorithms, adaptive agents, and expert systems, were created and described in the water engineering literature. Effective water use for a local community, country, or river basin depends on managing both the supply and demand for water using intelligent techniques. Smart water (SW) has embraced AI, water knowledge (WK), and a wide variety of search techniques. Intelligent water, in this context, is a subset both of WK and AI. Smart water (SW) technologies and software for operational monitoring of critical water crisis and problems is a must. The issue is to transform into a more rational and effective one while integrating operational and smart water monitoring, thereby providing objective, accurate, and sufficiently comprehensive data to serve as a basis for reliable evaluations, projections, and forecasts. The advantages that are expected from applying a smart water approach to the water industry might be realized. The specific objectives of this paper are to shed light on applied intelligence and how to be employed in all topics of water-related SDGs, to show the reasons for applied intelligence techniques’ success when optimization models fail, to suggest using these techniques in situations where optimal or exact results are either too expensive or not possible.

The study aims to explore how artificial intelligence (AI) could enhance the wise use of freshwater in all development actions related to global goals, The focus would be on conceptual work. As water resources are the core component in everyday life in any community, the broad scope is interdisciplinary and includes all global goals.

The research questions are as follows:

  1. 1.

    How the intelligent water applications could be implemented, and what are its components?

  2. 2.

    What are the features of intelligent water systems (IWSs), their contributions, and future opportunities that could be provided by intelligent water hackathons in the Arabsphere?

Literature review

Coronaviruses (CoV) pandemic

The coronavirus pandemic has triggered a crisis in food, health, and water security and severely impacted the Water-Climate-Food Nexus across the Arab Societies. In the Covid-19 era, many different approaches and attempts are being made to understand how the pandemic progresses. Many researchers have addressed the COVID-19 epidemic and its related challenges that occur in various application domains. Due to economic contraction, air and water quality were improved across the globe (Saadat et al. 2020). Others have addressed the COV pandemic from an environmental perspective. During the COVID-19 pandemic, the future control and forecasting of air pollutants in megacities are displayed in; China (Yuan et al. 2021), Korea (Ju et al. 2021), Spain (Martorell-Marugán et al. 2021), and California, USA (Liu et al. 2021). According to the Food and Agriculture Organization (FAO) (FAO 2020), sanitation, hygiene, and food safety practices may intensify and threaten the food supply. Alternatively, the COV pandemic may urge food production (Rowan and Galanakis 2020).

Forecasting models for the COV pandemic were used to make reasonable control measures. The CoV pandemic outbreak in Italy, China, and France was reported (Fanelli and Piazza 2020). Forecasting of the COV pandemic spread in Russia, India, USA, Peru, and Brazil was modeled (Hazarika and Gupta 2020). Based on time series, the death rate of the COV pandemic was modeled (Maleki et al. 2020). Machine Learning (ML) as a significant method for forecasting the CoV epidemic was reviewed (Lalmuanawma et al. 2020). Intelligent computing systems include both deep learning (DL) and machine learning (ML) techniques. These advanced computing techniques were applied in the forecasting of COVID-19. ML techniques include [Random Forest algorithm (RF), Support Vector Machine (SVM), XGBoost machine, K-means, neural network, logistic regression, Multi-Layered Perception (MLP), Adaptive Network-based Fuzzy Inference System (ANFIS)]. DL techniques include [Convolutional Neural Network (CNN), Tailored CNN Models, Deep CNN (DCNN), Improved Inception Recurrent Residual Neural Network (IRRCNN), Modified CNN, Generative Adversarial Networks (GAN), 3D DCNN, Residual Neural network, and Autoencoder]. The advanced intelligent computing methods for prognosis were reviewed (Swapnarekha et al. 2020). Forecasting of the COVID-19 outbreak in Canada using AI and Deep Learning was developed (Chimmula and Zhang 2020). The Self-organizing maps (SOM) applied to cluster classify the spatial spread of the coronavirus pandemic (Melin et al. 2020). Genetic programming (GP) [Genetic Evolutionary Programming (GEP)] was applied to assess the confirmed cases and death cases of the coronavirus pandemic in India (Salgotra et al. 2020).

Water stress (WS) indicator

The water stress indicator was displayed by FAO. In the context of human efforts to combat the world’s freshwater crisis, the United Nations (UN) addresses this core challenge to facilitate satisfying global goals and needs. Goal 6 of the global goals is to sustain water for all humans. The target 6.4 of Goal 6 is to reduce water scarcity by increasing water-use efficiency. The indicator “6.4.2” assesses the level of water stress. This indicator shows the degree to which WRs are exploited to meet a country’s water demand. It measures a country’s pressure on its water resources and therefore the challenge on the sustainability of its water use. It tracks progress regarding “withdrawals and supply of water resources to mitigate water scarcity”.

Methods

Arabsphere

The Arabsphere consists of twenty-two countries. In Arabsphere, sustainable development is particularly related to Water-Food-Climate Nexus. Water and food are exposed to high vulnerability and external shocks which causes significant challenges to achieving SDGs. Climate change happens in different ways, in particular, gradual changes in precipitation and/or temperature patterns, and increased both variability and frequency of extreme events. Global warming is the fundamental aspect of climate change. Climate change could be detected by studying patterns of climate variability and means. Climate change could affect all dimensions of the water security of vulnerable groups and different elements of food systems. Unconventional water is a strategic option to face water challenges. The promising unconventional waters for the Arab water future are desalination, agricultural drainage water reuse, treated greywater, treated wastewater, brackish groundwater use, and water, rain, dew, and fog harvesting.

Water stress (WS)

FAO is the data provider of the SDG6 indicator metadata, through AQUASTAT. Total renewable freshwater resources (TRWR), Environmental flow requirements (EFR), and Total freshwater withdrawal (TFWW) were defined by FAO. The definition implies all economic activities need water resources or water flow requirements to maintain environmental and ecosystem health. By defining TFWW, TRWR, and EFR, the “water stress” indicator could be straightforwardly computed using the Eq. (1):

$${{{\mathrm{Water}}{\mathrm{stress}}}}\,\left( \% \right) = \frac{{{{{\mathrm{Total}}\,{\mathrm{freshwater}}\,{\mathrm{withdrawn }}}}\,\left( {{{{\mathrm{TFWW}}}}} \right)}}{{{{{\mathrm{Total}}\,{\mathrm{renewable}}\,{\mathrm{water}}\,{\mathrm{resources }}}}\,\left( {{{{\mathrm{TRWR}}}}} \right) - {{{\mathrm{Environmental}}\,{\mathrm{flow}}\,{\mathrm{requirements}}}}\,\left( {{{{\mathrm{EFR}}}}} \right)}}$$
$${{{\mathrm{Water}}\,{\mathrm{stress}}}}\,\left( \% \right) = TFWW/\left( {TRWR - EFR} \right) \times 100$$
(1)

TFWW, TRWR, and EFR are expressed in 109 m3/year (km3/year).

Water stress indicators and data were issued by (FAO and UN Water 2021), for the Year 2020. Data for the Arab water were defined by the score (0–100), [Units = %].

Classes of water stress were displayed in Table 1 to elaborate the data. Water stress indicators in the Arabsphere are provided in Table 2. The last column was added to elaborate the class of water stress according to Table 1. Water stress indicators in the main regions and the world were displayed in Table 3 to elaborate on the severity of water stress in the Arabsphere, compared with the main regions and the world.

Table 1 Classes of water stress.
Full size table
Table 2 Water stress indicators in the Arabsphere.
Full size table
Table 3 Water stress indicators in the main regions and world.
Full size table

The thresholds of 25%, 50%, and 75% were identified to classify the limits for water stress. Classes of water stress were identified as follows: no stress <25%, low 25–50%, medium 50–75%, high 75–100%, and critical >100%.

Data validation was done according to the FAO (AQUASTAT) rules. The validation tools included cross-variable comparison, time-series coherency, and metadata verification. The last step is a statistical working system, with many validation rules.Missing values could be treated and imputed by linear imputation, carry forward, and vertical imputation. Data could be interpolated to continue the time series. After revision and validation, the data quality should be ensured by FAO. The quality management, quality assessments, quality assurance, and compliance monitoring of the statistical processes were the responsibility of FAO.

Smart water systems (SWSs)

Various types and sources of data are needed to conduct SWS. Some of these can be summarized as follows:

  • Meteorological data. These data are needed to define the climate of the region, and they are used to analyze the water availability for both planning and operational water supply management. Examples of meteorological data are precipitation, evaporation, temperature, wind direction, and velocity.

  • Hydrologic data. Hydrologic data consists of in situ precipitation gauge data, stream gauge readings, discharge measurements, and reservoir elevations. Water quality measurements and evaporation data are needed to establish the water balance. An adequate hydrologic network is required to manage water resources.

  • Remotely sensed data. The satellite used to derive large volumes of meteorological and hydrological products is advancing at a very high rate. Satellites can now provide estimates of precipitation rates, vegetation, evapotranspiration, soil moisture, and flood inundation coverage.

Integrative smart water knowledge system

The knowledge system that will serve SWS will have to take advantage of the existing data, information, and science on all critical water industry assets. The main features of the Smart Water System are depicted in Fig. 1. Identification, integration, behavior, characterization, and performance systems of the Smart Water System Components that maintain complex, dynamic, and non-stationary interactions were displayed. Integrating knowledge systems is envisioned to serve as the cement for new and objective data. Information could be retrieved from relevant components throughout the critical location of the water system, and with a fine spatial distribution. Such knowledge systems would acquire and provide, on-demand, real-time data to administrators, engineers, researchers, operators, enforcement officials, and the public.

Fig. 1: Smart water system components.
figure 1

The diagram shows the main components of the smart water system; the colors stand for the main components (yellow color = water knowledge system components including software and hardware components, blue color = modern mobile service and application components, and pistachio color = application layer components).

Full size image

Integrative knowledge systems would help provide online access to data. The integration and synchronization of data, graphical interfaces, and application software could facilitate the analysis, design, and interpretation of the SWS. Most importantly, an integrative knowledge system would further be integrated with a heuristic knowledge base and possess a certain level of intelligence. Then, data streaming from many nodes of a large network could be processed, and operators could be alerted if incidents or anomalies requiring human intervention are diagnosed. Otherwise, it is not realistic to expect even well-trained human operators to successfully recognize all critical incidents and events promptly.

Knowledge acquisition and interpretation

Knowledge integration (fusion) in water monitoring is critical for the reliable interpretation of data and information. Knowledge integration is closely dependent on how data is transformed into knowledge. The general platform for smarter water applications is illustrated in Fig. 2.

Fig. 2: The general platform for smarter water applications.
figure 2

The diagram shows the two main phases of the smarter water applications; the colors stand for the two phases (yellow = Nowcasting (Sensors) phase, and orange = Forecasting (Modeling) phase). The nowcasting (Sensors) phase has three main components (yellow color = space component, orange color = time component, and pistachio color = frequency component). The forecasting (Modeling) phase has three main scales (yellow color = local scale, pistachio color = regional scale, and green color = globals cale).

Full size image

Smart water system identification process

Strategies, methods, and tools that may enable reliable observations, experimental measurements, conceptualization, and characterizations of climate, environment, and behavior of complex water systems should be carefully investigated. The complexity of measuring, processing, and integrating data coming from such a spectrum of space, time, and frequency modality characteristics is a challenge that has yet to be fully recognized and appreciated in water knowledge.

Before various data sets from anywhere within the data space may be processed, structured, archived, correlated, displayed, and interpreted, they should be accurately synchronized concerning time and space, and their variability and confidence intervals must be established.

Intelligent water hackathons

Smart water hackathon could be supported by multidisciplinary teams involving many academic disciplines, scientific disciplines, humanities, and social sciences. Community engagement including experts, specialists, generalists, and citizens could be involved. Hackathon is a powerful process to connect government agencies, academia, industry, and representatives for rural, urban, luxurious, and marginalized areas, and other water stakeholders’ communities. Participants include experts “water professionals, practitioners, scholars, engineers, designers, programmers, administrators, public health specialists, and environmentalists, …”, and non-experts, “consumers, users, …”. Based on collaboration and community engagement, and through scheduled sessions, hackathons could facilitate community engagement, and balanced team building.

Results

Significant applied intelligence techniques for smart water system

Applied intelligence methodologies aim to achieve robustness, tractability, and low solution cost, although partial truth, uncertainty, and imprecision could be generated. The focus was to highlight the significant soft computing methodologies to solve real water problems. Examples of applied intelligence methodologies are Neural Networks, Evolutionary Computing, Fuzzy Logic, and Rough Sets. Examples of significant applied intelligence techniques for SWSs are shown in Table 4.

Table 4 Significant applied intelligence techniques for smart water systems.
Full size table

Successful implementation of smart water system

Implementing SWS involves linking various techniques, models, procedures, and data that could be easily learned and applied to existing water management programs. Success occurs when costs and efforts are expended to establish a modernized water management program that brings positive economic, health, social, and environmental returns.

The success of SWS could be assessed by the subsequent questions: Are water stakeholders involved to ensure fair and equitable allocation of water among users and to protect the environment? Are the data readily accessible? How are water-use planning and allocation carried out? Is the current data network sufficient to accurately depict the water balance and water quality for the river basin and country? Is the present hydrologic prediction capability adequate to meet the needs of the various water users? The main water users are agriculture (irrigation), drinking and municipal water supply, industry, hydropower, and river transport. The water users could be interested in specific water quality, pollution mitigation, or flood response. How are decisions arrived at to optimize water resources and/or flood control? How conflict among water users is resolved at the local, national, regional (Arab), and international levels? Can users point to improvements in actions and behavior from implementing an intelligent approach? To be successful, every player in the process must benefit. Some potential areas of SW applications include Selection between alternatives; Estimation and classification; Diagnostic problems; Dynamic modeling; Optimization tasks; and Real-time applications and time-dependent changes. Hopefully, several extensions to the described Smart Water applications could be quickly developed.

SWF opportunities provided by artificial intelligence

SWF opportunities mainly included agriculture, domestic purposes, and industry. The challenges for SWF include water governance, water scarcity, water-related disasters, river flow forecasting, surface, and/or groundwater flow, ensuring water quality, contaminant transport, water planning, smart metering, leakage detection in pipelines and water networks, analyzing environmental data, climate change, weather forecasting, climate-smart agriculture, rain-fed land, irrigated land, optimal land use, rising populations, access to fresh and clean water, adequate sanitation, water-related diseases, stakeholder engagement, socio-economic aspects, economic growth, and building an efficient circular water economy. Brief SWF opportunities provided by AI systems are offered in Table 5.

Table 5 SWF opportunities provided by artificial intelligence.
Full size table

Discussion

The Arabsphere population is 5% of the world, and its share is 1% of available global water (IFAD 2009). The Arabsphere faces water stress, scarcity, and crises. By 2035 the Arabsphere will face acute water stress. The shortage of water needs is vastly growing. The Arabic world should introduce innovative methods for adapting to water shortage. Arabic world peoples, political leaders, water professionals, scientists, governmental officials, NGOs, private businesses, civil associations, development organizations, and financing agencies must identify wise solutions and commitments to face the water challenges. Food security, and water security, are fundamental and vital for human and national stability. The main option available is to achieve more goods with less water, i.e. Increase water use productivity for the reason that new water development in the Arabic world is both limited and costly. Complex challenges and interactions related to water-food-energy nexus could be developed in a well-rounded equitable sustainable manner (Zhang et al. 2019).

This article has attempted to define the innovation in water knowledge from optimization to AI research and application. Numerical optimization for solving water issues has focused researchers’ interest on well-defined, isolated problems, often of limited scope that proved to be solvable. Accepting satisfaction instead of optimality of solutions, one need not restrict oneself to addressing only narrowly tailored problems and instead can look at broader problems to start with. AI techniques in water engineering are modest, compared to domains like transportation, and energy (Doorn 2021). The emerging risks and limitations of existing mechanisms in adopting AI for sustainability fields were identified (Galaz et al. 2021). AI could be incomprehensible and/or opaque. So, Innovative AI techniques are humanly explainable. Explainable AI was discussed from an engineering perspective (Naser 2021). Responsible AI pathways were suggested to face poor clearness and responsiveness (Buhmann and Fieseler 2021).

Climate Change (CC)

CC and food security are particularly closely linked in Arab societies due to their high vulnerability to water-related “external shocks.” Arab societies are exposed to CC, WS, and negative impacts on water resources security, safety, and peace. CC has significant implications for water security, creating new crises, risks, problems, and challenges and exacerbating existing vulnerabilities. The Arabsphere’s climate became warmer and drier. Climate changes cause uncertainty in water-related decisions. Water investments should offer the best strategies to adapt to CC. Facing climate change challenges requires applications of science, technology, innovations, knowledge systems, wise water investments, and improving agricultural water productivity. CC impacts should be included in water master plans in all economic sectors. Broad-based water service interventions in water supply and energy utilities, water and sanitation, irrigation services, and CC are a must. This ensures a basket of benefits for improved sustainable livelihoods.

Unconventional water

The AI techniques applied in hydrology were reviewed. Examples included forecasting of hydrological streamflow (Ibrahim et al. 2022). The decision-making activities in the public sector by AI, data intelligence, and big data were discussed (Di Vaio et al. 2022). The overpopulation, increasing consumption, Quality of life (QOL), and CC put more pressure on the limited available water, especially in arid (Arab) regions. There improvements in the efficiency of exploiting water resources have a ceiling (World Bank, 2017). Some researchers have studied unconventional water. Examples of unconventional water are atmospheric water (water-from-air extraction), reclaimed gray/wastewater, desalinated water, offshore groundwater, and water transportation. There is much fresh water available in the air. Atmospheric water capture (humidity harvesting, fog harvesting, dew harvesting, cloud seeding …) is a promising technology for harvesting water from the air. Reclaimed water is a reliable unconventional water resource alternative to address CC impacts (WWAP 2017). Seawater and/or brackish water desalination are productive water resources. Worldwide, 95 million m³/day of desalinated water was produced from about 16,000 desalination plants, approximately 50% of which is produced in the MENA region (Jones et al. 2019). In 2022, the Arab League estimated Arab region has a 46.7% share of global desalination capacity, 7-9 % annual growth, 78 desalination projects operating or planned for construction, and an expansion totaling 1.16 million m3/day. Offshore groundwater could be a practicable water resource alternative in the future. Fundamental metrics of offshore groundwater occurrences such as Locations, Offshore distances, Minimum total dissolved solids (TDS), and Water depths are reported (Post et al. 2013). Optimum coastal fresh groundwater resources could be estimated by Submarine Groundwater Discharge (SGD) (George et al. 2018). Greater volumes of water will be needed. Transportation of water and Towing icebergs technologies can be suitable future options to provide fresh water. Unconventional water (e.g., reclaimed water, desalination, fog collection, cloud seeding, and atmospheric water harvesting) is vital in future planning for the next generations (UNESCO, UN-Water 2020).

Hackathons development

Although hackathons were recognized in engineering disciplines, lately, hackathons have been implemented as a collaborative process in some scientific domains. Recent hackathon topics included health, healthcare, medicine, biotechnology, and social innovation. Recent examples included Pediatrics (Sajid et al. 2021), clinical trials (Tan et al. 2022), healthcare “genomics” (Leonard et al. 2023), healthcare “biomedical research” (Ramadi et al. 2022), healthcare (Park et al. 2023), digital biotechnology (Jenkins et al. 2022), and social innovation (Wu et al. 2023).

Globally, the Hajj hackathon was a notable, valuable, and huge event. Approximately, three thousand participants attended the Hajj hackathon. The participants were mainly software developers from a hundred countries. The Hajj pilgrimage is one of the largest religious gatherings in the world. Annually, Millions of Muslim pilgrims‏ head to the Holy City of Makkah “Mecca” and the Holy Sites, seven circling the Kaaba -Islam’s holiest site- for the Hajj pilgrimage. Also, the Muslim pilgrims‏ “Guests of the Merciful” converge on tent camps at the Mina location in the near desert for days. The Hajj hackathon aimed to serve millions of pilgrims (Muslims), and provide the opportunity for the largest possible number of Muslims to perform the Hajj to the fullest extent. The Hajj hackathon worked to enrich and deepen pilgrims’ experience, by preparing the Grand Mosque, the spiritual and holy sites, and religious Mecca city to receive them during the days of Hajj and mitigating the obstacles that they may face. The Hajj hackathon competition included important Hajj services such as capacity increase, the holy sites development, the longest pedestrian globally road, which starts from Jabal al-Rahma in Arafat “Arafah”, passing through Muzdalifah, and ends at Mina, travel and accommodation, food and beverages, crowd management, transportation, traffic control, public health, waste management, communication, and financial solutions.

Smart water hackathon in Arabsphere

The smart water model is established on the smart platform Data Collection & Analysis M2M Transactions. The main components of the SW model are water management, water security, water economy, ecology, environment, and energy. Water management focuses on modernizing water administration through AI solutions to better allocate water resources, prioritize investments to a comprehensive water view, and empathize E-Government, smart meter/grid, cloud, virtual hosting, remote control, automated solutions, minimizing water loss, smart computing, and maintenance. Water Security focuses on pollution prevention and water quality and efficiency, through AI solutions to enhance reservoir Capacity Tracking, water Emergency Management, leak detection, and optimizing water service routes. The water economy focused on modernizing how water is performing and enabling World growth. Ecology, environment, and sustainability focused on reducing water consumption, improving World growth and environment indicators by managing wastewater, and sustainability measures as part of national strategy. Figure 3 presents a Flow diagram of the Successful implementation of the Smart Water Hackathon. Smart Water Management (SWM) could improve hydrological responses, water quality, and water management by using proactive strategies based on real-time data (Du Plessis 2021). Global exemplary SWM case studies in both emerging and developed locations and their smart solutions were reported (K-WATER AND IWRA 2018).

Fig. 3: Flow diagram of the successful implementation of smart water hackathon.
figure 3

The flow diagram shows the three main phases of the smart water hackathon; the colors stand for the three phases (yellow = before the hackathon phase, orange = during hackathon phase, and green = after the hackathon phase).

Full size image

Smart solutions include smart sensors, real-time monitoring, flood, drought, water quality, leak detection, community satisfaction, integrated network, drinking water, groundwater, sanitation, efficient irrigation, soil monitors, energy optimization, rainwater collection, and stormwater management. The application of smart water-based fluid containing a magnetic suspension (ferrofluid) in anionic dye removal to prevent wastewater treatment pollution was reported (Chen et al. 2021). A smart irrigation water system to achieve related SDGs was implemented (Barkhordari and Hashemy Shahdany 2021). Also, an intelligent irrigation system that utilizes the Internet of Things (IoT) and fuzzy logic controller (FLC) has better irrigation performance by using the indicators of energy and water consumption (Benyezza et al. 2021).

Intelligent water metering (IWM) was applied to alleviate drought and water crises, and be efficient in water conservation and sustainable cities (Visser et al. 2021). Smart irrigation was proposed to optimize water use and improve crop yield (Shi et al. 2021). Smart water using soft computing techniques was proposed to ensure accurate incentives, water-wise usage, and sustainability of water resources (Thakur et al. 2021). In the governmental sector, AI could be used in the adoption phase, implementation phase, and decision-making phase (W. Zhang et al. 2021). The impact of AI on employees and worker welfare regarding health, stress, freedom, monitoring, insecurity, and satisfaction was studied (Nazareno and Schiff 2021). Unified Theory of Acceptance and Use of Technology (UTAUT2) was used to investigate the user behavior and behavioral intention of the common products and segments equipped with AI technologies (Gansser and Reich 2021).

The main issues of the intelligent water hackathon were expressed concerning hydrology, water security, water footprint, water management, circular water economy, hydraulic structures and ecology, environment & and sustainability. The intelligent water hackathon for the Arabsphere is displayed in Fig. 4. Hydrology topics included watersheds, flows, sediment transport, flooded areas, evaporation, seepage, hydropower generation… etc. Virtual water is an indicator to evaluate the significance of water for development or production. Water footprint is a numerical tool to value the relation between water consumption and water-related products. Water footprints (blue, green, and gray) are used to assess rainwater evaporated, surface or groundwater evaporated, and polluted water, respectively. Hydraulic structures could be constructed for irrigation, drinking water, agriculture, energy, and other purposes. When analyzing hydraulic structures and infrastructure, the realized benefits, alternatives, possible impacts, feasible alternatives, location, size, cost, and cost-effectiveness should be determined.

Fig. 4: The smart water hackathon in Arabsphere.
figure 4

The diagram shows the critical components of the intelligent water hackathon (e.g., hydrology, water security, water footprint, circular water economy, hydraulic structures, etc.). The colors highlight the idea of diversity.

Full size image

Characteristics of intelligent water system

Water intelligent systems imply the intensive use of AI concepts to optimize current and future water rural and urban requirements and services and enable safe and fresh water for new generations. The value opportunities of Smart water (Water Intelligent Systems) include but are not limited to cost reduction, increased income, water efficiency, optimal water planning, and governance, and paving the road for sustainability and quality of life. The framework of SWF based on AI is displayed in Table 6. The significant characteristics of an intelligent water system (IWS) could be outlined as:

  • SWS is fault tolerant. Since memory is distributed, failure of some processing elements will slightly alter the overall behavior of the system. Unlike traditional computing systems, the failure of any smaller part will stop its performance. This characteristic is very well suited to applications where reliable systems need to be developed from less reliable components like the case of the water industry.

  • SWS could represent uncertainty; a measure of “belief” could be incorporated by modifying the problem pattern.

  • SWS has associative memory. The SWS responds to noisy, incompetent, or previously unseen data.

  • SWS extracts classification characteristics from many input examples.

  • SWS needs small computer time for learning and could achieve fast responses.

  • SWS are particularly suited for pattern recognition tasks.

  • SWS learns by example. These examples could be elicited from experts without asking how and why they came to those conclusions.

Table 6 Artificial intelligence’ SMART criteria for sustainable water future.
Full size table

The water intelligent systems

The framework of Water Intelligent Systems for SWF is displayed in Fig. 5. The Water Intelligent System was expressed in terms of Vision, Foresight, Global Agenda, Cooperation, Innovation and knowledge, Water awareness and education, Standardization, Feasibility and success, Circular water economy, and Evaluation.

Fig. 5: The framework of water intelligent systems for sustainable water future.
figure 5

The diagram shows the critical components of the water intelligent systems for a sustainable water future (e.g., Vision, Foresight, Global Agenda, etc.). The colors highlight the idea of multifariousness.

Full size image

The contributions of smart water to water knowledge & and industries are:

First, large amounts of knowledge or data are typically made available in SW systems or databases linked to SW systems. These may be encoded as knowledge bases, classifying crises that appear on water industry sites, or detailed descriptions of water industry projects. Describing a crisis by using natural language such as English instead of cryptic variables makes SW systems easier to browse and understand even by novice users. Moreover, knowledge can include details that are quite domain-specific. Together with a sound classification system and fast query routines, such knowledge-intensive systems then make crisis-solving easier and produce tailored solutions.

Second, SW systems typically articulate individual objects and constraints between objects and constructively assemble solutions, much like people do. This enables them to reason about which objects to select and constraints to apply, relax, or ignore, and when to take applied constraints into account. If the SW system were developed to do so, it could even generate constraints to proceed with problem-solving. Decision-makers, initially using trial-and-error for selecting objects and constraints, eventually learn which choices are more likely to succeed than others, and develop strategies for problem-solving. Strategic knowledge can also make SW systems more effective in finding solutions.

The smart water influence

Finally, SW systems generally rely on one of two methods to somehow guarantee the quality of their solutions. Developers of SWSs may assume that their programmed strategy is a good one, and consequently, that the generated solution is a good one as well, even if that is difficult to prove. In addition, they may implement evaluation functions to compare intermediate solutions.

Conclusions

Artificial and applied intelligence methodologies are applied in a growing number of practices and research related to the fields of hydrology, and water resources. This paper reveals a young and promising field of study whose primary concern is finding an effective way to apply Smart Water problem-solving, and skills to a wide range of practical problems. Research and demonstrations of smart water require adequate resources, integrated multidisciplinary teams, and a true partnership of academe, government, and industry. Recruiting motivating and educating a new breed of researcher-engineers who can meet the intellectual and physical challenges of meaningful scientific explorations on operating SWSs was a most daunting challenge. Also, of note is the significance of the proper application of knowledge tools and methods within the scope of integrated water industry management. Knowledge fusion in smart water monitoring is critical for the reliable interpretation of data for management, governance, and decision-making. SWSs utilize current water data and future stream-flow forecasts to provide knowledge to water managers on how to optimize water usage, minimize the impact of both droughts and floods and maintain environmental quality. The smart water approach opened new ways of building computer models while bringing models and practice closer together. Model developers could make computers mimic water managers’ actions, and add flexibility and functionality to existing models, to develop programs that are potentially easier to understand and use. Smart water modeling techniques fill a gap among other modeling tools available today. Artificial intelligence could shape future policies to recover from the COVID-19 pandemic while preserving livable Arab societies. The author hopes that this paper provides some feel for the Arabsphere to face its water future benefiting from artificial intelligence. By highlighting challenges and encouraging competition, hackathons could develop applicable solutions or valuable wild, creative, or promising ideas. The hackathon encouraged diverse participation to generate innovative ideas and creative water solutions to complex water stress problems. The hackathon revealed the urgent need for mitigating the stress on freshwater resources in the Arabsphere.