Water quality and quantity are critical issues as the Florida’s population grows. This paper analyzed water use regionally (central, north, and south Florida) as well as in rural and urban areas in Florida from 2005 to 2015 using three indicators (total water use, agriculture water use, and per capita water use). Eight (8) water-consuming categories, such as aquaculture, livestock, irrigation, public supply, thermoelectric power, mining, industrial self-supply, and domestic self-supply, were considered for total water use. Per capita water use used public supply category and agricultural water use used aquaculture, livestock, and irrigation categories. Linear regression analysis was used to observe the relationship between population and water use. The highest water use was recorded in south Florida, while the lowest was in north Florida. Water use per capita was higher in urban areas. Irrigation water use was higher among the eight water use categories. Many drivers influencing Florida water use were identified through literature review and causal loop diagram was developed. Some (e.g., household size, land use/land cover change, urbanization, agriculture, population, income, climate change, tourism, and industry) may cause an increase in water use, while others (e.g., pricing systems, conservation methods, education, and technology) may cause a decrease in water use. Overall, this research addresses the need of understanding water use trends and the drivers affecting those trends, which are important to determine whether a water conservation plan is needed.

Artificial intelligence (AI) has the potential to significantly advance the management of nonpoint source pollution (NPSP), a critical environmental issue characterized by diffuse sources and complex transport mechanisms. This study systematically examines current AI applications addressing NPSP through bibliometric and systematic analyses. A total of 124 studies were included after rigorous identification, screening, and eligibility assessments based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework. Key findings from the bibliometric analysis include publication trends, regional research contributions, author and journal contributions, and core concepts in NPSP. The systematic analysis further provided: (a) a comprehensive synthesis of NPSP characterization, covering pollution sources, key drivers, pollutants, transport pathways, and environmental impacts; (b) identification of emerging AI technologies such as the Internet of Things, unmanned aerial vehicles, and geographic information systems, and their potential applications in NPSP contexts; (c) a detailed classification of AI models used in NPSP assessment, highlighting predictors, predictands, and performance metrics specifically in water quality prediction and monitoring, groundwater vulnerability mapping, and pollutant-specific modeling; and (d) a critical assessment of knowledge gaps categorized into AI model development and validation, data constraints, governance and policy challenges, and system integration, alongside proposed targeted future research directions emphasizing adaptive governance, transparent AI modeling, and interdisciplinary collaboration. The findings from this study provide essential insights for researchers, policymakers, environmental managers, and communities aiming to implement AI-driven strategies to mitigate NPSP.

Artificial intelligence (AI) has the potential to revolutionize water management (WM) by enabling accurate predictions and effective monitoring of water resources, especially in response to climate change (CC) challenges. This study offers insights into the current state of research on AI applications in water management (AI-WM) through bibliometric and systematic analyses. A total of 191 studies were selected following the identification, screening, and eligibility phases of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework. The study's key findings include: (a) A bibliometric analysis identifying core concepts in AI-WM and underexplored aspects of WM, highlighting critical areas like water quality, consumption, and availability. (b) A classification of AI models and algorithms, emphasizing their application to specific WM areas and performance metrics used for evaluation. (c) An assessment of technical, data-related, socio-economic, ethical, and policy-related challenges in AI-WM, along with recommendations to address these challenges. (d) Identification of key research gaps and future research needs within AI-WM. Furthermore, this paper synthesizes challenges, knowledge gaps, and future research directions identified from over 25 review papers. The findings provide valuable guidance for researchers, policymakers, environmental agencies, utility companies, and communities seeking to improve WM through AI-driven solutions.

The climate-smart agriculture (CSA) approach, a sustainable alternative to conventional practices in agriculture, supports three main pillars: increasing productivity, resilience, and greenhouse gas (GHG) mitigation through the adoption of climate-smart practices (CSPs). Effective CSA assessment tools are needed to evaluate the impact of and support the broader adoption of CSPs. This study addresses this need by developing the RAPTURE (Resilient Agricultural Practices for Transforming Uncertain and Resource-Scarce Environments) tool. The RAPTURE tool was developed through five steps, which included collecting data on CSA definitions, existing practices and classifications, climatic conditions of the study areas, and the mathematical equations used to assess CSPs—all of which were stored in databases. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework was adopted to guide the selection and inclusion of 222 studies from the Web of Science database, forming the basis for the development of the RAPTURE tool. The first step of RAPTURE synthesizes simple and complex definitions of CSA from the database of 35 definitions. For the second and third steps, an updated classification of the CSPs was developed using a database with 78 CSPs, and a weather conditions database created from areas where CSPs have been studied and implemented was also provided, respectively. The fourth step of the RAPTURE tool includes a database containing the input and output variables necessary for the assessment of CSPs’ impacts, which is essential for the selection of an assessment method. The fifth and last step of the tool contains the assessment methods available, including 24 mathematical methods documented and synthesized. An application of RAPTURE using agricultural data from Florida in 2022 and 2023, and considering an increase of 20% with the implementation of CSPs, showed better productivity and rain-use efficiency. While previous studies have shown that adopting CSPs in agriculture provides several benefits, such as better agricultural production, higher carbon sequestration, the application of the RAPTURE tool in assessing CSPs also demonstrates their ability to increase productivity and resource-use efficiency.