In the fast-changing world with increased water demand, water pollution, environmental problems, and related data, information on water quality and suitability for any purpose should be prompt and reliable. Traditional approaches often fail in the attempt to predict water quality classes and new ones are needed to handle a large amount or missing data to predict water quality in real time. One of such approaches is machine-learning (ML) based prediction. This paper presents the results of the application of the Naïve Bayes, a widely used ML method, in creating the prediction model. The proposed model is based on nine water quality parameters: temperature, pH value, electrical conductivity, oxygen saturation, biological oxygen demand, suspended solids, nitrogen oxides, orthophosphates, and ammonium. It is created in Netica software and tested and verified using data covering the period 2013–2019 from five locations in Vojvodina Province, Serbia. Forty-eight samples were used to train the model. Once trained, the Naïve Bayes model correctly predicted the class of water sample in 64 out of 68 cases, including cases with missing data. This recommends it as a trustful tool in the transition from traditional to digital water management.

One of the most important issues in multi-criteria decision making is the number of requited judgments decision-maker/analyst has to perform. This paper presents a comparison of the results obtained by standard analytic hierarchy process (AHP), limited AHP, and best-worst method (BWM) if the number of criteria is 6, 7, and 8. The examples show that BWM's results are comparable with the results if standard AHP is used, while the limited version of AHP is generally inferior to the other two methods.

In the assessment of principles and guidelines to achieve specific goals before strategies in water resources and related sectors are formulated, the quality of experts participating in making group decisions should be evaluated. This paper introduces an innovative approach designed to evaluate the quality of group members based on their consistency and deviations from the group's decision. The group members are considered as alternatives within a multi-criteria framework, employing several typical performance indicators as criteria to assess their competence and compliance with the group. Considering the policy-making, the paper provides a rationale for possibly excluding certain members from the decision-making process to prevent making unsustainable decisions. A case study is presented about the evaluation of the importance of six Ramsar sites in Serbia, facing imminent threats from water regime disturbances and climate change-induced droughts. Seven experts participated in the process and the results revealed that several experts displayed the poorest performance across all three prioritization schemes. This suggests the necessity for re-evaluating their judgments or considering their exclusion from the final decision-making process. The proposed assessment procedure holds promise for enhancing the potential to derive sustainable solutions in any complex and critical domain of water resources policy-making and strategic planning.

Wetlands, crucial ecosystems providing vital services and habitats, face threats from human activities and climate change. The Restore4Life project, centered in the Danube basin, aims to address these challenges through holistic wetland restoration efforts. Across the Danube basin, transformative restoration activities are underway, focusing on enhancing wetland connectivity, fostering biodiversity, unlocking carbon sequestration potential, and delivering essential ecosystem services. Implementation sites include floodplains, rivers, and lakes, where dedicated efforts encompass concrete restoration activities. Additionally, at six monitoring sites, the project team tracks the impacts of previous wetland restoration initiatives on ecosystem conditions and services. Within Serbia, the Landscape of Outstanding Features – Vlasina stands out as a valuable implementation site, boasting significant peatlands and biodiversity. Despite being protected, these habitats face threats from tourism, urbanization, agriculture, and peat extraction. Restoration efforts within Vlasina target four polygons, aiming to address degraded areas spanning 1,600 hectares. Restore4Life represents a significant endeavor to address wetland restoration challenges, engaging in restoration activities, community empowerment, and the promotion of sustainable practices. Moreover, the project pioneers citizen science initiatives in Serbia, fostering public involvement in environmental conservation efforts. By combining scientific expertise with citizen engagement, Restore4Life aims to pave the way for effective wetland restoration practices and deepen societal appreciation for the ecological importance of these vital habitats. The objectives of the paper are to highlight the importance of wetlands restoration, biodiversity conservation, water security, and climate resilience, and to advocate for community engagement, including citizen science, and sustainable practices to preserve these vital ecosystems. Recognizing and nurturing the values of wetlands is crucial for fostering harmonious relationships between humans and nature, ensuring the long-term well-being of both present and future generations.