Ms Lamia Enab (p)

Rapid urbanization and increasing waste generation are intensifying pressure on Solid Waste Management (SWM) systems in developing countries, where limited resources, static planning practices, and operational inefficiencies remain prevalent. Although Artificial Intelligence (AI) is frequently promoted as a transformative solution for urban services, empirical evidence of its effectiveness and institutional applicability in resource-constrained SWM systems remains scarce. This study addresses this gap by conceptualizing AI as a decision-support tool that complements, rather than replaces, conventional waste management practices. Using the Radwan neighborhood in Amman, Jordan, as a case study, the research develops and evaluates an AI-supported waste collection framework integrating Internet of Things (IoT) sensing, geospatial data, and heuristic optimization. The methodology incorporates qualitative analysis of an existing SWM system as well as quantitative simulation of AI-based routes for waste collection vehicles as well as capacities. Real-time levels of fill, spatial data from a Global Positioning System (GPS), as well as capacities of waste collection vehicles, are incorporated in order to create optimized routes. Performance of the system is evaluated through a comparative analysis of conventional and AI-optimized routes, whereby performance metrics are based on evaluation of distance travelled, route duration, and fuel consumption, as well as carbon produced. Importantly, the study demonstrates the institutional feasibility of AI adoption through a human-in-the-loop configuration that preserves municipal control and aligns with existing governance structures. The findings provide empirical evidence that AI can function as a practical lever for enhancing efficiency and sustainability in SWM systems without requiring costly infrastructure overhauls. The study offers actionable insights for Jordanian municipalities and other municipalities in comparable contexts and contributes to advancing sustainable urban planning objectives aligned with the Sustainable Development Goals (SDGs). Moreover, the study offers a foundation for future research on AI applications in urban sustainability and circular economy transitions.

Ms Hyojoo Han (p), Ms Geunhee Kim

Digital platformization is reshaping how urban environmental knowledge is produced, shared, and mobilized in governance processes. While citizen science has expanded rapidly through online platforms, existing research has primarily focused on data accuracy or participants’ learning effects, paying limited attention to how platform-mediated data practices may reconfigure local ecological governance and planning. This study aims to examine how citizen science platforms structure ecological monitoring practices and to analyze their potential to reshape urban ecological governance, with a focus on policy and planning implications. Drawing on a qualitative case study of the Uiwang Community Ecology Research Group in South Korea, the research combines semi-structured interviews with 15 members and the group leader and participant observation of regular monitoring activities (August 2025–January 2026). The analysis is guided by a three-stage conceptual framework linking (1) offline ecological observation and data production, (2) platform mediation through standardized data formats, interaction features, and gamification elements, and (3) the translation of accumulated data into public assets connected to local governance. The findings reveal three main results. First, the platform transforms dispersed individual observations into standardized, cumulative datasets, enabling their reinterpretation as collective ecological resources used in local education programs, environmental festivals, and community reports. Second, interactive features such as species identification requests, comments, rankings, and challenges enhance sustained participation, facilitate peer learning, and enable cross-validation, thereby improving data reliability and reinforcing participants’ ecological identities. Third, accumulated citizen-generated data functions as a “language of collaboration” in interactions with local authorities, supporting recognition of ecological monitoring as formal volunteer work and providing potential evidence in development–conservation conflicts. However, despite these emerging governance linkages, the institutional integration of citizen science data into formal planning instruments remains limited, and systematic verification and administrative feedback mechanisms are underdeveloped. The study contributes to urban and regional planning debates by conceptualizing citizen science platforms not merely as data-collection tools but as governance devices that mediate relationships between citizens and municipalities in the context of digital transformation. It suggests that strengthening institutional pathways for data validation, feedback systems, and integration into environmental assessment and planning procedures is essential to realizing the adaptive potential of platform-mediated ecological governance.

Ms. Hyemee Hwang (p), Prof. Dongkun Lee, Dr. Huicheul Jung

Urban green spaces (UGSs) are vital for enhancing urban ecological health and resident well-being. However, their diverse functions need to be balanced in consideration of limited space and varying stakeholder preferences. Integrated planning approaches are needed to exploit the multiple benefits of UGSs. This study introduces a multi-objective decision-support model designed to optimize UGS planning by simultaneously addressing carbon sequestration, ecological connectivity, and cost constraints. The model incorporates the non-dominated sorting genetic algorithm II to identify Pareto-optimal solutions for tailored decision-making strategies balancing different priorities. The model indicated that ecological connectivity can be improved by 7.57% while meeting carbon-reduction and budgetary targets. The model effectively balanced trade-offs, underscoring the importance of not only the quantity of green space but also its strategic placement. This decision-support framework empowers decision-makers to rapidly simulate and validate optimal scenarios, effectively balance competing objectives, and provide a scientific basis through verifiable feedback, ultimately promoting the development of sustainable urban environments.