An indicator-based framework of circular cities focused on sustainability dimensions and sustainable development goal 11 obtained using machine learning and text analytics
The circular economy (CE) serves a practical pathway to facilitate sustainable development (SD) and achieve the Sustainable Development Goals (SDGs). Current frameworks for assessing city sustainability and circularity often lack comprehensibility and multi-dimensional indicator-based approaches, al...
| Autores: | , , , |
|---|---|
| Formato: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2025 |
| País: | España |
| Recursos: | Instituto Valenciano de Investigaciones Agrarias (IVIA) |
| Repositorio: | idUS. Depósito de Investigación de la Universidad de Sevilla |
| OAI Identifier: | oai:idus.us.es:11441/174145 |
| Acesso em linha: | https://hdl.handle.net/11441/174145 https://doi.org/10.1016/j.scs.2025.106219 |
| Access Level: | acceso abierto |
| Palavra-chave: | Circular city indicator Circular economy Macro level of circular economy Sustainable development goals (SDGs) Machine learning (ML) Semi-supervised learning Clustering algorithms |
| Resumo: | The circular economy (CE) serves a practical pathway to facilitate sustainable development (SD) and achieve the Sustainable Development Goals (SDGs). Current frameworks for assessing city sustainability and circularity often lack comprehensibility and multi-dimensional indicator-based approaches, also fail to include city-level CE indicators. This study defines an innovative structure for defining the circular city indicators (CCIs) addressing critical gaps in existing methodologies and CCIs coverage of sustainability and SDGs, especially SDG11. The methodology encompasses an extensive literature review, integrating CE principles, macro level of CE parameters and current CCIs, resulting in a comprehensive list of 241 indicators. Using advanced machine-learning techniques—semi-supervised learning, text analysis, and clustering algorithms—enhances the accuracy, comprehensiveness of the indicator classification. The indicators are categorized into 3D space across environmental, economic, and social dimensions of sustainability. This multi-dimensional approach also reveals the relationships between CCIs and 16 SDG11 classes. The analysis shows 75% of CCIs are multi-dimensional, but, five SDG11 classes show the lowest coverage in the heatmap of CCIs probability distribution across SDG11 classes, indicating a need to revise SDG11 classes and the social indicators of CCIs. The findings offer urban planners and stakeholders a practical list of CCIs to evaluate sustainability and CE level in cities. |
|---|