Leveraging Remote Sensing and GIS for Evidence-Based Policy Implementation of SDGs

Vollständiger Abstract

Worum geht es in dieser Arbeit?

The 2030 Agenda for Sustainable Development faces a critical data gap, with recent assessments indicating that only 15% to 18% of the 169 Sustainable Development Goal (SDG) targets are currently on track for completion as of mid-2025. This paper investigated how Remote Sensing (RS) and Geographic Information Systems (GIS) provide the essential "where" dimension required for evidence-based policy implementation and localized decision-making. By integrating Earth observation data with advanced analytics such as Machine Learning (ML) and Convolutional Neural Networks (CNNs), these technologies enable monitoring systems to achieve an average accuracy of 90% in tracking complex indicators. Methodologically, the paper adopts the three-phase SDGs Geospatial Roadmap, encompassing preparation, design, and production, to bridge the divide between traditional statistical records and spatial data. The analysis demonstrated the transformative impact of geospatial intelligence across multiple sectors, including high-accuracy poverty mapping (SDG 1), real-time crop yield prediction (SDG 2), and resilient urban modeling (SDG 11). Case studies, such as Costa Rica’s forest management system (SDG 15), further illustrated the role of these tools in securing international climate funding and ensuring accountability. Despite these technical successes, the study identified significant institutional and technical barriers, including fragmented governance, data silos, and a persistent geospatial digital divide. The paper concluded that the successful implementation of the SDGs requires a systemic shift toward anticipatory governance, necessitating robust inter-agency collaboration between National Statistical Offices (NSOs) and National Geospatial Information Agencies (NGIAs), alongside significant investment in local technical capacity