Tracking Progress Towards Sustainable Development Goal 6 Using Satellite Imagery
It provides policymakers with a scalable tool to identify underserved areas for targeted interventions in water and sanitation, though it is incremental as it applies existing methods to new data for specific SDG indicators.
This study tackled the problem of tracking progress towards Sustainable Development Goal 6 by developing a modeling framework using satellite imagery and deep learning to evaluate access to piped water and sewage systems in Africa, achieving over 96% accuracy for classification and high concordance with official statistics (R2 of 0.95 for piped water and 0.85 for sewage).
Clean water and sanitation are essential for health, well-being, and sustainable development, yet significant global disparities persist. Although the United Nations' Sustainable Development Goal (SDG) 6 clearly defines targets for universal access to clean water and sanitation, limitations in data coverage and openness impede accurate tracking of progress in many countries. To bridge these gaps, this study integrates Afrobarometer survey data, satellite imagery from Landsat 8 and Sentinel-2, and advanced deep learning techniques using Meta's self-supervised Distillation with No Labels (DINO) model to develop a modeling framework for evaluating access to piped water and sewage system across diverse African regions. The modeling framework achieved notable accuracy, with over 96% for piped water and 97% for sewage system access classification. When combined with geospatial population data, validation against official statistics from the United Nations Joint Monitoring Program demonstrated high concordance at the national scale (R2 of 0.95 for piped water access and R2 of 0.85 for sewage system access). The national-level estimates can represent SDG Indicators 6.1.1 and 6.2.1. This approach provides policymakers and stakeholders with an effective, scalable, and cost-efficient tool to pinpoint underserved areas requiring targeted intervention. The methodology developed herein can be adapted for assessing other infrastructure-related SDGs, promoting enhanced monitoring and informed decision-making towards achieving global sustainability objectives.