Investigating the Resolution-Performance Trade-off of Object Detection Models in Support of the Sustainable Development Goals

Satellite imagery provides impartial, inclusive, and timely geospatial data regarding global issues, supplementing traditional ground-based methods. The volume, velocity, and variety of satellite imagery present novel capabilities to support the United Nations' Sustainable Development Goals by providing repeatable data to assess progress and support reliable statistics connecting policy with evidence. Currently, the relationship between spatial resolution and accurate detection of sub-meter- to meter-scale objects supporting policy-making remains unexplored. This study investigates the resolution-performance trade-off by comparing results of object detection models and their implications for two sustainability-motivated use cases. These include vehicle detection, used to inform traffic flow and density for understanding infrastructure needs and lockdown policies, and solar panel detection, where accuracy is crucial in monitoring green energy production and sustainable energy access. The results show a largely linear degradation of object detection models using imagery at 30, 40, 50, and 60 cm resolutions simulated from 7 cm aerial imagery. Object detection models using 30 cm imagery improve F
$_{1}$
score by 65% compared to 60 cm models. Further investigation into a preprocessing step using 30 cm imagery to generate 15 cm imagery shows an average F
$_{1}$
score increase by 5% for detection of small objects across multiple use cases. The results and analysis provide a basis for more robust investigations into the capabilities of very high resolution satellite imagery to support the Sustainable Development Goals.