Suburbanisation effects on light pollution in Warsaw’s natural areas assessed using drone imagery and machine learning

Abstract

Suburbanisation is a major driver of artificial light at night (ALAN) in urban environments, yet its specific impacts on ecologically valuable areas remain insufficiently quantified. This study investigates the effects of suburbanisation on light pollution (LP) across eight ecologically significant natural areas in Warsaw, Poland. Field measurements were conducted using a luxometer and a Sky Quality Meter (SQM-L), yielding night sky brightness values ranging from 16.23 to 19.03 mag/arcsec² across sites (Bortle classes 6–9). A Faster Region-based Convolutional Neural Network (Faster R-CNN) model was trained on drone images to detect and spatially map streetlights. Boundary zones between urbanised and natural landscapes were identified as the most vulnerable to ALAN intrusion. The study demonstrates that AI-based object detection can support LP monitoring and streetlight location identification in selected high-value urban areas. The findings provide evidence to support urban planning and lighting management, particularly in boundary zones between urbanised and protected natural areas.