Analysis of spatial patterns of light pollution risk in urbanization areas and influencing factors based on Luojia 1-01 nighttime imagery and illuminance measurements

Quantitative analyses of the spatial characteristics and drivers of risk levels in urban nighttime light pollution remain underexplored in research. Using Shenzhen as a case study, this paper combines nighttime remote sensing data with vertical illuminance measurements and applies five empirical models to estimate overall nighttime environmental illuminance. This approach supports spatial pattern analysis and light pollution risk assessment. Eight socio-economic and natural factors were selected as independent variables. Random forest, support vector machine, and back-propagation neural network models were employed to predict light pollution risk levels. Key findings include: (1) High-precision nighttime remote sensing data, coupled with ground survey results, effectively estimates surface illuminance levels; (2) the univariate linear model was optimal for surface illuminance inversion, indicating that Shenzhen's surface illuminance ranges from 0 to 70 lx, with higher values in the west and lower values in the east; (3) among machine learning models, the random forest (RF) model best identified influencing factors, with commercial area density, road network density, and residential area density as the main drivers of spatial differentiation in light pollution risk, while topography had no impact. (4) It is recommended that in urbanized areas with significant differences in topography, sampling and analysis should be conducted in illuminated areas when analyzing the causes of light pollution. This study offers systematic insights into urban light pollution patterns and drivers, providing scientific support for urban light environment planning and management.