Application of Land Use Regression (LUR) Models in Air Pollution Assessment

Pollution, posing a significant health and societal risk, intensifies with urbanization and industrialization. This chapter explores Land Use Regression (LUR) models that predict air pollution concentrations at specific locations using geospatial data and variables like land use and traffic density. Despite their broad application in environmental health to capture complex dynamics with fine spatial resolution, LUR models depend heavily on statistical correlations rather than direct measurements, face potential data quality issues, and struggle with micro-scale predictions. The chapter highlights the importance of integrating multiple data sources, such as satellite imagery and mobile sensors, via Geographic Information System (GIS) technology. This integration enhances the robustness and accuracy of the models, underlining their essential role for policymakers and researchers in tackling air pollution effectively.