Rapid urbanization and industrial growth have intensified air quality challenges in cities worldwide. Understanding how urban structure influences air pollution requires analytical frameworks capable of handling complex spatial and temporal data. This seminar presents how the integration of Geographic Information Systems (GIS) and Machine Learning (ML) can enhance urban air quality research. GIS provides a spatial foundation for managing and visualizing environmental parameters such as land use, traffic density, meteorological conditions, and emission sources. ML techniques make it possible to identify complex relationships between urban structural characteristics such as urban built-up areas (UBAs) and urban green spaces (UGSs) and pollutant concentrations. Moreover, ML enables air quality assessment by predicting pollutant levels, estimating missing data, and determining the influence of environmental and urban factors. By integrating GIS-based spatial analysis with ML-based predictive modeling, it becomes possible to generate high-resolution air quality maps, identify pollution hotspots, and evaluate the role of urban morphology in pollutant dispersion. This integrated approach improves the interpretability of air quality assessments and informs strategies for sustainable urban and environmental management.

Join Zoom Meeting
https://uw-edu-pl.zoom.us/j/97848514361?pwd=pcbE5IPFUz5241S7SpZVbnfom5jF8e.1

Meeting ID: 978 4851 4361
Passcode: 005211