AtmosTrack

AtmosTrack is an open-source platform that helps cities understand and manage air pollution at a hyperlocal level. Instead of relying only on city-wide Air Quality Index (AQI) readings, the system analyzes historical air quality and weather data to estimate pollution patterns across different areas of a city.

Using machine learning models, AtmosTrack predicts AQI values based on factors such as temperature, humidity, wind speed, and historical pollution trends. These predictions are visualized on an interactive map, allowing users to identify pollution hotspots and monitor environmental conditions more effectively.

The platform also calculates a vulnerability index that highlights sensitive locations such as schools, hospitals, and densely populated neighborhoods that may be more exposed to pollution risks.

AtmosTrack includes a policy simulation feature, enabling users to explore how interventions like traffic reduction or environmental regulations could influence air quality outcomes. By combining predictive analytics, geospatial visualization, and decision-support tools, the platform aims to support smarter environmental planning and more transparent climate governance.

As an open-source project, AtmosTrack is designed to be adaptable to different cities and datasets, encouraging collaboration in building data-driven solutions for urban air pollution.