Air in Your Neighborhood: Fine-Grained AQI Forecasting Using Mobile Sensor Data
This provides more accurate local air pollution forecasts for public health in developing countries, though it is an incremental improvement using existing methods on new data.
The paper tackles the problem of inaccurate air-quality index (AQI) data due to sparse sensors by predicting AQI in 1 km² neighborhoods using the AirDelhi dataset, achieving a 79% reduction in MSE (71.654 improvement) over existing works.
Air pollution has become a significant health risk in developing countries. While governments routinely publish air-quality index (AQI) data to track pollution, these values fail to capture the local reality, as sensors are often very sparse. In this paper, we address this gap by predicting AQI in 1 km^2 neighborhoods, using the example of AirDelhi dataset. Using Spatio-temporal GNNs we surpass existing works by 71.654 MSE a 79% reduction, even on unseen coordinates. New insights about AQI such as the existence of strong repetitive short-term patterns and changing spatial relations are also discovered. The code is available on GitHub.