To help forecasters save time and make more accurate air quality predictions, STI developed AQCast, a web-based air quality forecasting system. AQCast inputs observed air quality and meteorological conditions, and also incorporates meteorological predictions from multiple forecast models. Users can view predictions by city, pollutant, and model. Predictions are color-coded by their Air Quality Index (AQI) category.
The system automatically runs daily air quality regression equations and Classification and Regression Trees (CART). If the model inputs are found to be biased, forecasters can manually adjust the input value and get more accurate predictions. AQCast was developed using several years of observed air quality and meteorological data, and STI analysts regularly update the model to incorporate new data as emissions for a given region change.