Creating a high-resolution heat map of air quality is another technological challenge for us to tackle. Airvoice’s mathematical modeling team is developing maps to provide air quality information for any location—at the moment and with a 72-hour forecast.
Today, similar services already exist, but most of them provide unverified data. Such services are useful for obtaining an overview of the air quality in a city but are not suitable for making responsible decisions. City managers need reliable data. To get that reliable data, it is necessary to identify or deploy reliable real-time monitoring networks in the area of interest, adapt numerical models to local conditions, and conduct an inventory of emission sources (and then to keep it up-to-date combining automatic and manual updates).
Here’s how our model works.
Our fusion model combines a regional chemical transport model with a quasi-stationary building-height-aware Gaussian model. This predictive pollutant dispersion model is driven by either real-time traffic data or traffic forecasts provided by a powerful ML model; other pollution source data; the city’s built environment data; and more. Meteorological inputs are drawn from up-to-date regional weather forecasts produced by an expertly tuned WRF-ARW model.
Here’s how our model works.
Our fusion model combines a regional chemical transport model with a quasi-stationary building-height-aware Gaussian model. This predictive pollutant dispersion model is driven by either real-time traffic data or traffic forecasts provided by a powerful ML model; other pollution source data; the city’s built environment data; and more. Meteorological inputs are drawn from up-to-date regional weather forecasts produced by an expertly tuned WRF-ARW model.
