Recognizing that available modeling methods to gauge urban air pollution are cumbersome and reliant on extraordinary amounts of data points, Cornell University researchers devised machine learning models to simplify the calculation of fine particulate matter. The proposed data-driven approach requires considerably fewer modeling steps and is computationally more effective.

Four machine learning models analyze traffic-related particulate matter concentrations in data gathered in New York City’s five boroughs, which have a combined population of 8.2 million people and a daily-vehicle miles traveled of 55 million miles. The equations use few inputs such as traffic data, topology and meteorology in an artificial intelligence algorithm to learn simulations for a wide range of traffic-related, air-pollution concentration scenarios.

Instead of focusing on stationary locations, the method provides a high-resolution estimation of the city street pollution surface. Higher resolution can help transportation and epidemiology studies assess health, environmental justice and air quality impacts.

The machine learning scheme is described in the journal Transportation Research Part D: Transport and Environment.