, also used visual identification and showed increases in particulate matter related to coal trains.
The technique used in Richmond could also help monitor other sources of pollution that have historically been difficult to track. Vallejo, a waterfront city about 30 miles northeast of San Francisco, has five oil refineries and a shipyard within a 20 mile radius, making it hard to discern a pollutant’s origin. Some residents hope more data may help attract regulatory attention where their own concerns have not.
The team planted new cameras and programmed them to take a photo each minute. After months of collecting enough images of the tracks, UC Davis students categorized them into groups—train or no train, day or night—using Playstation controllers. The team created software designed to play like a video game, which sped up the process, Spada said, by allowing the students to filter through more images than if they simply used a mouse or trackpad to click through pictures on a computer.
Nicholas Spada holds a piece of graphite tape used to collect dust samples in the field. Spada and his colleague Bart Ostro didn’t originally envision using AI in their coal train study in Richmond. But, Spada said, using the technology was a “game changer.”Hanna Best, former student of Spada’s, classifies train images with with the help of a Playstation controller. Best classified hundreds of thousands of images as a part of a team of UC Davis students who helped train the AI model.