Engineering students dig through snowplow data to gauge Toronto’s response to winter storms

Last January, as 55 centimetres of snow blanketed Toronto over a period of just 15 hours, the city's snow-clearing fleet appeared to struggle to keep up. But was it actually different than other storms, or did it just seem that way? For three students in the University of Toronto's Faculty of Applied Science & Engineering who were taking "Data Science for Engineers," a graduate-level course taught by Sebastian Goodfellow, an assistant professor in the department of civil and mineral engineering, it was the perfect case study to test out their new number-crunching skills.  "There was a lot of news coverage at the time saying the city had poorly responded," says  Katia Ossetchkina , a master's candidate. "We wanted to see if there was a way to analyze the movement and dispatch of snowplows and salt trucks across the city." Real-time data on the locations of Toronto's more than 800 snowplows and salt trucks is publicly available during the winter months. There is even  . But the team - which also included master's candidates Thomas de Boer and Lucas Herzog - soon realized they needed more.  "There's no historic storage," says de Boer. "You can't just download it as a file, so we had to create an algorithm that would ping that web server and download the data and store it on our computer, which we could then use to build up our own historic database and do our analysis off that." By the time the team had its technique up and running, it was too late to gather data from the January storm.