�山ǿ��

A team of researchers from the department of civil and mineral engineering in the University of Toronto’s Faculty of Applied Science & Engineering are wielding machine learning to understand where cycling infrastructure should be located in order to benefit the most people.

In a , researchers used novel computing approaches to compare two strategies for expansion of protected bike lanes – using Toronto as a model.

“Right now, some people have really good access to protected biking infrastructure: they can bike to work, to the grocery store or to entertainment venues,” says post-doctoral fellow and lead author Madeleine Bonsma-Fisher, who previously researched interactions between bacteria and viruses before applying her data analysis skills to active transportation. “More lanes could increase the number of destinations they can reach, and previous work shows that will increase the number of cycle trips taken. 

“However, many people have little or no access to protected cycling infrastructure at all, limiting their ability to get around. This raises a question: is it better to maximize the number of connected destinations and potential trips overall, or is it more important to focus on maximizing the number of people who can benefit from access to the network?” 

To delve into the question, Bonsma-Fisher and co-authors used machine learning and optimization, a challenge that required them to explore new computational approaches.

“This kind of optimization problem is what’s called an ‘NP-hard’ problem, which means that the computing power needed to solve it scales very quickly along with the size of the network,” says Shoshanna Saxe¸ associate professor in the department of civil and mineral engineering and one of Bonsma-Fisher’s two co-supervisors alongside Professor Timothy Chan of the department of mechanical and industrial engineering. “If you used a traditional optimization algorithm on a city the size of Toronto, everything would just crash.”

To get around the problem, PhD student Bo Lin invented a machine learning model capable of considering millions of combinations of over a thousand different infrastructure projects in order to test where the most impactful places are to build new cycling infrastructure.

Using Toronto as a stand-in for any large, automobile-oriented North American city, the team generated maps of future bike lane networks along major streets, optimized according to two broad types of strategies. 

The first strategy, dubbed the utilitarian approach, focused on maximizing the number of trips that could be taken using only routes with protected bike lanes in under 30 minutes – without regard for who those trips were taken by. 

The second, an equity-based strategy, sought to maximize the number of people who had at least some connection to the network. 

“If you optimize for equity, you get a map that is more spread out and less concentrated in the downtown areas,” says Bonsma-Fisher. “You do get more parts of the city that have a minimum of accessibility by bike, but you also get a somewhat smaller overall gain in average accessibility.” 

This results in a trade-off, says Saxe. “This trade-off is temporary, assuming we will eventually have a full cycling network across the city, but it is meaningful for how we do things in the meantime and could last a long time given ongoing challenges to building cycling infrastructure.”

Another key finding was that certain routes appeared to be essential no matter what strategy was pursued – for example, protected bike lanes along Bloor Street West.

“Those bike lanes benefit even people who don’t live near them and are a critical trunk to maximizing both the equity and utility of the bike network. Their impact is so consistent across models that it challenges the idea that bike lanes are a local issue, affecting only the people close by,” Saxe says. “Optimized infrastructure repeatedly turns out in our model to serve neighbourhoods quite a distance away.”  

The team is already sharing their data with Toronto’s city planners to help inform ongoing decisions about infrastructure investments. Going forward, the researchers hope to apply their analysis to other cities as well. 

“No matter what your local issues or what choices you end up making, it’s really important to have a clear understanding of what goals you are aiming for and check if you are meeting them,” says Bonsma-Fisher. 

“This kind of analysis can provide an evidence-based, data-driven approach to answering these tough questions.”