Innovative Approach to Urban Planning
Researchers at the University of Toronto have developed a groundbreaking method that utilizes artificial intelligence (AI) and Google Maps’ Street View images to extract detailed information about buildings, such as their age and floor area. This additional data can then be used to assess building stock, construction material flows, and embodied greenhouse gases – estimates of the emissions generated by the production and transportation of goods.
The study, published in the Journal of Industrial Ecology, marks a significant breakthrough in the field. “This is the first paper we know of where people took a picture that shows you the front of the building and then predicts things that you can’t see in the picture,” says Shoshanna Saxe, an associate professor in the department of civil and mineral engineering. “My motivations were focused on embodied carbon research, but this will be useful for various applications, including understanding water usage for future planning or resilience assessments.”
The method offers a cost-effective way to generate large-scale building data, with the researchers spending approximately $1,000 on photos to obtain data that would otherwise cost millions of dollars. The AI was trained to estimate building attributes based on exterior images, achieving 70% accuracy for age prediction and 80% accuracy for floor area prediction.
“Being able to assess the exteriors allows a sort of educated guess at the interiors and the kinds of uses the occupants put on local infrastructure,” explains co-author Alex Olson, a senior AI researcher. “It gives a strong estimate of the resources used in building, maintaining, and operating the buildings.”
The insights gained through this approach cannot be derived from maps or building plans alone. “You need to see structures,” Saxe emphasizes. “Knowing the age of the building is crucial, as it tells you what materials were used and what embodied carbon there is.”
This innovative technique has the potential to help urban planners better understand cities’ resource needs and prioritize future infrastructure projects. “You want to understand where there’s underused resources or infrastructure in your city,” Olson notes. “This method accurately describes the current situation, allowing us to use the data for planning our resource uses and future developments.”
