Researchers at the University of Notre Dame developed an AI tool, called EcoSphere, to help make cities greener. They published their findings in npj Urban Sustainability.
Credit: Barbara Johnston/University of Notre Dame
Ming Hu, associate dean for research, scholarship and creative work, School of Architecture, University of Notre Dame
The researchers aim to help urban policymakers make informed decisions about sustainable building practices. “Our goal is to develop tools that assess the carbon emission reduction and mitigation potentials of the built environment infrastructure, both through renovation and improved new construction,” said Ming Hu, the associate dean for research, scholarship and creative work in Notre Dame’s School of Architecture.
The hidden impact of embodied carbon
Embodied carbon is greenhouse gas (GHG) emissions from the manufacturing, transportation, installation, maintenance and disposal of building materials. It makes up a large part of global GHG emissions; embodied carbon accounted for 37% of global energy-related carbon dioxide emissions in 2020, according to the UN.
In their study, researchers found that the most effective way to reduce embodied carbon is to focus on renovating and improving buildings’ lifespans, rather than undertaking new construction. According to the study, new construction produces up to 7,500 times more carbon dioxide than renovation. The study also indicated that buildings with a 50-year lifespan have three times more embodied carbon than buildings with an 80-year lifespan.
These results came from over 350,000 simulated scenarios, which drew data from more than 1 million Chicago buildings. The researchers transformed these simulations into an AI-powered platform called EcoSphere, with results to be published in Automation in Construction next month.
A map produced by EcoSphere showing the median year built of buildings in Chicago. Credit: Notre Dame University
Exposing the impact with EcoSphere
The platform combines national building datasets, embodied carbon data, Google Street View, satellite imagery and machine learning to generate graphics that visualize emissions data. The graphics are presented in an interactive dashboard, enabling users to dive deeper into simulation results. The team hopes this will help policymakers and non-experts understand their city’s carbon footprint.
EcoSphere uses AI to gather high-resolution building data and categorizes the buildings into archetypes to allow for detailed simulations. The results of the simulation are presented in three optimistic scenarios, three pessimistic scenarios and three most probable scenarios. The study to be published in August will cover case studies of the platform in Chicago and Indianapolis.
“Together, these studies show how detailed data and smart software can help empower city planners to make informed decisions for a greener future,” Hu said.
