AI model maps building emissions to support fairer climate policies
Peer-Reviewed Publication
Updates every hour. Last Updated: 18-Dec-2025 20:12 ET (19-Dec-2025 01:12 GMT/UTC)
Researchers at the College of Design and Engineering at the National University of Singapore (NUS) Urban Analytics Lab have developed an open-source AI model that maps carbon emissions from individual buildings using only publicly available data. Applied to more than 500,000 buildings across five global cities (Singapore, New York, Melbourne, Seattle and Washington DC) the model accurately identifies emission hotspots and reveals how a city’s planning history, building density, and income levels shape urban carbon footprints. The tool, which uses satellite imagery, street views, and other open geospatial data, aims to help cities design more targeted and equitable climate policies.
The COVID-19 pandemic highlighted how the same health information affects the behavior of individuals differently. A recent study revealed cultural differences in how people respond to hypothetical COVID-19 infection information at the local level. The analysis also found differences in how individual subgroups react differently to pandemic information.
The COVID-19 pandemic highlighted how the same health information affects the behavior of individuals differently. A recent study revealed cultural differences in how people respond to hypothetical COVID-19 infection information at the local level. The analysis also found differences in how individual subgroups react differently to pandemic information.
A research team has developed PlantCaFo, an advanced few-shot plant disease recognition model powered by foundation models, capable of achieving high accuracy with only a handful of training images.