Scientists at the Johns Hopkins University Applied Physics Laboratory, in Laurel, have leveraged artificial intelligence and machine learning to produce estimates for road transportation emissions of the top 500 emitting cities worldwide.
After estimating that there are 1.4 billion motor vehicles in the world, the APL remote sensing and computer vision team measured the greenhouse gases from these vehicles by pulling signatures of emissions from visual satellite data, essentially making the invisible visible. They then looked at existing emissions data, correlating it with those images and teasing out anything they could with neural networks.
Then the team mapped out land use and structures, using satellite data from different times of day to understand and differentiate between similar-looking structures, like office buildings versus apartment complexes.
“In particular, we were able to estimate the average annual daily traffic on individual road segments in urban areas and combined this with localized estimates of vehicle emissions factors to produce a total emissions estimate,” said Marisa Hughes, assistant program manager for Environmental Resilience in APL’s Research and Exploratory Development Mission Area.
“The ability to calculate emissions per road segment provides an unprecedented level of detail and global coverage,” said Hughes, who helps manage APL’s climate change efforts. “The combination of ML-predicted road activity, along with region-specific emissions factors data, creates automated, accurate, global, timely and actionable road transportation greenhouse gas emissions estimates.”