AI Offers Hope on Dangerous Ground
Researchers Pinpoint Unexploded Shells, Rockets in Ukraine’s Agricultural Regions
By Chris Carroll
Illustration by Charlene Prosser Castillo
Indiscriminate shelling along the front lines of Russia’s invasion of Ukraine has seeded farm fields and towns with untold numbers of unexploded munitions. Now University of Maryland geographical sciences researchers are combining satellite imagery with deep learning, a form of artificial intelligence (AI), to prevent a deadly harvest.
Their system has mapped about 2.5 million artillery strike craters in a 500-mile arc across the country’s agricultural south and east—data that Ukrainian and international demining organizations can use to prioritize the most dangerous areas for cleanup.
An estimated 10 to 30% of Soviet-era artillery shells that both sides have used fail to explode, says Associate Professor Sergii Skakun, who co-authored a paper on the system in the journal Science of Remote Sensing—meaning nearly 1 million unexploded shells might be lying across the region they surveyed.
A Ukrainian scientist with expertise in satellite operations to monitor agriculture and environmental conditions, Skakun says that farmers in the region face a particularly frightening choice between bankruptcy and injury or death.
“You can’t wait until it’s safe (to plant),” he says. “But you are in danger of being blown up in your tractor.”
Anecdotal evidence suggests incidents involving unexploded ordnance (UXO) occur on an almost daily basis, says co-author Erik Duncan, a faculty specialist who studied unexploded artillery on the ground in Ukraine.
From the Balkans to the Middle East to Southeast Asia, global estimates of yearly civilian deaths from UXO range from 10,000 to 20,000, including many children, according to UNICEF, the United Nations’ child welfare division. It had already classified Eastern Ukraine as one of the most mine-plagued spots on Earth as early as 2017, years before the full-scale invasion that Russian President Vladimir Putin launched in early 2022.
Duncan trained the deep learning AI system (which mimics certain human cognitive functions) to find artillery craters in high-resolution commercial satellite imagery. “You can certainly see the craters and label them manually if you want, but it’s a pretty big ask if you wanted to zoom out and cover 40,000 square kilometers and determine what’s been hit and what hasn’t been hit,” he says.
The researchers are now planning a finished platform that agencies can use, Skakun says. “We can provide this valuable information to the (demining) operators and the government they couldn’t get by themselves, and help save lives.”
Leave a Reply
* indicates a required field