Researchers have used artificial intelligence (AI) to detect Vietnam War-period bomb craters in Cambodia from satellite photographs—with the hope that it can assist find unexploded bombs.
The brand new method increased true bomb crater detection by over 160% over customary methods.
The model, combined with declassified U.S. military records, suggests that 44% to 50% of the bombs in the area studied may stay unexploded.
As of now, attempts to seek out and safely remove unexploded bombs and landmines—referred to as demining—has not been as efficient as needed in Cambodia, said Erin Lin, assistant professor of political science at The Ohio State University.
She cites a recent UN-commissioned report that has criticized the Cambodian nationwide clearance company for presenting an image of speedy progress by focusing on areas at minimal or no danger of having unexploded mines. The report urges a shift in focus to more excessive-danger areas.
Lin co-led the study with Rongjun Qin, assistant professor of civil, environmental, and geodetic engineering at Ohio State. The research features in the journal PLOS One.
The researchers began with a business satellite tv for pc picture of a 100-sq.-kilometer space close to the city of Kampong Trabaek in Cambodia. The world was the goal of carpet bombing by the U.S. Air Drive from Could 1970 to August 1973.
The researchers used artificial intelligence referred to as machine learning to review6 the satellite photos for proof of bomb craters.