Satellite Photos and AI Combine to Reveal Secret Roads Damaging Rainforests
Scientists used AI to analyze satellite images and find the secret, unmapped roads that are destroying rainforests.
In some regions, roads, both legal and illegal, are unmapped — with road-mapping studies in the Brazilian Amazon and Asia-Pacific regularly finding that the true length of all roads was nearly 13 times higher than the length that has been reported in government or road databases.
According to a study published this week that was reported by Phys.org, the Earth is experiencing an unprecedented wave of road building — with some 25 million kilometers (15.5 million miles) of new paved roads expected by 2050.
“Roughly 90% of all road construction is occurring in developing nations including many tropical and subtropical regions of exceptional biodiversity,” the study’s co-author Professor Bill Laurance tells Phys.org.
“By sharply increasing access to formerly remote natural areas, poorly regulated road development triggers dramatic increases in environmental disruption due to activities such as logging, mining and land clearing.”
AI Could Help World’s Most Environmentally Critical Areas
However, Laurance says that AI has emerged as a new tool for finding the unmapped roads that bring environmental destruction to wilderness areas and rainforests.
Laurance and his fellow researchers trained three machine-learning models to automatically map road features from high-resolution satellite imagery covering rural, generally remote, and often forested areas of Papua New Guinea, Indonesia, and Malaysia.
“Traditionally, road mapping meant tracing road features by hand, using satellite imagery. This is incredibly slow, making it almost impossible to stay on top of the global road tsunami,” Professor Laurance tells Phys.org.
The scientists were able to use the AI algorithm to analyze satellite images and uncover the unknown roads that lurked in these rainforest areas.
“This study shows the remarkable potential of AI for large-scale tasks like global road-mapping. We’re not there yet, but we’re making good progress,” Laurance says.
“Proliferating roads are probably the most important direct threat to tropical forests globally.
“In a few more years, AI might give us the means to map and monitor roads across the world’s most environmentally critical areas.”
Image credits: Header photo via “Mapping Remote Roads Using Artificial Intelligence and Satellite Imagery” published in Remote Sensing.
