Researchers at the Plymouth Marine Laboratory in the U.K. have developed an artificial intelligence system that can identify sea plastic in imagery taken at varying wavelengths of light.
The team trained the system using images from the European Space Agency's Sentinel-2 satellites, which record visual information at multiple wavelengths along the electromagnetic spectrum.
The algorithm can distinguish floating pieces of plastic greater than five millimeters in size (called macroplastics) from sea foam and seaweed with 86% accuracy.
The researchers tested the system on four sites off the coasts of Canada, Ghana, the U.K., and Vietnam.
They plan to expand the monitoring system over open oceans, where currents move less rapidly.
From New Scientist
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found