Revolutionary Neural Network Speeds Up Large Iceberg Mapping 10,000 Times Faster Than Humans

The University of Leeds researchers have developed a neural network that claims to be able to map a large iceberg in just 0.01 seconds. Tracking the locations of large icebergs manually is possible, but it’s not feasible to track changes in their area and thickness. “Giant icebergs are important components of the Antarctic environment,” Anne Braakmann-Folgmann, lead author of a paper on the neural network, stated. The researchers trained an algorithm called U-net using imagery captured by the ESA’s Copernicus Sentinel-1 Earth-monitoring satellites. The new model is said to surpass previous attempts at automation, being 10,000 times faster than humans at mapping icebergs.