acm-header
Sign In

Communications of the ACM

ACM TechNews

Deep Learning Quickly Finds Structures Affected by Lava


View as: Print Mobile App Share:
Hawaii's Kilauea volcano erupting.

Officials at the U.S. Federal Emergency Management Agency have been getting insight into the buildings and infrastructure affected by the stream of molten rock emanating from Hawaii's Kilauea volcano with the help of Oak Ridge National Laboratory in Tenne

Credit: POLITICO Tube

Researchers at Oak Ridge National Laboratory (ORNL) are working with the U.S. Federal Emergency Management Agency to provide insight into the buildings and infrastructure affected by the stream of lava erupting from the Kilauea volcano in Hawaii.

The team is analyzing satellite images of the area around the volcano and combining that information with property ownership data, a process that allows officials to determine which buildings have been damaged and whether people are evacuating ahead of the lava's approach.

The researchers sharpen and adjust satellite images for perspective, selecting segments to help train a convolutional neural network.

ORNL researcher Melanie Laverdiere says, "With deep learning, we now have the power to create one model for a county or a state or a region, something that can be generalizable to a large geographic area."

From Government Computer News
View Full Article

 

Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account