The Department of Defense’s Joint Artificial Intelligence Center has asked Johns Hopkins University Applied Physics Laboratory to develop an AI tool that will work to help analysts process and examine overhead imagery.
APL said Thursday its researchers aim to create a machine learning technology for disaster response organizations to monitor flooding, analyze roads and assess building damage.
Last year, APL provided imagery to help the Federal Emergency Management Agency identify North Carolina’s flooded areas in the wake of Hurricane Florence.
The lab used deep learning algorithms in efforts to process satellite-based images into visuals that include information about flood water segments. The algorithms also helped FEMA detect other items of concern such as roads, bridges, buildings and vegetation, APL noted.
“We are excited to bring this technology capability to the analysts, since a lot of this type of work right now is done by hand,” said software engineer Beatrice Garcia, project manager for humanitarian assistance and disaster relief at APL.