Geospatial scientists at Oak Ridge National Laboratory have developed a novel method to quickly gather building structure datasets that support emergency response teams assessing properties damaged by Hurricanes Harvey, Irma and Maria. By coupling deep learning with high-performance computing, ORNL collected and extracted building outlines and roadways from high-resolution satellite and aerial images.


Access & Use Information

Public: This dataset was intended for public access and use.

Downloads & Resources

Puerto Rico Download

US Virgin Islands Download



User assumes all risk related to the use of this data. FEMA provides this data “as is” and disclaims any and all warranties, whether express or implied, including (without limitation) any implied warranties of merchantability or fitness for a particular purpose, and there are no express or implied guarantees of accuracy of the data. In no event will FEMA or any other Federal Agency be liable to you or to any third party for any direct, indirect, incidental, consequential, special, or exemplary damages or lost profit resulting from any use or misuse of this data.



Updated on October 10, 2019