Providing Open Mapping Data to Help Responders After the Beirut, Lebanon Explosion
Ecopia AI, in partnership with Maxar Technologies, has mapped a 1-kilometre radius surrounding the point of the explosion to support response efforts.
-
Date 08/07/2020
-
Partnership Maxar
-
Topic AI for Good
-
Product Global Feature Extraction
On August 4th, 2020, a major explosion devastated the city of Beirut, Lebanon. The cause of the explosion, as cited from the Prime Minister, was 2,750 metric tons of ammonium nitrate, a common chemical compound used in fertilizer and a component in mining explosives. As of August 7, at least 150 people have been killed and more than 5,000 people injured; another 300,000+ people have been displaced by the explosion. It is estimated that the explosion has caused as much as $5 billion in damage.
Ecopia.AI, in partnership with Maxar Technologies, has mapped a 1-kilometre radius surrounding the point of the explosion to support response efforts. To conduct this effort, Maxar Technologies first captured new high-resolution satellite imagery of the region and pulled pre-explosion imagery from its 110-petabyte archive. Ecopia then leveraged the pre-event imagery as an input into our proprietary artificial intelligence-based systems to rapidly generate highly accurate vector maps of the region: 2.5D building footprints and road centrelines.
August 17, 2020 Update:
Ecopia.AI, in partnership with Maxar Technologies, has generated 2D building footprints within a 10-kilometre radius surrounding the point of explosion. The dataset includes 70,613 building footprints.
To support first responder workflows with organizations like the Red Cross and other non-profits, Ecopia and Maxar are making the imagery and vector maps available under the Creative Commons Attribution Non-Commerical 4.0 license. The data can be downloaded via Maxar’s Open Data Program.
Learn more about Ecopia's mission to use AI for Good
Ready to get started?
If you're ready to leverage groundbreaking advancements in artificial intelligence, let's chat.