Locating Refugee Presence using Deep Learning on Satellite Imagery

Lebanon


Context and Issues

Because of war, thousands of Syrians have fled their homeland to seek refuge in Lebanon. Most of them live in informal camps. Locating them and estimating their number is critical to the international community and actors wishing to support them


Solution

The team used advanced deep learning methods to identify the tents scattered across Lebanon on high-resolution satellite imagery (accuracy of 90%).

Masae leveraged Altai’s consultant network to verify the findings on the field.


Based on this identification, the team followed the evolutions of the camps and assess their access to infrastructure (roads, markets, tents).