Return to site
Return to site

Locating Refugee Presence using Satellite Imagery

Lebanon

Client Brief

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

Solution

  • Use advanced deep learning methods to identify the tents scattered across Lebanon on high-resolution satellite imagery
  • Check the findings in the field with local consultants
  • Based on this identification, follow the evolution (where ? how many ?) of the informal refugee settlements and assess their access to infrastructure (roads, markets)

Results

  • Training of a Convolutional Neural Network with roughly 3,000 images distributed between tents/not tents areas
  • Testing the algorithm on a batch of 1,000 other labeled images
  • Accuracy: 90% of the tents are correctly identified
Previous
Rural Markets Detection for Financial Inclusion
Next
Detecting Rural Habitat using Satellite Imagery
 Return to site
All Posts
×

Almost done…

We just sent you an email. Please click the link in the email to confirm your subscription!

OK