The SKAI isn’t the limit: How WFP uses satellite imagery and machine learning in emergencies

Overview of SKAI
SKAI is unique in having been trained with past-onset disasters that were previously tagged by manual analysts.
In the aftermath of a disaster, access to information is critical to allocate resources and reach people in need of assistance. In the photo: aerial image of Beira, Mozambique, after Cyclone Idai in 2019. Photo: WFP/INGC/Antonio Jose Beleza

Introducing SKAI

Approach: machine learning on satellite imagery

SKAI uses artificial intelligence to analyze satellite images to automatically assess damage post disasters.

Lessons learned from SKAI deployment in humanitarian operations

The destruction at Beirut’s port following a huge chemical explosion that devastated large parts of the Lebanese capital in 2020. Photo: WFP/Malak Jaafar

The way forward

Learn more

--

--

--

Sourcing, supporting and scaling high-impact innovations to disrupt hunger.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Exploring and evaluating ML algorithms with the Wisconsin Breast Cancer Dataset

Deep learning: From natural to medical images

When your target is a category, your ‘regression’ is not a regression

YOLOv3 Object Detection in TensorFlow 2.x

A wizard’s guide to Adversarial Autoencoders: Part 2, Exploring latent space with Adversarial…

5 Best Open-Source Projects That Will Teach You All You Need To Know About Best Generative…

Reduced deep neural network architecture using TF Lite and STM32 X-Cube-AI for running deep…

Content Bases Image Retrieval(CBIR)

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
WFP Innovation Accelerator

WFP Innovation Accelerator

Sourcing, supporting and scaling high-impact innovations to disrupt hunger.

More from Medium

“Think Strategy, before Technology” — Topic Modeling example

Text2Landscape: Visualize a Text in Multiple Spaces with R

Classifying sentences: part 1 clustering sentences