{"slug":"airbus-defence-and-space-uses-deep-learning-and-google-cloud-to-deliver-real-time-satellite-imagery","url":"https://findausecase.com/use-cases/airbus-defence-and-space-uses-deep-learning-and-google-cloud-to-deliver-real-time-satellite-imagery","title":"Airbus Defence and Space Uses Deep Learning and Google Cloud to Deliver Real-Time Satellite Imagery","description":"Airbus Defence and Space's Intelligence business line rebuilt its satellite imagery platform, OneAtlas, on Google Cloud, using Kubernetes Engine, Cloud Pub/Sub, Cloud Storage and Cloud Datastore to serve more than 1,200 customers in over 100 countries. Airbus trained TensorFlow deep learning models to recognize cloud cover, cutting its cloud-detection error rate from 11% to 3%, and the new platform reduced the time for customers to access satellite imagery from hours to less than half a second while adding millions of square kilometers of imagery weekly.","company":"Airbus Defence and Space","industry":"Aerospace & Defense","country":"France","aiCapabilities":["Computer Vision"],"technology":["Google Kubernetes Engine","Cloud Pub/Sub","Cloud Datastore","Cloud Storage","TensorFlow"],"deployment":"Public Cloud","problemStatement":"Airbus Intelligence's existing satellite imagery solution could not speed up production and delivery of image and data products fast enough to meet growing customer expectations; customers had to choose images from a catalogue and wait several hours to receive them, and the specialized imagery required customers to have significant technical capability to use it.","solutionApproach":"Airbus built a new platform called OneAtlas on Google Cloud, using Google Kubernetes Engine to orchestrate image-processing workloads and scale compute up and down with demand, Cloud Pub/Sub for messaging, Cloud Datastore and Cloud Storage to hold and serve imagery and data, and trained deep learning algorithms in TensorFlow to automatically recognize cloud cover in satellite imagery.","evidence":{"band":"high"},"sourceUrl":"https://cloud.google.com/customers/airbus","dates":{"publishedAt":"2026-10-07T05:46:35.731Z","publishedAtSource":"pipeline","updatedAt":"2026-10-07T05:46:35.731Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/airbus-defence-and-space-uses-deep-learning-and-google-cloud-to-deliver-real-time-satellite-imagery. Bulk republication requires permission."}