Super-Resolution

Sentinel-2Super-Res
Nakuru, Kenya
Nakuru, Kenya
Nakuru, Kenya
Nakuru, KenyaSydney, AustraliaNew Orleans LocksMaisse, FranceLos Angeles, CaliforniaDry Tortugas, Florida
Super-Resolution allows a very high level of detail compared to Sentinel-2 images.

Introduction

Global low resolution satellite imagery is available on a weekly basis, but public high resolution imagery is very limited. High resolution imagery can help with tasks such as post-disaster building damage estimation and crop type classification, but since it is available infrequently, we cannot scale up promising AI methods to automate these tasks, especially in developing countries where it is needed most.

We have trained super resolution models to generate high resolution imagery on a global scale.

The Satlas Map allows users to explore globally generated high resolution imagery for 2023.

Frequent Updates

Super-Resolution is generated from 2023 Sentinel-2 imagery, and is sometimes more up-to-date than Google Maps. This example of Cebu City, Phillippines shows evidence of coastal infrastructure in both Sentinel-2 and the generated Super-Resolution but not in the Google Maps image.
2023 Sentinel-22023 Sentinel-2 image
Google Maps (outdated)Google Maps image (outdated)
2023 Satlas Super-Res2023 Satlas Super-Resolution

Change Over Time

With increased resolution and cloud-free views, Super-Resolution's enhanced imagery makes it easier to see change over time.
Sinop Dam in Brazil filling up, including removal of trees and dirt to build pathways for the water.

Super-Resolution Model

The Super-Resolution imagery is generated using an adaptation of the ESRGAN model. It is trained on pairs of corresponding Sentinel-2 (low resolution) and NAIP (high resolution) images. Our model inputs a sequence of between 6-18 Sentinel-2 images for each location.
Super-Resolution ModelSuper-Resolution Model Architecture
The training and inference code is open source and can be found at our Github. We note that AI models are not perfect and there are instances where the super-resolution outputs are incorrect.