up42 airbus

Satellite Image Augmentation with Generative Adversarial Networks

UP42 is looking for algorithms that leverage generative models (GANs) in the context of Earth Observation (EO) to provide new ways of performing EO analytics.

The Finalists

Discover the TOP submissions to the UP42 Airbus Challenge below. Please note, that finalists are presented in an alphabetically order of their submission title.

CloudlessEO: Cloudless, Up-to-Date, On-Demand

Zayd Mahmoud Hamdi

Cloud cover is the most challenging problem encountered in optical satellite imagery. It leads to difficulty in information extraction, as well as demand for larger constellations, higher revisit times, and larger data storage capacity.
The ultimate goal of CloudlessEO is to propose a way to increase the usability of acquisitions from optical satellites already in orbit by addressing the cloud-cover problem. CloudlessEO is interactive, on-demand, web-based software that consists of a novel generative adversarial network architecture. It exploits the synergies of SAR and optical data from Sentinel-1 and -2 to generate highly accurate synthetic optical data to fill data gaps related to to clouds and their shadows. This will allow the reliable and continuous monitoring of changes in Earth’s surface regardless of location, weather or season. Furthermore, CloudlessEO gives the user full control over the data sources and methods that are used to form cloud-free images of their areas of interest, along with metrics and suggestions to guide their decision processes.

No More Space Debris

Takehiro Ishimatsu

In recent years, space debris has become a problem. The main causes are satellites, and new ones are launched every year to get high-quality data. An effective way to reduce the debris would therefore be to reduce the number of satellites in space.

With No More Space Debris, it is possible to collect data without launching new satellites. The solution is able to generate the desired data by merging various types of data from existing satellites. For example, higher-resolution multispectral images can be generated by combining synthetic-aperture radar (SAR) images from Sentinel-1 and multispectral images from Sentinel-2 (among other data) using image fusion methods.

As the application becomes more widespread, the number of satellites that need to be launched will be further reduced. This will help reduce space debris and lead to the realisation of sustainable space development.

TreeMonitor – Affordable Tree Health and Growth Monitoring from Space

Jack-Antoine Charles

While Covid-19 has highlighted the importance of green spaces in our cities, trees have long been our best defence against rising temperatures due to climate change. Municipalities and utility companies manage hundreds of thousands of trees in their communities, incurring considerable costs in planting and pruning in the process. Enter TreeMonitor, which WEO has developed to tackle this problem by mapping tree growth, health, canopy cover, and height across entire cities. The solution relies on Copernicus Sentinel satellite data and improves its resolution using innovative machine-learning techniques. Thanks to its use of open-source data, TreeMonitor is affordable for all. This allows municipalities to optimise pruning and prevent tree losses, while utility companies can reduce the risks they face.

Want to know the winner of this year’s challenge? Then join the Space Awards via livestream on 14 December 2021. Register now for free!

The Challenge

UP42 will provide access to very-high-resolution satellite imagery from Airbus via the OneAtlas Living Library, as well as to data for all the Sentinel missions via the Sobloo platform, to develop algorithms that address challenging problems in EO, namely:

  • Unsupervised change detection. GANs can be used to generate better coregistered images via synthetic image generation.
  • Clouds and their associated shadows in optical satellite images are large obstacles for almost all land, water, and atmosphere applications.
  • Super-resolution: Increasing the resolution of satellite imagery can widen the range of objects detected from a given data set.

UP42 is calling on researchers, companies and students to develop algorithms for these types of image augmentation.

Hover the images to see before and after.

Desertification example © osir.io.
Optical image enhancement: P. Wang and V. M. Patel, "Generating high quality visible images from SAR images using CNNs," 2018 IEEE Radar Conference (RadarConf18), Oklahoma City, OK, USA, 2018, pp. 0570-0575, doi: 10.1109/RADAR.2018.8378622.

Rewards 2021

OneAtlas Prize
Voucher to access commercial satellite data from Airbus
UP42 Prize
Voucher to access all types of geospatial data and algorithms from the UP42 marketplace
Satellite Data
Possibility to access EUR 10,000 worth of commercial datasets from the Copernicus Contributing Missions in the Copernicus Data Warehouse (financial support by COM).

Additional Reward for the Overall Winner 2021

Cash Prize

EUR 10,000 if your concept gets selected as Copernicus Masters 2021 Overall Winner

Evaluation Criteria

A combination of scientific, product/business value, quality of implementation and ecological impact is taken into consideration:

Scientific value

How original and innovative is the proposed solution? Does it have original research aspects to it or not?

Product/business value

Does the proposed solution have great business and/or product value potential?

Quality of implementation

Robustness of the proposed solution: How does it deal with noisy data? What about evaluation criteria?

Ecological impact

Does the proposed solution prevent ecosystem degradation and contribute in some way to the SDGs?

About UP42

UP42 is changing the way geospatial data is accessed and analysed. The platform and marketplace bring together multiple sources of data such as satellite imagery, weather data, and more—along with algorithms to identify objects, detect change, and find patterns. Industry leaders use UP42 to inform business decisions and build scalable customer solutions. Know when and where to fertilise crops. Measure air quality and map emissions. Count cars, trucks, planes, and ships. Developers and data scientists across all industries now have access to a platform to build, run, and scale projects all in one place.

About Airbus

Airbus is a global leader in aeronautics, space and related services. In 2017 it generated revenues of EUR 59 billion restated for IFRS 15 and employed a workforce of around 129,000. Airbus offers the most comprehensive range of passenger airliners from 100 to more than 600 seats. Airbus is also a European leader providing tanker, combat, transport and mission aircraft, as well as one of the world’s leading space companies. In helicopters, Airbus provides the most efficient civil and military rotorcraft solutions worldwide. The Intelligence Programme Line within Airbus is the supplier of choice for commercial satellite imagery, C2ISR systems and related services. The company has unrivalled expertise in satellite imagery acquisition, data processing, fusion, dissemination and intelligence extraction allied to significant command and control capabilities. Based upon exclusive commercial access to Pléiades, SPOT, TerraSAR-X and TanDEM-X and PAZ satellites, DMC Constellation and third-party satellites (TripleSat constellation, KazEOSat) combined with broad applications experience, Intelligence delivers an extensive portfolio spanning the entire geo-information value chain.



António Almeida
Senior Tech Evangelist

Hall of Fame

Discover all previous winners of the Copernicus Masters!

This site uses Cookies

Please accept cookies and tracking on this site for the best experience.

If you deny the use of cookies and tracking on this site, we will save that in a necessary cookie. You will lose access to personalised content and may not have the best experience on this website.

Please see our Privacy Policy for detailed information on how we process your personal data. You can withdraw your consent at any time and demand information about your data as well as the correction, access to or deletion of it.

To protect your privacy, we block cookies and tracking scripts until you consent with the usage.

We use cookies and tracking scripts to offer additional functions, to provide social media features and to analyse our traffic. We also share information about your use of our site with our social media, advertising and analytics partners who may combine it with other information that you’ve provided to them or that they’ve collected from your use of their services. 

You are able to change or withdraw your consent anytime. 

About Cookies
Cookies are small text files that can be used by websites to make a user’s experience more efficient.
The law states that we can store cookies on your device if they are strictly necessary for the operation of this site. For all other types of cookies we need your permission. This site uses different types of cookies. Some cookies are placed by third party services that appear on our pages.
Learn more about who we are, how you can contact us and how we process personal data in our Privacy Policy.

Necessary cookies help make a website usable by enabling basic functions like page navigation and access to secure areas of the website. Also, your consent with or denial of additional cookies and tracking scripts is stored in a necessary cookie.
The website cannot function properly without these cookies.

Marketing cookies are used for personalisation and tracking users across websites and devices. These cookies help us to display relevant content and ads for the individual user.

Marketing services used on this site:
On this site, we use cookies from:

  • Mautic

Tracking cookies help us to better understand the behaviour of our visitors. We track your interaction on this and across other websites and devices to improve the user’s experience on our site.

Tracking services used on this site:

  • Mouseflow
This site uses Cookies

Please choose:



If you deny, we will save this information in a necessary cookie and accept your wish.

Get in Touch!

Let us know how we can help you!

Anwendungszentrum GmbH Oberpfaffenhofen (AZO)

Ines Kühnert
Head of Galileo & Copernicus Competitions
+49 8105 77277-19