ESA title

Highly reusable AI-based cloud screening for general EO missions

Space Segment
  • Payload
  • Platform
  • Product Development
SKAISEN is an AI-driven cloud screening solution designed to support Earth Observation missions. Regardless of the sensor and processing unit integrated onboard the satellite, SKAISEN optimizes data downlink by effectively filtering out cloudy pixels directly onboard the satellites. By leveraging advanced AI algorithms, SKAISEN eliminates up to 70% of noisy data, thereby significantly reducing mission costs while ensuring data quality
Objectives of the Product

Earth Observation missions generate a vast amount of data. Particularly, missions with hyper/multispectral cameras commonly collect hundreds of gigabytes per day. Up to 70% of this data consists of cloudy pixels lacking any added value and thus cannot be further utilized by the end users. SKAISEN addresses this challenge by helping Mission Owners, System Integrators, Payload Developers and Mission Operators mitigate these financial losses by identifying cloudy pixels directly onboard the satellites before the downlink costs occur. By leveraging the AI-driven SKAISEN solution, customers can significantly reduce their costs associated with the ground segment infrastructure while maximizing the valuable data downlink. SKAISEN is designed to be highly reusable and independent of the sensor and processing unit selected for the mission. This ensures its availability for any Earth Observation mission and its highly competitive price.

Customers and their Needs

The key customer segments targeted by SKAISEN are Mission Owners, System Integrators, Payload Developers and Mission Operators.

The main pains of these customers in data access are:

  1. Data downlink is wasted with unusable data instead of actionable information
  2. Wasted downlink resources increase latency and delay the access time to valuable data for end-users
  3. Undesired high costs for ground segment infrastructure caused by unusable data transfer
  4. Lower profit for data providers caused by downloading noisy data, which cannot be sold and has no added value
  5. Long lead times and high prices for custom onboard data processing solutions, since there is a low number of COTS options
  6. Time and cost-consuming data analysis by a mission operator

SKAISEN aims to bring a customer-friendly solution for acquiring valuable data only, reduce mission costs and increase mission profits.

Targeted customer/users countries

Mission Owners, System Integrators, Payload Developers and Mission Operators all over the world, focusing on Earth Observation missions.

Product description

The product SKAISEN is an onboard software solution designed to estimate cloud coverage on EO imagery. The key components of the product are:

  1. Dataset – composed of open and commercial data as well as data from the target mission (if available)
  2. Cloud screening model(s) – to predict cloud pollution
  3. On-board software – software or hardware implementation of the cloud screening model optimised for the specific embedded processor or FPGA target

The role of SKAISEN in the context of the overall satellite system is a pluggable onboard software integrated into the data pipeline of the satellite, with the aim to provide additional information to the platform and mission operator. The product has no impact in terms of data modification or deletion. This decision remains with the mission operator or other responsible person.

Added Value

The principle of how SKAISEN works is described in the picture below. After collecting imagery by the satellite, SKAISEN processes the data and extracts valuable data only, which is then transported to Earth. This approach optimizes downlink by minimizing unnecessary data transmission.

There are several views on how to optimize data transfer to Earth. The most common approach is processing data before transportation. There are already available onboard data processing products in the market. The difference between them and SKAISEN lies in their reusability.

SENSOR INDEPENDENCE: While the existing products are operable, e.g., in the visible spectrum, SKAISEN is sensor independent, regardless of whether the optical sensor operates as monochromatic, RGB, multispectral or hyperspectral. The flexibility in choosing the right camera for the mission remains for the customer.

DPU INDEPENDENCE: Whether a single software solution or the entire payload is needed, SKAISEN offers both. SKAISEN is available in three different configurations, and there is no limitation in choosing the hardware part.HERITAGE: Operating in the space segment means understanding the emphasis placed on flight heritage. SKAISEN demonstrated its first capabilities during the VZLUSAT-2 mission in the summer of 2022. Additionally, three confirmed missions for SKAISEN are scheduled for 2024

Current Status

The activity kicked off in November 2023.

Prime Contractor Company
Zaitra s.r.o.
Czech Republic Flag Czech Republic
Constellr GmbH
Germany Flag Germany
Fraunhofer Institute for High-Speed Dynamics, Ernst-Mach-Institut, EMI
Germany Flag Germany
SatRev S.A.
Poland Flag Poland
Contractor Project Manager
Rado Pitoňák
Plynárenská 499/1, 602 00 Brno, Czech Republic

ESA Technical Officer
Piera di Vito

Current activities