Skip to main content

Swedish Space Data Lab 1.0

The objective of the Swedish Space Data Lab is to increase the use of data from space for the development of society and industry and for the good of the planet. Swedish Space Data Lab, is a collaboration project between AI Sweden, the Swedish National Space Agency, Rise, and Luleå University of Technology.

Swedish Space Data Lab webinar

The purpose of this webinar is to spark an interest in the possibilities that satellite data can offer when we plan and make decisions about the built environment.

Webinar (2021-06-16) 1:32


Space data is now used in a wide range of fields. It is indispensable for weather forecasts and monitoring the climate, among other things, but it is also extremely important for forestry, agriculture and other fields in which up-to-date information about vegetation and the land surface is needed.


The Swedish Space Data Lab (former National Space Data Lab) will be a national knowledge and data hub for Swedish authorities' work on earth observation data and for the development of AI-based analysis of data, generated in space systems. The purpose is to increase the use of data from space for the development of society and industry and for the benefit of the globe. The goal is to get data, technology and methodology in place to systematically develop services and applications that use space data in the data lab.

Through the Space Data Lab, we create a national infrastructure for the exploitation of space data in order to increase the possibilities of developing smart and effective AI solutions for everything from storage of space data to how you manage constellations of satellites in orbit.

The users of the data lab will be primarily public authorities with responsibility for civil, environmental and natural resources.

A national resource for Satellite data

The Space Data Lab uses the Open Data Cube (ODC) platform which is an open-source project for geospatial data analysis that organizes the data into an efficient database structure and has Python-based API for querying data. ODC support third-party tools like NumPy, Matplotlib, Pandas, Shapely, TensorFlow, and PyTorch and allows for Space data science using popular Jupyter notebooks web-based interactive computational environment that mixes code, documentation, mathematical mark-up and images.

The Open Data Cube contains Copernicus data, primarily Sentinel-2 as of today but will over time facilitate Sentinel-1 and Sentinel-3 and potentially additional data sources. Sentinel-2 data samples 13 spectral bands: four bands at 10 metres, six bands at 20 metres and three bands at 60 metres spatial resolution. The satellite's high revisit frequency over Swden provides new data every 2-3 days. The data is designed to be modified and adapted by users interested in thematic areas such as:

  • Spatial planning
  • Agro-environmental monitoring
  • Water monitoring
  • Forest and vegetation monitoring
  • Land carbon, natural resource monitoring
  • Global crop monitoring

The users of the data lab will be primarily public authorities with responsibility for civil, environmental and natural resources, but the data lab will over time be available to everything from large forestry companies to individual farmers and private persons.

The Space Data Lab mission

  • Make space data easily accessible and contribute to innovations and applications based on space data 
  • Make data, processing capacity, software platforms & tools and methodology available to lower the threshold
  • Enable systematic development of services and applications based on space data
  • Create new possibilities – based on a real-time, true situational awareness
  • Increase the pre-requisites for developing countries as well as technically advanced countries


The Swedish Space Data Lab project is partially financed by Vinnova and coordinated by AI Sweden in cooperation with the Swedish National Space Agency, RISE, and Luleå University of Technology. The project is coordinated by AI Sweden. 

Reference group: Skogsstyrelsen, SGI, SMHI, Jordbruksverket, Lantmäteriet, SSC and Naturvårdsverket.

Project period: 20190603-20210602

Project deliveries and status updates

Data Analysis of Earth Observation Data From Copernicus Satellites

Data Analysis of Earth Observation Data From Copernicus Satellites

The following report covers the use of Earth Observation data from Copernicus satellites combined with AI for the purpose of monitoring drought. The report includes a brief introduction to the concept of Open Data Cubes, a description of the Sentinel and Landsat satellites and their data, especially Sentinel-2, and a presentation of the SSDL. It also describes common applications of satellite data. The results obtained are promising, even though further work has to be done on the scalability of the method.

Illustrations of three people

Swedish Space Data Lab personas

In 2019 The Swedish Space Data Lab conducted a user study to try to understand who our users are and how we can develop the lab to best serve them. At the outset of the study, we decided to make a distinction between our beneficiaries or customers who make decisions to adopt satellite data and related technologies, and users who work hands on the satellite data. The study was conducted in two phases; phase 1 to understand our beneficiaries, followed by phase 2 to understand the users. 

The first phase was designed as a persona development study, by reaching out to our reference group members and pilot leaders and conducting 10 in-depth interviews that informed our personas. A common representation of personas is using the resume format, but it is important to note that they represent beneficiary attributes and behaviors rather than job descriptions (indeed, they may both overlap).

Data cube for climate adoption - Lake Vänern

Data cube for climate adoption - Lake Vänern

This pilot has focused on the state of Lake Vänern with respect to water levels, vegetation, and green regeneration. As increasing numbers of open beach areas are becoming overgrown with small trees and bushes, we need to monitor how fast and where overgrowth is becoming a problem in order to identify the locations that need to be maintained.

By using the satellite data from the data cube, the pilot can show how the changes occur over time. Combined with machine learning it is possible to train the application in how to recognize areas that will soon become overgrown.

Working group: Västra Götalands länstyrelseSwedish National Space AgencyRise and Luleå University of Technology. The pilot is developed in collaboration with Metria.

A forest with autumn leaves on the ground

Data cube for climate adoption - Mälardalen

The pilot focuses on measuring ground humidity to predict forest fires, which would have been useful during the summer of 2018 when large areas of forest in Västmanland were destroyed by fire. This is essential in view of the fact that the number of days with low ground humidity and a consequential high risk of fires is likely to increase in the future because of climate change.

The pilot that has been developed aims to identify potential areas where there is a risk of fires and, for example, announce outdoor grilling bans in good time, and increase water reserve reservoirs. It also allows us to track the damage that is caused by fires. The primary users of the application will be Västmanland County administrative board and insurance companies as a basis for customer risk assessment.

Working group:  Rise and Västmanland county administrative board

More on this topic:

Image of the Earth taken from space with a satellite in the corner
Edge learning has the potential to revolutionize the development of AI for space applications and AI...
An image displaying predicted cloud thickness
The National Space Data Lab 2.0 (SDL2.0) is a collaborative project led by AI Sweden, RISE, Luleå...
The European Space Agency (ESA) and AI Sweden have signed a letter of intent to establish a space...


A picture of Vinutha Magal Shreenath
Vinutha Magal Shreenath
Senior Data Scientist
+46 (0)73-152 10 98
Chiara Ceccobello
Chiara Ceccobello
Data Scientist