The availability of large amounts of satellite imagery data through the European Copernicus project and open source platforms like the OpenDataCube (ODC) greatly bolsters the opportunities to apply classical machine learning and deep learning algorithms. These models can be employed to meet many challenges. One challenge often arising in the analysis of satellite data is that of cloud occlusion. Depending on the time of year and the location of the Area of Interest (AoI) clouds can fully or partially cover the image and hamper the analysis. However, there are many methods available for estimating missing data.
There are two parts to this challenge:
- Part 1 of this challenge is to use the Swedish satellite data (provided through ODC) to train a model that is able to estimate certain statistics for an occluded area based on the information from the surrounding area, as reliably and accurately as possible.
- Part 2 of this challenge is to develop a viable business case for the solution developed or from techniques utilized to develop the solution. Team will be provided a framework to follow for this aspect of the challenge.
The winning teams will be decided by a jury and they will receive the following:
- SEK 12,000 for the 1st place team
- 8000 SEK for the 2nd place team
- An optional coaching session to further develop the business case of the developed solution with ABI or Innovatum Startup. The opportunity to have solution adopted by the Space Data Lab
Please make sure to register before February 9th at 24:00.
More information here: