On Cloud N: Cloud Cover Detection Challenge Hosted By Microsoft AI for Earth




Satellite imagery is critical for a wide variety of applications from disaster management and recovery, to agriculture, to military intelligence. Clouds present a major obstacle for all of these use cases, and usually have to be identified and removed from a dataset before satellite imagery can be used. Improving methods of identifying clouds can unlock the potential of an unlimited range of satellite imagery use cases, enabling faster, more efficient, and more accurate image-based research.

In this challenge, your goal is to detect cloud cover in satellite imagery to remove cloud interference. The challenge uses publicly available satellite data from the Sentinel-2 mission, which captures wide-swath, high-resolution, multi-spectral imaging. For each tile, data is separated into different bands of light across the full visible spectrum, near-infrared, and infrared light. Data is shared through Microsoft's Planetary Computer.

Competition End Date:

Feb. 7, 2022, 11:59 p.m. UTC

Place Prize Amount
1st $10,000
2nd $6,000
3rd $4,000

How to compete

  1. Click the "Join the competition" button on the sidebar to enroll in the competition.
  2. Get familiar with the problem through the about page and problem description. You might also want to reference additional resources available on the about page and the user forum.
  3. Download the data from the data tab.
  4. Create and train your own model. The benchmark blog post is a good place to start.
  5. Package your model files and inference into submission.zip based on the code submission format page.
  6. Click “Submit” in the sidebar followed by “Make new submission”. You’re in!

We will generate predictions for the evaluation dataset and score your submission in a containerized execution environment.

This challenge is sponsored by our friends at Microsoft AI for Earth.

With support from Radiant Earth Foundation

Image courtesy of NASA Earth Observatory, Jeff Schmaltz, LANCE/EOSDIS MODIS Rapid Response Team at NASA GSFC.