Spot the Crop Data Challenge focuses on using satellite imagery and machine learning for automating South African crop identification

Information from Radiant Earth Foundation

Radiant Earth Foundation’s Spot the Crop Data Challenge seeks entrants to predict crop types in the Western Cape, South Africa using satellite image time-series from 5 July to 6 September.

Participants are challenged to build machine learning models to identify crop type classes using training data generated by Radiant Earth, based on ground reference data collected and provided by the Western Cape Department of Agriculture, South Africa, for a chance to win up to $4000 in cash prizes.

The goal of this challenge is to showcase the potential of Earth observation data and machine learning applications to develop an operational agricultural monitoring system, particularly for regions without dependable monitoring systems in place.

The competition, hosted on the Zindi platform and running from 5 July to 6 September 2021, consists of two tracks:

  • Track 1: using time-series Sentinel-2 multi-spectral data as input to in a model – enter this track here:
  • Track 2: using both Sentinel-2 and Sentinel-1 (radar) data as model inputs – enter this track here:

The competition is organised in collaboration with the Western Cape Department of Agriculture in South Africa, with support from the GIZ FAIR Forward program, Computer Vision for Global Challenges, and Descartes Labs.