Global Crop Data Challenge to Automate Crop Monitoring in South Africa


The United States-based nonprofit, Radiant Earth Foundation and the Western Cape Department of Agriculture in South Africa are inviting data scientists worldwide to join the Radiant Earth Spot the Crop Data Challenge. The challenge’s objective is to identify crop types in South Africa using earth observation (EO) satellite data and machine learning. 

Participants will build machine learning models to identify crop types in the Western Cape province of South Africa using training data generated by Radiant Earth, based on ground reference data collected and provided by the Western Cape Department of Agriculture.

The data science competition consists of two parallel tracks: In track 1, participants are using the as input to their model. In track 2, both are used as input. The participation awards are USD 4,000, USD 2,800, and USD 2,000 for each track’s first, second, and third prizes.

EO technologies help to understand the planet’s different elements and monitor natural and anthropogenic changes. And machine learning can be used to run predictive analyses based on the data at scale. Thus, the combination of EO satellite data and machine learning [ML] is essential for developing agricultural monitoring tools that can determine and anticipate change trajectories.

Many examples demonstrate the power of technologies, including assessing drought risks and mapping optimal soil conditions for certain crops, among other applications. In addition, satellite data can be used to build an automated agricultural monitoring system at a fraction of the cost and time that a traditional agricultural census would take.

The Western Cape province’ agricultural sector makes a significant contribution to South Africa’s GDP so that when extreme weather conditions affect it, such effects are felt by the whole country. 

The winning results of this data competition can demonstrate the potential EO data and machine learning applications have to develop an operational agricultural monitoring system and develop applications that allow for more frequent updates to monitor agricultural change trajectories in the Western province.

Radiant Earth will host a webinar on August 5, 2021, at 9 AM EST. Experts will provide technical tutorials and examples for those interested in participating in the data challenge. 

This open competition is currently running until September 5, 2021. To attend the webinar, participants can register.

About Radiant Earth

Radiant Earth Foundation is a nonprofit corporation working to empower organisations and individuals with open ML and EO data, standards, and tools to address the world’s most critical international development challenges. Radiant Earth fosters collaboration through a cloud-based open geospatial training data library, Radiant MLHub. Radiant also supports an ecosystem of practitioners to develop standards, expand interoperability around ML on Earth observation, and provide information and training to help advance the capacity of those working in the global sector using ML and Earth observation.

For more enquiries, contact  

Click here to get real time data and information on every Segments and players in the African space and satellite industry.