Radiant Earth Spot the Crop Challenge
$8 800USD
Based on time-series of Sentinel-2 satellite images can you classify crop types in South Africa?
247 data scientists enrolled, 16 on the leaderboard
ForecastSatelliteSDG2
South Africa
5 July—5 September
Ends in 1 month

This competition is organised into two parallel tracks. For this track, participants are asked to only use time-series of Sentinel-2 multi-spectral data as input to their model. For the other track, see Radiant Earth Spot the Crop XL Challenge.

Watch an introduction to the challenge and technical tutorial here

The agricultural sector makes a substantial contribution to GDP and livelihoods across the developing world. However, regular and reliable agricultural data remains difficult and expensive to collect on the ground. As a result, policy-makers usually don’t have access to updated data for implementing policies or supporting farmers.

Earth observation satellites provide a wealth of multispectral image data that can be used for developing agricultural monitoring tools. These tools support farmers and policy-makers across Africa and the developing world.

The objective of this challenge is to use time-series of Sentinel-2 multi-spectral data to classify crops in the Western Cape of South Africa. Your challenge is to build a machine learning model to predict crop type classes for the test dataset. The training dataset is generated by the Radiant Earth Foundation team, using the ground reference data collected and provided by the Western Cape Department of Agriculture.

The competition and data preparation are made possible with support by the convening sponsor, GIZ FAIR Forward, which is implemented by Deutsche Gesellschaft für Internationale Zusammenarbeit (GIZ) GmbH on behalf of the German Ministry for Economic Cooperation and Development (BMZ).

To be eligible for cash prizes, winners will release their top solutions under an open source license for ongoing use and learning. The winners’ solutions will be shared in a well-organized code repository with proper documentation, and added to the Radiant MLHub model repository.

About Radiant Earth Foundation (radiant.earth)

Radiant Earth Foundation is a nonprofit corporation working to empower organizations and individuals with open machine learning (ML) and Earth observation 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 development sector using ML and Earth observation. Visit Radiant Earth on Twitter, LinkedIn, Medium, and GitHub.

About GIZ FAIR Forward (toolkit-digitalisierung.de/en/fair-forward)

The “FAIR Forward - Artificial Intelligence for all” initiative promotes a more open, inclusive and sustainable approach to AI on an international level. It is implemented by the Deutsche Gesellschaft für Internationale Zusammenarbeit (GIZ) on behalf of the German Federal Ministry for Economic Cooperation and Development (BMZ). Fair Forward seeks to improve the conditions for local AI innovation and policy in five partner countries: Rwanda, Uganda, Ghana, South Africa and India. Together with our partners, we focus on three areas of action: (1) strengthen local technical know-how on AI, (2) increase access to open AI training data, (3) develop policy frameworks ready for AI.

About Western Cape Department of Agriculture (elsenburg.com)

The Western Cape Department of Agriculture provides a wide range of development, research and support services to the agricultural community in the Western Cape. The Western Cape province of South Africa is the country’s leading producer of high value agricultural export crops and derived products (mainly fruit & wine), as well as being the “breadbasket” of South Africa in terms of dryland winter wheat production. The Western Cape Department of Agriculture initiated a detailed crop survey in 2013 to establish a field-scale, land use data set, initially in response to growing data requirements emanating from developmental pressures and regional planning initiatives. The process was repeated during 2017/18. For more information, visit the department website.

About CV4GC (cv4gc.org)

The Computer Vision for Global Challenges is an initiative to bring the computer vision community closer to socially impactful tasks, datasets and applications for worldwide impact.

About Descartes Labs (descarteslabs.com)

Established in 2014 by a team of scientists from Los Alamos National Laboratory, Descartes Labs was founded on the belief that planetary knowledge has the power to radically alter how companies, governments, and nonprofits understand their relationship to the world's physical systems. Scientific integrity, innovation, and a commitment to sustainability define Descartes Labs’ core values. It’s talented team possesses decades of experience working on some of the United States’ most difficult problems, with expertise in large-scale computing, artificial intelligence, and satellite imagery.