Skip to content

radiantearth/spot-the-crop-xl-challenge

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Radiant Earth Spot The Crop XL Challenge

The objective of this challenge was to use time-series of Sentinel-2 multispectral and Sentinel-1 SAR data to classify crops in the Western Cape of South Africa. Participants were asked to build a machine learning model to predict crop type classes for the test dataset. The training dataset was generated by the Radiant Earth Foundation team, using the ground reference data collected and provided by the Western Cape Department of Agriculture.

This repository contains the winning models from the XL track of the competition in which participants used time series of Sentinel-1 SAR data in addition to Sentinel-2 multispectral data as input for crop type classification.

The competition was run on Zindi platform.

Results and Solutions

The evaluation metric for the competition was Cross Entropy with binary outcome for each crop:

cost function

The following table shows the competition scores of the awarded winners.

Team Competition Score
SkaMo 0.634814703680626
Ensemble 0.680127144327633
ASSAZZIN 0.690294803999381

Organizer

Convening Sponsor

Data Provider and Collaborator

Platinum Sponsor

Gold Sponsor

Releases

No releases published

Packages

No packages published