Zindi
CompeteJobsLearnChatLeaderboardFor Organisations
PartnersMeet the teamPressCase studiesAI4EAC
Primary competition visual

CGIAR Eyes on the Ground Challenge

Helping Africa
$10 000 USD
Completed (almost 3 years ago)
Prediction
879 joined
137 active
InfoDataChatLeaderboard
Starti
21 Jul 23
Closei
03 Nov 23
Reveali
03 Nov 23
About

This dataset contains a set of training and testing data for the CGIAR Drought on the Ground challenge. The data is divided into training (the `train` directory), for which labels are provided in `train.csv` and test (`test` directory) for which no labels are provided. In total the training data provided consists of ~26K images with images distributed across seasons as illustrated below. 

| Season   | Image Count   |
|----------|:-------------:|
| LR2020   | 2034          |
| LR2021   | 7979          |
| SR2020   | 6163          |
| SR2021   | 9930          |

## Ancillary data For each growth stage the damage types and their `extent` are provided with the extent given as percentage (%) in 10% increments.


### Growth Stages

| Growth Stage   | Definition       |
|----------------|:----------------:|
| F              | Flowering        |
| M              | Maturity         |
| S              | Sowing           |
| V              | Vegetative       |


### Damage types

| Damage          | Definition         |
|-----------------|:------------------:|
| DR              | Drought            |
| DS              | Disease            |
| FD              | Flood              |
| G               | Good (growth)      |
| ND              | Nutrient Deficient |
| PS              | Pest               |
| WD              | Weed               |
| WN              | Wind               |

Download the image data from Google Drive HERE.

Files
Description
Files
This is the dataset that you will use to train your model.
This is the dataset that you will use to test your model.
shows the submission format for this competition, with the ‘ID’ column mirroring that of Test.csv. The order of the rows does not matter, but the names of the ‘ID’ must be correct.

Join the largest network for
data scientists and AI builders

AboutFAQsPrivacy PolicyTerms of UseRules
Status
© Zindi 2026