• SOLUTION

Providing richer
cropland data

We make detailed, high resolution maps of African croplands by combining human and machine intelligence with new satellite imaging capabilities.

Banner

Better quality

High resolution, data-rich
cropland maps

Higher Resolution

Higher Resolution

Richer Information

Richer Information

Track changes

Maps can be updated each year

TRACK CHANGES

Get answers

Are there any new fields?

Were any fields lost?

Did field sizes change?

How it works

Four innovative components built on
the latest technology

1

Image
Processing

A custom procedure for converting daily, high- resolution imagery collected by small satellites into cloud-free seasonal composite images

2

Labelling
Platform

A web-based platform that allows rapid collection of training data, with built-in quality control procedures for reducing labeling errors.

3

Machine
Learning

We train a model to identify crop fields in the imagery, iteratively refining it with new labels collected from areas where its predictions are least certain

4

Field Boundary
Delineation

An algorithm converts predicted cropland probabilities into individual field boundaries.

Increase knowledge

A foundation for building
downstream models & analyses

ans-icon1

What is the
average size &
shape of crop
fields?

ans-icon2

How are fields changing from
year to year?

ans-icon3

What crops are growing in the
fields?

ans-icon4

What are their
yields?

image
image

News