Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Ai2 launches PLANTEUR, a tropical crop-mapping benchmark extending PASTIS

AI summary

Ai2 has released PLANTEUR, an extension of the PASTIS crop-mapping benchmark to six tropical regions: Réunion, Guadeloupe, Martinique, Guyane, Mayotte and Saint-Martin. Built from France's Land Parcel Identification System, it contains 2,750 aligned Sentinel-2, Sentinel-1 and Landsat-8 time series and 4,506 km² of parcel-derived labels across seven crop classes, including sugarcane, banana, pineapple and tropical tubers, with baseline results on standard, leave-one-island-out and few-shot splits. Ai2 reports that every method it evaluated, including its own, scores substantially lower on PLANTEUR than on PASTIS, and that every model loses roughly half its accuracy on an island it never saw in training. The data and code are available on Hugging Face and GitHub.

In-depth insight

Ai2 says PLANTEUR aims to let teams building geospatial foundation models check whether their models work in the smallholder, tropical and topographically complex agricultural systems where mapping could be most valuable.

A crop-mapping benchmark for the tropics

October 22, 2026

Ai2


Tech ReportDataCode

Foundation models and open data are driving rapid progress in machine learning for remote sensing, and benchmarks play a key role in understanding model improvement. PASTIS is one of the community's most trusted benchmarks, thanks to its high-quality labels and geospatial metadata. It also represents an important problem. Crop-type mapping is the starting point for food security planning, water allocation, and tracking how farmland changes. However, its coverage is limited to metropolitan France. We present PLANTEUR, an extension of PASTIS to six tropical regions, in hopes that teams building geospatial foundation models can check whether their model performs in agricultural systems where mapping could be most valuable: smallholder, tropical, topographically complex.

#Ai2#PLANTEUR#PASTIS#Hugging Face#GitHub

Original · 2 min readRead the original
Group chat

No comments yet. Start the conversation.