Tree crop mapping of South America reveals links to deforestation and conservation

2026-02-19

AI Summary

This study addresses the critical lack of high-resolution data in South America needed to distinguish woody crop agricultural systems from natural forests—a gap that has hindered the precise implementation of zero-deforestation policies. For the first time, we integrate time-series Sentinel-1 and Sentinel-2 imagery to develop a multimodal spatiotemporal deep learning model, producing a 10-meter resolution map of woody crop extent across approximately 11 million hectares in South America. Our results reveal that existing regulatory maps misclassified 23% of smallholder agroforestry systems as forest loss between 2000 and 2020, substantially inflating deforestation estimates. This advancement significantly improves the accuracy of deforestation monitoring and enhances policy equity, providing essential baseline data to support the European Union’s Deforestation-Free Regulation.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Multimodal Learning
• Multiagent Systems: Agreement, Argumentation & Negotiation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Monitoring tree crop expansion is vital for zero-deforestation policies like the European Union's Regulation on Deforestation-free Products (EUDR). However, these efforts are hindered by a lack of highresolution data distinguishing diverse agricultural systems from forests. Here, we present the first 10m-resolution tree crop map for South America, generated using a multi-modal, spatio-temporal deep learning model trained on Sentinel-1 and Sentinel-2 satellite imagery time series. The map identifies approximately 11 million hectares of tree crops, 23% of which is linked to 2000-2020 forest cover loss. Critically, our analysis reveals that existing regulatory maps supporting the EUDR often classify established agriculture, particularly smallholder agroforestry, as "forest". This discrepancy risks false deforestation alerts and unfair penalties for small-scale farmers. Our work mitigates this risk by providing a high-resolution baseline, supporting conservation policies that are effective, inclusive, and equitable.

Problem

• tree crop mapping
• deforestation
• agroforestry
• EUDR
• forest classification

Innovation

• tree crop mapping
• deep learning
• multi-modal satellite imagery
• deforestation monitoring
• high-resolution land cover