AI maps oil palm plantations in Southeast Asia without manual annotation

Researchers have developed a deep learning framework to create high-resolution maps of oil palm plantations in Indonesia and Malaysia from 2020 to 2024. The system uses Sentinel-2 imagery and a U-Net architecture with Determinant-based Mutual Information to overcome the limitations of noisy, low-resolution historical data. Validation against manually verified points showed accuracies ranging from 60% to 70%, with the study indicating a peak in oil palm coverage in 2022 followed by a slight decline. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Provides a novel deep learning approach for generating high-resolution land-use maps from noisy historical data, applicable to environmental monitoring.

RANK_REASON Academic paper detailing a new deep learning framework for land-use mapping.

Read on arXiv cs.CV →

• Malaysia
• Indonesia
• Sentinel-2
• U-Net
• Determinant-based Mutual Information
• arXiv

• paper
• other