Machine learning maps cashew orchards in Guinea-Bissau

Researchers have developed a novel machine learning approach to detect cashew orchards across Guinea-Bissau using Sentinel-2 satellite imagery. This method employs margin-based active learning to create an optimal training dataset, achieving a 94.0% balanced accuracy for nationwide mapping. The project has made two datasets and a 2021 cashew map with 10m resolution openly available via GitHub, aiming to support environmental applications and combat deforestation. AI

IMPACT Enables large-scale environmental monitoring and resource management through automated satellite imagery analysis.

RANK_REASON Academic paper detailing a novel application of machine learning for environmental mapping. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• active learning
• GitHub
• Guinea-Bissau
• machine learning
• Sentinel-2
• West Africa

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →