PulseAugur
EN
LIVE 02:03:22

Google AI maps natural forests with 92.2% accuracy for deforestation-free supply chains

Google AI has developed a new AI-powered map called Natural Forests of the World 2020, which distinguishes natural forests from other types of tree cover. This tool is designed to help governments and companies comply with new regulations, such as the European Union Regulation on Deforestation-free Products (EUDR), by providing a high-resolution, globally consistent baseline of natural forests as they existed in 2020. The AI model, a multi-modal temporal-spatial vision transformer (MTSViT), analyzes satellite imagery and topographical data over time to identify unique spectral, temporal, and texture signatures that differentiate natural forests from plantations and other land uses, achieving 92.2% accuracy. AI

IMPACT Enables better compliance with deforestation regulations and supports global conservation efforts.

RANK_REASON AI research paper detailing a new model and dataset for environmental monitoring. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Google AI / Research →

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

Google AI maps natural forests with 92.2% accuracy for deforestation-free supply chains

COVERAGE [1]

  1. Google AI / Research TIER_1 English(EN) ·

    Separating natural forests from other tree cover with AI for deforestation-free supply chains

    Climate & Sustainability