Global forest typology at 10-meter resolution for forest and land-use monitoring
森林・土地利用モニタリングのための全球10m解像度森林タイポロジー (AI 翻訳)
Neumann, Maxim, Raichuk, Anton, Potapov, Peter, Lesiv, Myroslava, Overlan, Matthew, Rey, Melanie, Rajakumar, Ravindran, Conserva, Michelangelo, Stanimirova, Radost, Sims, Michelle, Carter, Sarah, Goldman, Elizabeth, Jiang, Yuchang, Scheibenreif, Linus, Georgieva, Ivelina, Shchepashchenko, Maria, Fritz, Steffen, Clinton, Nicholas, Stanton, Charlotte, Morris, Dan +1
🤖 gxceed AI 要約
日本語
本論文は、FAOおよびEU森林劣化防止規則(EUDR)の定義に準拠した6区分（原生林、自然再生林、植林、プランテーション、樹木農園・アグロフォレストリー、その他）で全球10m解像度の森林タイポロジーマップForTy v1を提供する。深層学習を用いて1.7百万サンプルから訓練し、全体精度90.2%、自然林分類94.8%を達成。炭素会計や生物多様性評価、サプライチェーン規制に貢献する。
English
This paper presents ForTy v1, a global 10-meter resolution forest typology map for 2020 with six classes aligned with FAO and EUDR definitions: Primary Forest, Naturally Regenerating Forest, Planted Forest, Plantation Forest, Tree Crops and Agroforestry, and Other Land. Using a cascaded deep learning pipeline trained on 1.7 million global samples, it achieves 90.2% overall accuracy for the six-class scheme and 94.8% for natural forest classification. The dataset supports carbon accounting, biodiversity assessment, and supply-chain regulation.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本では、森林炭素吸収量のJ-クレジット制度への活用や、EUDR対応サプライチェーン管理が重要課題。本データセットは、高解像度かつ国際基準に準拠した森林タイプ分類を提供し、企業の森林関連開示や政策策定の基盤となる。
In the global GX context
This dataset directly addresses the need for high-resolution, globally consistent forest typology data critical for carbon accounting under frameworks like TCFD/ISSB, and for compliance with the EU Deforestation Regulation (EUDR) which requires supply-chain traceability. It enables more accurate scope 3 emissions from land use change and supports biodiversity reporting.
👥 読者別の含意
🔬研究者:Provides a benchmark global forest typology dataset at 10m resolution, enabling studies on carbon dynamics, biodiversity, and land-use change with improved spatial detail.
🏢実務担当者:Can be used for corporate supply-chain mapping to identify deforestation risks and for reporting forest-related metrics aligned with EUDR and carbon accounting standards.
🏛政策担当者:Offers a scalable tool for monitoring forest types and land-use changes to enforce regulations like EUDR and support national carbon accounting under Paris Agreement.
📄 Abstract（原文）
Distinguishing forest types---primary, naturally regenerating, planted, and plantation forests---from agricultural tree crops and other land uses is essential for carbon accounting, biodiversity assessment, conservation planning, and supply-chain regulation. However, no existing global dataset resolves this typology at high spatial resolution. We present the Forest Typology (ForTy) v1 dataset, a global 10-meter resolution map for 2020 that classifies all land into six categories aligned with FAO and EU Deforestation Regulation (EUDR) definitions: Primary Forest, Naturally Regenerating Forest, Planted Forest, Plantation Forest, Tree Crops and Agroforestry, and Other Land. A cascaded deep learning pipeline, trained on 1.7 million globally distributed samples, generates per-class probability maps from geospatial satellite embeddings by combining weakly supervised learning with active learning. Independent validation against 8,190 stratified random sites, each labeled by two experts, yields an overall accuracy of 90.2% for the six-class scheme, 94.8% for natural forest classification, and 95.5% for forest/non-forest classification.
🔗 Provenance — このレコードを発見したソース
- EarthArXiv https://eartharxiv.org/repository/object/13130/download/23296/first seen 2026-05-23 04:16:56 · last seen 2026-05-27 04:15:58
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。