樹木の空間配置特性に基づくアフリカ全土のアグロフォレストリー土地の空間範囲マッピング
Mapping the spatial extent of agroforestry lands across Africa by characterizing tree spatial arrangements (原題)
Minxuan Sun, Martin Brandt, Philippe Ciais, David Makowski, Youngryel Ryu, Yidi Xu, Mengjie Han, Yi Leng, Zhixuan Guo, Xiaomeng Du, Jianchu Xu, Florian Reiner, Jingbo Chen, Jiaying He, Xin Jiao, Wei Li
🤖 gxceed AI 要約
日本語
アフリカ全土を対象に、10m解像度の樹冠被覆データ（PlanetScope・Sentinel-2）を用いて2019年のアグロフォレストリー農地を100m解像度で地図化した研究。農地内の樹木配置を「不規則に散在する樹木」と「列状に植栽された樹木」に分け、前者は樹木ピクセル距離指標、後者は約3.8万の手作業ラベルで学習したU-Netで検出した。地上データとGoogle Earth画像で検証し全体精度77.2%を達成。アグロフォレストリーの環境影響・収量変化評価やプロセスモデル開発の基盤データとなる。
English
This study maps the spatial extent of agroforestry lands across Africa for 2019 at 100 m resolution, using 10 m tree canopy cover from PlanetScope and Sentinel-2. It distinguishes scattered trees (via tree-pixel distance metrics) from row-planted trees (via a U-Net trained on ~38,000 labelled tree-row features), achieving 77.2% overall accuracy against ground and Google Earth validation. The dataset provides a baseline for assessing agroforestry's environmental and yield impacts and for process-based modelling.
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
アグロフォレストリーは炭素隔離・気候適応の手段として注目されるが、本論文はアフリカ対象で日本のSSBJ・有報開示との直接接続は薄い。ただし自然資本・土地利用の高解像度モニタリング手法として、TNFDや生物多様性開示に関心を持つ日本企業・研究機関にとって参考になる。
In the global GX context
Agroforestry is increasingly recognized in climate mitigation and adaptation finance, and this high-resolution, tree-arrangement-aware mapping improves on coarse canopy/biomass proxies. It offers a methodological template relevant to nature-related disclosure (TNFD) and land-use carbon accounting, though it does not directly engage TCFD/ISSB disclosure frameworks.
👥 読者別の含意
🔬研究者:樹木配置を明示的に扱う高解像度アグロフォレストリー地図作成の手法と検証枠組みを参考にできる。
🏢実務担当者:土地利用・自然資本モニタリングに関わる企業は、粗い樹冠被覆に代わる精緻な評価手法として注目できる。
🏛政策担当者:アフリカの農業・気候政策におけるアグロフォレストリー推進のベースライン整備に示唆を与える。
📄 Abstract（原文）
Agroforestry is a land-use practice that integrates trees into agricultural lands, supporting food security and rural livelihoods while delivering both climate adaptation and mitigation benefits. However, current large-scale assessments often rely on coarse tree canopy cover or biomass products to approximate agroforestry, which results in biases estimates of the production and ecological effects from agroforestry. Here, we produced a 100 m resolution map of the spatial extent of agroforestry lands in Africa for 2019, using 10 m resolution tree canopy cover data derived from PlanetScope and Sentinel-2 imagery. This map explicitly delineates croplands where agroforestry system is practised by distinguishing tree spatial patterns within croplands, focusing on irregularly scattered trees and trees aligned in rows. Scattered trees are identified using tree-pixel distance metrics, whereas trees planted in rows are detected using a U-Net model trained with ~38,000 manually labelled tree-row features. The identified agroforestry lands with scattered trees and trees in rows on cropland were validated against ground-based sites collected from the literature and Google Earth imagery, yielding an overall accuracy of 77.2%. This agroforestry dataset with explicit spatial tree arrangements can served as a baseline for assessing environmental impacts and crop yield change of agroforestry ecosystems, as well as for supporting the development of process-based agroforestry models.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1016/j.jag.2026.105644first seen 2026-11-03 04:39:57 · last seen 2026-11-06 04:34:21
🔔 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。