A scalable workflow for urban tree inventory and carbon estimation based on UAV LiDAR–hyperspectral fusion
UAV LiDAR–ハイパースペクトル融合に基づく都市樹木インベントリと炭素推定のためのスケーラブルなワークフロー (AI 翻訳)
Feiya Luo, Yanyun Nian, Pinqi Rao, Hao Wang, Junyu Huang
🤖 gxceed AI 要約
日本語
本研究は、UAV搭載LiDARとハイパースペクトルデータの融合による個別樹木の種分類と炭素蓄積量推定のスケーラブルなワークフローを提案する。適応的特徴選択法（ACV-DCC）とRF分類器を用いて18樹種で85.67%の精度を達成し、大学キャンパス内で約1.85×10^6 kgの炭素量を推定した。この再現可能なフレームワークは、世界中の不均質な都市環境に適用可能である。
English
This study proposes a scalable workflow integrating UAV LiDAR and hyperspectral data for individual tree species classification and carbon stock estimation in urban forests. Using an adaptive feature selection method (ACV-DCC) and RF classifier, it achieved 85.67% accuracy for 18 species and estimated ~1.85×10^6 kg carbon on a university campus. The framework is reproducible and suitable for heterogeneous urban environments globally.
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
日本の都市緑化政策やカーボンニュートラル目標において、UAVリモートセンシングによる樹木炭素ストックの高精度推定は、市区町村レベルのGHGインベントリやカーボンオフセット認証に貢献できる。特に、東京都や横浜市などでの都市林管理への応用が期待される。
In the global GX context
Urban tree carbon estimation is increasingly important for city-level climate action plans and net-zero targets. This UAV-based method offers a cost-effective and accurate solution for municipalities to monitor carbon sequestration, aligning with global frameworks like GPC (Global Protocol for Community-Scale Greenhouse Gas Inventories) and C40 cities' reporting requirements.
👥 読者別の含意
🔬研究者:A reproducible framework for individual-tree carbon stock estimation using multi-sensor fusion, with implications for urban ecology and remote sensing methodology.
🏢実務担当者:Urban planners and sustainability teams can adopt this workflow for carbon offset verification and green infrastructure management.
🏛政策担当者:Provides a precise tool for integrating urban forest carbon sinks into municipal climate inventories and NDC reporting.
📄 Abstract（原文）
Urban forests are critical nature-based solutions for climate change mitigation, yet accurately quantifying their carbon sequestration potential at fine scales remains a major challenge. In this study, an integrated framework for individual-tree-level species classification and carbon stock estimation in urban forests is proposed, leveraging UAV-based LiDAR and hyperspectral data fusion. To address the challenges of high feature dimensionality and class imbalance, an enhanced feature selection strategy termed adaptive cross-validation with dynamic correlation constraints (ACV-DCC) was introduced. A total of 14,376 individual trees were automatically segmented using a seed-growing algorithm across three types of urban green spaces on the Yuzhong Campus of Lanzhou University. The ACV-DCC method significantly improved classification performance, increasing the accuracy for 18 tree species to 85.67%. Among the tested classifiers, the RF outperformed the SVM and XGBoost algorithms in terms of the accuracy (85%–86%) and robustness. Its nonlinear modeling capacity also enabled accurate prediction of tree structural attributes, supporting a carbon stock estimation of approximately 1.85 × 106 kg on campus. The results demonstrate the scalability and effectiveness of the proposed framework in small- to medium-scale heterogeneous urban green environments. This reproducible and scalable workflow provides a high-precision technical pathway that can be adapted to heterogeneous urban environments worldwide, thereby contributing to global urban carbon monitoring efforts and sustainable ecosystem planning.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1080/10095020.2026.2681362first seen 2026-06-20 05:46:10
🔔 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。