GEOSPATIAL TECHNIQUES FOR ASSESSING CARBON SEQUESTRATION IN MANGO ORCHARDS
マンゴー果樹園における炭素隔離評価のための地理空間技術 (AI 翻訳)
T. Sindhu, Dr. K. Sivakumar, Dr. D. Jayanthi, R. Jagadeeswaran, P. Kennedy Kumar
🤖 gxceed AI 要約
日本語
本レビューは、マンゴー果樹園の炭素貯留量を評価するための地理空間技術（GIS、リモートセンシング、UAV、LiDAR）と機械学習アルゴリズムの統合を検討する。衛星画像とMLモデル（ランダムフォレスト、SVM、ANN）の組み合わせにより予測精度が向上し、高解像度の3Dデータが個体レベルの評価を可能にする。今後の課題として、データ統合、モデルの転用性、標準化された測定プロトコルが挙げられる。
English
This review examines geospatial technologies (GIS, remote sensing, UAV, LiDAR) combined with machine learning for carbon stock estimation in mango orchards. Integration of satellite imagery and ML models (Random Forest, SVM, ANN) improves prediction accuracy, while high-resolution 3D data enables tree-level assessment. Challenges include data integration, model transferability, and standardized protocols.
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、果樹園を含む農地の炭素貯留はカーボン・クレジット制度（J-クレジット）の対象となり得る。本技術は、精密農業と炭素会計の統合を促進し、地域の脱炭素施策や持続可能な農業経営に貢献する可能性がある。
In the global GX context
Globally, this aligns with the growing demand for robust MRV frameworks in nature-based solutions and agricultural carbon markets. The integration of AI and remote sensing supports scalable carbon accounting, relevant to ISSB and CSRD disclosure requirements for land-related emissions.
👥 読者別の含意
🔬研究者:Provides a comprehensive overview of geospatial and ML methods for carbon sequestration assessment, highlighting research gaps.
🏢実務担当者:Offers practical insights into using remote sensing and AI for orchard carbon accounting, potentially supporting sustainability reporting.
🏛政策担当者:Informs policy on standardizing MRV protocols for agricultural carbon projects.
📄 Abstract（原文）
Carbon sequestration in mango (Mangifera indica L.) orchards represents a promising nature-based strategy for climate change mitigation, yet accurate large-scale assessment remains challenging using conventional field methods. This review examines the application of geospatial technologies—including Geographic Information Systems (GIS), remote sensing, Global Positioning Systems (GPS), Unmanned Aerial Vehicles (UAVs), and Light Detection and Ranging (LiDAR)—for estimating carbon stocks in mango orchards. Satellite platforms such as Sentinel-2 and Landsat provide multispectral imagery enabling derivation of vegetation indices (NDVI, EVI, NDRE, GNDVI) strongly correlated with biomass and carbon storage. Integration of these spectral datasets with machine learning algorithms, particularly Random Forest, Support Vector Machine, and Artificial Neural Networks, substantially improves prediction accuracy. Species-specific allometric models relating diameter, height, and wood density to biomass further enhance carbon estimation. UAV and LiDAR technologies provide high-resolution three-dimensional canopy information for individual tree-level assessment. Despite advances, challenges persist regarding data availability, sensor integration, model transferability, and standardized measurement protocols. Future research should prioritize multisensor data fusion, artificial intelligence applications, cloud-based platforms, and robust measurement, reporting, and verification frameworks. Integrating advanced geospatial techniques with sustainable orchard management offers a reliable pathway for enhancing carbon accounting, supporting precision agriculture, and contributing to global climate mitigation efforts.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.4238/00rzy185first seen 2026-08-08 05:05:10
🔔 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。