四川省南部における炭素貯留の時空間動態と駆動メカニズムのデータセット：Sentinel-2画像と説明可能な機械学習に基づく（2019年～2030年）
Dataset of Spatiotemporal Dynamics and Driving Mechanisms of Carbon Storage in Southern Sichuan, China Based on Sentinel-2 Imagery and Explainable Machine Learning (2019–2030) (原題)
Xi Pan, Xiong Duan, Yu Yu, Qian Li, Haiying Wang
🤖 gxceed AI 要約
日本語
本データセットは、四川省南部の炭素貯留の時空間動態と駆動メカニズムを分析するためのもので、Sentinel-2画像と機械学習を用いた高精度な土地利用分類、InVESTモデルによる炭素貯留シミュレーション、SSPシナリオに基づく将来予測、SHAPによる駆動要因の解明を含む。地域の生態保護と炭素削減政策に貢献する。
English
This dataset supports analysis of carbon storage dynamics in southern Sichuan, China, using Sentinel-2 imagery and machine learning for land use classification, InVEST for carbon simulation, SSP scenarios for future projections, and SHAP for driver analysis. It aids regional ecological protection and carbon reduction policies.
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GX文脈では、地域レベルの炭素貯留評価と土地利用計画の統合は、SSBJやカーボンニュートラル施策における地域データ活用の参考となる。ただし、中国の事例であり、日本の制度への直接適用は限定的だが、データ駆動型の環境評価手法は示唆に富む。
In the global GX context
Globally, this dataset exemplifies the integration of remote sensing, machine learning, and carbon modeling for regional carbon accounting, relevant to TCFD/ISSB disclosure needs for land-use-related emissions. It provides a methodological template for spatially explicit carbon monitoring that can inform transition finance and climate risk assessment.
👥 読者別の含意
🔬研究者:Provides a comprehensive dataset and methodology for spatially explicit carbon storage assessment using ML and SHAP, useful for land-use carbon modeling research.
🏢実務担当者:Offers a replicable approach for companies to assess land-based carbon stocks and inform sustainability reporting and land management decisions.
🏛政策担当者:Demonstrates how to use remote sensing and ML for regional carbon monitoring, supporting spatial planning and carbon reduction policy design.
📄 Abstract（原文）
This dataset supports the study of "Spatiotemporal Dynamics and Driving Mechanisms of Carbon Storage in Southern Sichuan, China." It includes: (1) high-accuracy land use/land cover classification (LUCC) maps for 2019–2025 derived from 10 m Sentinel-2 imagery via Google Earth Engine; (2) InVEST carbon storage simulation results for 2019–2030; (3) intPLUS multi-scale land-use change scenario simulations under SSP1-1.9 and SSP5-8.5; and (4) Random Forest–SHAP driving mechanism analysis outputs. The LUCC classification integrates spectral, vegetation index, and texture features, with the optimal Random Forest model selected from eight machine learning algorithms (OA = 0.9756, Kappa = 0.9715). Carbon storage dynamics were simulated using the InVEST Carbon module, and SHAP explainability analysis was applied to quantify the non-linear threshold effects of elevation, temperature, and precipitation on carbon fixation. This dataset provides critical decision-making support for ecological redline management, territorial spatial planning, and differentiated carbon reduction pathways in southern Sichuan.
🔗 Provenance — このレコードを発見したソース
- scidb https://doi.org/10.57760/sciencedb.00zxifirst seen 2026-08-21 05:24:05 · last seen 2026-09-18 05:56:56
🔔 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。