← 論文一覧に戻る

マルチソースデータ統合による中国の年次グリッド人為起源CH4排出量推計（2019–2025）：SHAPに基づく要因帰属と時空間パターン

Annual Gridded Anthropogenic CH4 Emissions Estimation in China (2019–2025) Integrating Multisource Data: SHAP-Based Driver Attribution and Spatio-Temporal Patterns (原題)

Chao-Kang He, Qinjun Wang, Wen-Yue Xie

Remote Sensing📚 査読済 / ジャーナル2026-09-15#AI×ESGOrigin: CN経営インパクト: 調達リスク対象セクター: cross_sector
DOI: 10.3390/rs18183168
原典: https://doi.org/10.3390/rs18183168
📄 PDF

🤖 gxceed AI 要約

日本語

本研究は地理・衛星・統計のマルチソースデータと4種の機械学習（RF・CB・XGB・LGBM）を統合し、中国の人為起源メタン排出量を0.1°解像度で2019〜2025年まで年次推計する枠組みを提案する。LGBMが最高精度（R²=0.938）を示し、SHAP解析により石炭採掘と夜間光が寄与の65.6%を占めることを明らかにした。空間的には「北高南低」で山西・陝西・内モンゴルのエネルギー三角地帯に極端高値が集中する。

English

This study integrates multi-source geographic and remote-sensing data with four ML algorithms (RF, CB, XGB, LGBM) to build a 0.1° annual gridded inventory of China's anthropogenic CH4 emissions for 2019–2025. LGBM achieves the best accuracy (R²=0.938), and SHAP attribution shows coal mining plus nighttime lights drive 65.6% of predictions. Emissions cluster in the Shanxi–Shaanxi–Inner Mongolia energy triangle, revealing a north-hot/south-cold pattern.

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

日本企業にとっては、Scope 3上流（石炭・農業・廃棄物）の排出係数精緻化や、衛星×MLによるサプライチェーン排出モニタリング手法として示唆が大きい。SSBJ開示や有報でのScope 3算定高度化を検討する日本企業の参考になる。

In the global GX context

For global disclosure scholarship, this demonstrates how ML plus remote sensing can move beyond static emission factors toward dynamic, high-resolution inventories — directly relevant to refining Scope 3 upstream estimates and to ISSB/GHG Protocol discussions on data quality and verification.

👥 読者別の含意

🔬研究者:ML×衛星データによる排出インベントリ高度化とSHAP解釈手法の実証例として参照価値が高い。

🏢実務担当者:Scope 3上流（石炭・農業）の排出係数精緻化やサプライヤー排出モニタリングへの応用を検討できる。

🏛政策担当者:地域別・高解像度のメタン排出マップは、中国の炭素市場やメタン削減政策の標的設定に資する。

📄 Abstract（原文）

Accurately quantifying the spatiotemporal dynamics and driving mechanisms of anthropogenic methane (CH4) emissions (MEs) is of great significance for achieving regional “dual-carbon” goals and global climate collaborative governance. However, existing ME inventories and macro-inversion models generally face bottlenecks such as coarse spatial resolution, lack of data update timeliness, and the inability of traditional static emission factors to capture non-linear responses. To address these issues, this study proposes an annual ME inventory enhancement framework integrating multi-source geographic and remote sensing data. This framework evaluates four advanced machine learning (ML) algorithms, including Random Forest (RF), Categorical Boosting (CB), Extreme Gradient Boosting (XGB), and Light Gradient Boosting Machine (LGBM), to construct a 0.1° high-resolution spatial grid of anthropogenic ME in China from 2019 to 2025. Furthermore, it introduces the SHapley Additive exPlanations (SHAP) framework and multi-scale spatial autocorrelation analysis to parse the driving mechanisms and clustering patterns. The results show the following: (1) LGBM exhibits the optimal comprehensive estimation accuracy (R2 = 0.938, RMSE = 3.707 Kt) and robust capability in capturing extreme ME sources (RTop2 = 0.929). (2) SHAP attribution reveals that coal mining and nighttime light (NTL) represent the primary contributing features to ME predictions (with a cumulative contribution of 65.60%), followed by agricultural and pastoral activities (24.98%), and all factors exhibit significant non-linear threshold and step-response characteristics. (3) Regarding spatiotemporal evolution, China’s total anthropogenic ME shows a trend of initial slow increase followed by high-level stabilization; spatially, it presents a “hot in the north, cold in the south” pattern, with extreme high values highly clustered in the Shanxi–Shaanxi–Inner Mongolia energy triangle and its peripheral expansion nodes. This study provides scientific references for formulating tailored, multi-scale, and refined CH4 mitigation strategies.

🔗 Provenance — このレコードを発見したソース

🔔 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。