Research on carbon drivers of agricultural exports combined with XGBoost and SHAP
XGBoostとSHAPを組み合わせた農業輸出の炭素排出要因の研究 (AI 翻訳)
Jiayuan Guo, Kai Quan Zhang, Yanlai Wang, Krishnan Vijayaletchumy
🤖 gxceed AI 要約
日本語
XGBoostとSHAP解釈性分析を統合した枠組みで、中国中部のパネルデータ（1993-2019）を用いて農業輸出の炭素排出要因を特定。最適化モデルは高い予測精度（R²=0.935）を示し、農村電力消費、農業機械総出力、農業総生産額が主要な正の要因であることを定量的に評価。非線形関係と交互作用も明らかにし、説明可能なAIを環境経済学に応用した点が特徴。
English
This study integrates XGBoost with SHAP interpretability to identify carbon emission drivers of agricultural exports using panel data from Central China (1993-2019). The optimized model achieves high predictive accuracy (R²=0.935), revealing rural electricity consumption, agricultural machinery power, and gross agricultural output as key positive drivers. It uncovers nonlinear relationships and interaction effects, advancing explainable AI in environmental economics and providing evidence for targeted agricultural 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
日本の農業分野における脱炭素戦略（みどりの食料システム戦略など）への示唆に富む。AIを用いた排出要因分析は、日本の農業輸出や地域別の排出削減策の策定に応用可能。
In the global GX context
This paper contributes to global GX scholarship by demonstrating the application of explainable AI (XGBoost+SHAP) to agricultural carbon emissions, a sector often underrepresented in climate disclosure research. Its methodological framework can inform similar analyses in other regions and support the development of data-driven agricultural decarbonization policies.
👥 読者別の含意
🔬研究者:Provides a novel application of explainable AI to agricultural carbon drivers, offering a methodological template for similar studies.
🏢実務担当者:Identifies key emission drivers (energy use, production scale) that can guide corporate sustainability strategies in agricultural supply chains.
🏛政策担当者:Offers evidence for designing targeted, differentiated agricultural carbon reduction policies based on quantitative driver analysis.
📄 Abstract（原文）
Accurate identification of agricultural export carbon emission drivers is essential for developing effective mitigation strategies under global climate change. This study proposes an integrated analytical framework combining the XGBoost machine learning model with SHAP interpretability analysis to capture nonlinear relationships and quantify factor contributions. Using panel data from Central China (1993–2019), model parameters were optimized through grid search and cross-validation. Results show that the optimized XGBoost model achieves high predictive accuracy ( R 2 = 0.935). The SHAP-based attribution analysis quantitatively assessed factor contributions, revealing rural electricity consumption, total agricultural machinery power, and gross agricultural output value as the three most significant positive drivers. These factors displayed mean absolute SHAP values of 0.176, 0.158, and 0.144 correspondingly, whereas total export trade exhibited negative influence. The findings indicate that energy usage and agricultural production scale represent fundamental drivers of agricultural export carbon emission growth, while simultaneously uncovering nonlinear relationships and notable interaction effects between critical factors and emission outputs. Methodologically, this research advances the integration of explainable artificial intelligence within environmental economics, while practically it delivers scientific evidence and policy support for developing differentiated, precise agricultural carbon reduction strategies, contributing significant theoretical and practical implications for advancing agricultural trade’s green transformation.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.3389/fenvs.2026.1778130first seen 2026-05-27 04:54:27 · last seen 2026-06-17 07:06:33
🔔 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。