A Machine Learning Framework for Enhancing Scope 3 Emissions Measurement through Integrated Product and Industry Classifications
製品分類と産業分類を統合したスコープ3排出量測定の機械学習フレームワーク (AI 翻訳)
Ajay S. Jadhav, Shiva Abdoli
🤖 gxceed AI 要約
日本語
スコープ3排出量の測定はデータ不足が課題だが、本論文は中央製品分類(CPC)、国際標準産業分類(ISIC)、北米産業分類システム(NAICS)を統合し機械学習モデルを適用する新フレームワークを提案。勾配ブースティング決定木がR²0.9108を達成し、精度向上を示した。
English
Addressing data scarcity in Scope 3 measurement, this paper proposes a machine learning framework integrating CPC, ISIC, and NAICS classifications. Using supply chain emission factors as target, Gradient Boosting Decision Trees achieved R² 0.9108, demonstrating improved granularity and predictive accuracy over traditional methods.
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SSBJ基準に対応したスコープ3開示が進んでいる。本フレームワークはNAICSベースだが、ISICとCPC統合により国際比較可能で、日本企業がグローバルサプライチェーン排出量を高精度で推定する基盤となり得る。
In the global GX context
With ISSB and CSRD requiring Scope 3 disclosure, this ML framework offers a scalable approach to improve data quality. By integrating product and industry classifications, it addresses granularity gaps in monetary input-output methods, supporting more reliable climate transition plans.
👥 読者別の含意
🔬研究者:Novel integration of CPC/ISIC/NAICS with ML for Scope 3; provides a methodological benchmark for future studies.
🏢実務担当者:Enables firms to estimate Scope 3 emissions with higher granularity using publicly available classification data and ML models.
🏛政策担当者:Standardizing classification integration could enhance comparability and reliability of Scope 3 reporting across jurisdictions.
📄 Abstract（原文）
Scope 3 emissions are major contributor for emissions of many industries. Since these emissions are indirect/complex in nature, data availability is a major challenge in estimating them. Current methods mostly rely on high level economic transactions with less inclusion of product details and have shortcomings in handling lack of data. In this research, we firstly discussed the benefits/shortcomings of existing methodologies for estimating scope 3 emissions and proposed a Machine Learning (ML) based framework to overcome those shortcomings. In our approach we map the Central Product Classification (CPC) system with International Standard Industry Classification (ISIC) and North American Industry Classification System (NAICS) together to gain higher granularity in scope 3 emission estimation. For ML models implementation, we used the supply chain emission factors based on NAICS codes as targeted variable. Our best performing model, Gradient Boosting Decision Trees, achieved an R² score of 0.9108 and MSE of 0.034 while giving balanced importance to CPC and ISIC codes. Results suggest our ML framework, combined with integrated classifications, can enhance the granularity and predictive accuracy for scope 3 emission factors derived from monetary input-output databases.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://doi.org/10.5539/mas.v20n1p1first seen 2026-05-05 21:55:05
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。