食品飲料セクターにおける参照食品カーボンフットプリント推計のためのガウス混合モデル基盤機械学習フレームワーク
A Gaussian Mixture Model-Based Machine Learning Framework for Reference-Food Carbon Footprint Estimation in the Food and Beverage Sector (原題)
Thing-Yuan Chang, Chien-Chih Chen, Chin-Hsien Hsu, Fong Kin Law, Hsi-Lin Chang
🤖 gxceed AI 要約
日本語
食品飲料セクターの参照食品について、GMMで学習データを分割し近傍ルーティングで回帰器を切り替える機械学習フレームワークを提案。LEAF名称をAGRIBALYSEやCIQUAL栄養データと紐付け約47万件の観測を構築した。重み付きルーティングはRMSEを3.465から3.136 kg CO2e/kgへ低減するが、全体XGBoostが2.773と最小で、主要比較は統計的に有意でなかった。製品別LCAを代替せず、初期スクリーニング用途の限界を示す。
English
A GMM-based framework routes reference foods to outcome-specialized regressors (KNN, random forest, XGBoost) using predictor-space neighbors, trained on ~472k observations linking multilingual LEAF names to AGRIBALYSE 3.1.1 climate values and CIQUAL nutrients. Weighted routing lowers RMSE versus majority routing (3.465 to 3.136 kg CO2e/kg), though global XGBoost achieves the lowest RMSE (2.773) and no primary comparison is significant. Results reveal limits to outcome-based specialization and support screening, not replacement of product-specific LCA.
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
Scope 3 排出量算定において、サプライヤー一次データが乏しい食品分野でのスクリーニング手法として、SSBJ・Scope 3 開示対応の実務に示唆を与える。
In the global GX context
Offers a scalable ML screening approach for food-sector Scope 3 estimation where primary inventory data are scarce, relevant to ISSB/CSRD value-chain disclosure and GHG Protocol Scope 3 screening.
👥 読者別の含意
🔬研究者:GMMベースのルーティングと回帰器特化の有効性・限界を検証する方法論的知見を提供する。
🏢実務担当者:一次データ不足時のScope 3食品排出スクリーニングにMLを活用する際の精度限界を把握できる。
🏛政策担当者:食品分野の排出推計におけるML利用の限界とLCA補完の必要性を示す。
📄 Abstract（原文）
Product carbon footprint estimation can support early screening in the food and beverage sector, but life cycle assessment requires detailed inventory data that are often unavailable. Machine learning can estimate reference-food impacts from food descriptors; however, whether grouping training outcomes improves prediction remains uncertain when unseen foods must be routed using predictors alone. To examine this gap, we present and evaluate a Gaussian mixture model (GMM)-based framework combining outcome-specialized regressors with neighbor-based routing. Multilingual LEAF names are linked to AGRIBALYSE 3.1.1 climate-change values and enriched with non-environmental descriptors and CIQUAL nutrients, yielding 471,970 observations across 1562 reference codes. Within each training fold, a univariate GMM defines hard or overlapping alpha-cut subsets for K-nearest-neighbor, random-forest, and extreme gradient boosting (XGBoost) regression. Five predictor-space neighbors determine majority or weighted routing. Evaluation uses ten repetitions of five-fold cross-validation grouped by reference code, with training-only preprocessing and fitting. Weighted routing lowers mean root mean squared error (RMSE) relative to majority routing across matched configurations. Weighted fuzzy random forest at alpha = 0.1 reduces mean RMSE from 3.465 to 3.136 kg CO2e/kg, while global XGBoost achieves the lowest RMSE of 2.773. No primary comparison is significant under corrected repeated cross-validation tests with Holm adjustment. Target-value-grouped sensitivity analysis retains the principal learner-dependent pattern. These findings identify limits to outcome-based specialization rather than general superiority, supporting further investigation of reference-impact screening without replacing product-specific life cycle assessment.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.3390/sym18101745first seen 2026-10-22 04:57:27 · last seen 2026-11-06 05:00:03
🔔 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。