いつ転移すべきかを学ぶ：新規製造領域におけるカーボンフットプリントモデリングのための強化学習
Learning When to Transfer: Reinforcement Learning for Carbon-Footprint Modeling in New Manufacturing Domains (原題)
Muhammad Umar Farooq, Daniel Cooper
🤖 gxceed AI 要約
日本語
新規材料・工程のカーボンフットプリントを予測する際、既存製造データの無差別な再利用は負の転移を招く。本研究は強化学習により転移の可否を選択する手法を提案し、検証ゲートで改善時のみ転移予測を採用する。材料押出AM5材料729実験で検証し、RMSE 5.2 g CO2e/部品を達成、ターゲット単独学習比20%改善、無差別プーリング比10.3%改善を示した。
English
Manufacturers often lack data to model carbon footprints of new materials or processes. This work proposes a reinforcement-learning policy that selectively transfers knowledge from existing manufacturing domains, using a validation gate to deploy transferred predictions only when they beat supervised alternatives. Evaluated on material-extrusion additive manufacturing across five polymers (729 experiments), it achieves 5.2 g CO2e RMSE per part—20% better than target-only training and 10.3% better than indiscriminate pooling.
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 算定や製品別カーボンフットプリント開示が求められる中、データ不足の新規製品・材料でも信頼できる排出量予測を可能にする手法。SSBJ・有報での製品別排出量開示や、サプライチェーン上流の排出量推計精度向上に直結する。
In the global GX context
As ISSB/CSRD push product-level and Scope 3 disclosure, manufacturers face data scarcity for new materials. This RL-based transfer learning offers a way to estimate embodied emissions credibly without full primary data, supporting disclosure infrastructure and carbon accounting accuracy.
👥 読者別の含意
🔬研究者:負の転移を回避する選択的転移学習の枠組みは、データ希薄領域での炭素会計モデリングに応用可能な方法論的貢献。
🏢実務担当者:新規材料・製品の排出量を限られたデータで予測でき、Scope 3 や製品CFP算定の初期段階に活用できる。
🏛政策担当者:製品別排出量開示制度の実効性を高めるため、データ不足下での推計手法の標準化を検討する際の参考になる。
📄 Abstract（原文）
Manufacturers often need to characterize a new material, process, or product before enough operating data are available to train reliable predictive models for this new, target domain. Existing manufacturing operations contain potentially useful knowledge to accelerate this characterization, but indiscriminate reuse of data from existing source domains can cause negative transfer in learning of the new, target domain when the manufacturing domains differ sufficiently. This work proposes a reinforcement-learning method for selective knowledge transfer, where its reward scores each opportunity to transfer against supervised alternatives, so negative transfer is avoided and controlled during forward prediction instead of being diagnosed afterwards. Given limited data from a new target domain, the learned policy chooses among predictors based on individual source operations, subsets of the sources, or the supervised alternatives: fully pooled sources, or target data alone. A validation gate deploys the transferred prediction only when it improves upon the supervised alternatives. The method is designed for learning variables supporting carbon accounting, as well as performance and quality outcomes. We demonstrate the approach by quantifying the embodied greenhouse-gas emissions of parts produced via material-extrusion additive manufacturing, using data from 729 experiments spanning five materials: ABS, PETG, TPU, PLA, and recycled PLA. The response combines measured fabrication electricity with polymer-specific cradle-to-gate production factors, while 22 material, process, and toolpath features characterize each experiment. In leave-one-material-out evaluation, this method achieves a mean test RMSE of 5.2 g CO2e per part, 20.00% lower than target-only training (32.5% lower when only 5-10% of the target training data are available) and 10.30% lower than indiscriminate source-target pooling.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.48550/arxiv.2610.18730first seen 2026-10-16 05:05:03
🔔 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。