Greenhouse Gas Emissions Optimization for Vegetable Processing in Production Area Using Deep Deterministic Policy Gradient
深層決定性方策勾配を用いた産地野菜加工における温室効果ガス排出最適化 (AI 翻訳)
Jianxun Zhao, Mingxuan Huang, Changqing Tian, Mingsheng Tang
🤖 gxceed AI 要約
日本語
本研究は、野菜産地のハンドリング工程におけるGHG排出削減を目的とし、感度分析で主要パラメータを特定した上で、深層決定性方策勾配（DDPG）を用いた排出最適化モデルを構築した。マルコフ決定過程としてモデル化し、報酬関数設計によりGHG排出最小化、野菜質量保持率最大化、保管時間短縮の多目的最適化を実現。ケーススタディでは、1000kgの野菜処理で排出量を117.06kg CO2eqから36.63kg CO2eqへ削減しつつ、質量保持率も向上させた。
English
This study optimizes GHG emissions in vegetable handling processes using Deep Deterministic Policy Gradient (DDPG). Sensitivity analysis identifies key parameters, and a Markov decision process model with multi-objective reward design minimizes emissions, maximizes mass retention, and shortens storage time. A case study shows emissions reduced from 117.06 to 36.63 kg CO2eq per 1000 kg vegetables while improving mass retention.
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、食品ロス削減と冷蔵・冷凍倉庫の脱炭素が課題であり、本手法は産地物流の効率化とGHG削減を両立する点で、農産物サプライチェーンのGX推進に示唆を与える。SSBJ開示対応においても、サプライチェーン排出量の削減策として参考になる。
In the global GX context
Globally, this work contributes to AI-driven decarbonization of cold chain logistics, aligning with Scope 3 reduction targets under TCFD/ISSB frameworks. It demonstrates a practical application of reinforcement learning for multi-objective optimization in agri-food supply chains, offering a replicable model for emissions reduction in perishable goods handling.
👥 読者別の含意
🔬研究者:Reinforcement learning (DDPG) applied to GHG optimization in agri-food logistics; useful for AI×ESG research.
🏢実務担当者:Provides a data-driven method to reduce Scope 3 emissions in cold chain operations, potentially lowering compliance costs.
🏛政策担当者:Highlights potential for AI-based optimization in agricultural supply chains to meet national decarbonization targets.
📄 Abstract（原文）
Abstract The continuous expansion of cold chain logistics has drawn increasing attention to its associated greenhouse gas (GHG) emissions. To support the cold chain's low-carbon transition, this study focuses on GHG reduction in handling processes within vegetable production area. We first employed sensitivity analysis to identify key parameters for GHG reduction across different handling stages. Subsequently, GHG emissions optimization model was developed using the Deep Deterministic Policy Gradient. Handling processes in vegetable production were modeled as a Markov decision process. Through reward function design, the model achieves multi-objective optimization by simultaneously minimizing GHG emissions, maximizing vegetable mass retention, and shortening on-farm storage time. A case study demonstrates that processing 1000 kg of vegetables under the current system generates 117.06 kg carbon dioxide equivalent (CO2eq), whereas the proposed optimization model reduces the emissions to 36.63 kg CO2eq while simultaneously achieving a significant increase in the vegetable mass retention rate.
🔗 Provenance — このレコードを発見したソース
- crossref https://doi.org/10.1093/fqsafe/fyag062first seen 2026-08-06 06:07:08
🔔 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。