Hybrid Feature‐Selection and Multi‐Scale Deep Learning for Carbon Price Forecasting in Emerging Carbon Markets
新興炭素市場におけるハイブリッド特徴選択とマルチスケール深層学習による炭素価格予測 (AI 翻訳)
Sensheng Li, Minjun Huang, Fuping Wang, Junkun Hu, Han-Ning Wang, Houjian Li
🤖 gxceed AI 要約
日本語
中国6つの排出権取引制度（ETS）を対象に、ET-MVMD-GRUを組み合わせたハイブリッド炭素価格予測フレームワークを提案。特徴選択、マルチスケール分解、深層学習を統合し、10の競合モデルと比較してMAE、RMSE、MAPEで最良の性能を達成。政策立案者への示唆も提供。
English
Proposes a hybrid ET-MVMD-GRU framework for carbon price forecasting across six Chinese pilot ETSs. Integrates feature selection, multi-scale decomposition, and deep learning, outperforming 10 competing models on MAE, RMSE, and MAPE. Offers evidence-based guidance for policymakers in developing carbon markets.
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、カーボンプライシング（排出量取引・炭素税）の本格導入が検討されており、本手法は市場設計や価格予測の参考となる。また、AIを活用した予測モデルは、企業のリスク管理や投資判断にも応用可能。
In the global GX context
As global carbon markets expand, accurate price forecasting is critical for risk management and policy design. This study provides a novel AI-driven approach applicable to emerging ETSs, complementing TCFD/ISSB-aligned climate risk assessments and transition finance strategies.
👥 読者別の含意
🔬研究者:Provides a robust hybrid deep-learning framework for carbon price forecasting, with comparative performance analysis across multiple markets.
🏢実務担当者:Offers a tool for anticipating carbon price movements, useful for compliance planning and hedging strategies.
🏛政策担当者:Demonstrates the value of AI in carbon market oversight and provides evidence for designing effective ETS policies.
📄 Abstract（原文）
As global attention to CO 2 intensifies, accurate carbon‐price forecasting has become a core topic in carbon‐market research. We propose a hybrid forecasting framework, extremely randomized trees (ET)–multivariate variational mode decomposition (MVMD)–gated recurrent unit (GRU), that integrates three advanced components to predict carbon prices for China’s six pilot emissions trading systems (ETSs)—Hubei, Shenzhen, Guangdong, Beijing, Shanghai, and Fujian. First, ET are used to assess feature importance and select key predictors. Second, after the observations are chronologically divided into an 80% training set and a 20% test set, MVMD is applied separately to the two subsets to decompose the carbon‐price series and the selected predictors into eight regularized intrinsic mode functions (IMFs), thereby achieving denoising and multi‐scale representation. Third, a GRU model is employed to learn the decomposed components and generate the final carbon‐price forecast. Empirical results across the six pilots show that ET–MVMD–GRU achieves the lowest MAE, RMSE, and MAPE among the 10 competing models, including the newly added ET–VMD–GRU and ET–ICEEMDAN–GRU, and remains in the superior model set in the model confidence set (MCS) tests. The framework offers a new methodological avenue for carbon‐price forecasting and provides evidence‐based guidance for policymakers on developing carbon markets in developing countries, strengthening risk management, and advancing the internationalization of carbon markets.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://onlinelibrary.wiley.com/doi/pdfdirect/10.1155/er/1314913first seen 2026-08-16 05:29:58
🔔 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。