Carbon Allowance Price Forecasting Based on a Multi-Scale Decomposition Strategy and a TCN–LSTM Hybrid Model: A Case Study of Hubei Province
マルチスケール分解戦略とTCN–LSTMハイブリッドモデルに基づく炭素排出枠価格予測：湖北省の事例研究 (AI 翻訳)
Guidan Zhong, Binbin Zhao, Yuan Xue
🤖 gxceed AI 要約
日本語
本論文は、非定常で高ノイズな炭素排出枠価格の短期予測のために、CEEMDANとVMDによる多段階分解とTCN-LSTMハイブリッドモデルを提案。伝達エントロピーで因果関係を特定して系列を再構成し、湖北省市場のデータでR²=0.8873を達成。外部変数不要で高精度な予測を実現し、政策評価や意思決定に貢献する。
English
This paper proposes a short-term carbon allowance price forecasting framework using multi-scale decomposition (CEEMDAN-PSO and VMD) and a TCN-LSTM hybrid model. Transfer entropy identifies causal relationships for series reconstruction. Empirical results on Hubei province market show R²=0.8873, outperforming single LSTM and TCN models. The method requires only price series data, avoiding external variables, and supports decision-making and policy assessment.
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
日本でも東京都や埼玉県の排出量取引制度が運用されており、炭素価格予測手法は市場参加者や政策担当者にとって有用。本研究の手法は、外部変数に依存しないためデータ制約のある地域への応用可能性が高く、日本の炭素市場設計や価格安定化策の検討に示唆を与える。
In the global GX context
Carbon price forecasting is crucial for emissions trading market stability and investment decisions globally. This paper introduces a novel hybrid model that achieves high accuracy using only price data, which is particularly valuable for emerging carbon markets with limited data. The method's transferability offers insights for markets like the EU ETS, China's national ETS, and others seeking robust short-term forecasting tools.
👥 読者別の含意
🔬研究者:Provides a novel hybrid forecasting method (TCN-LSTM with multi-scale decomposition) and empirical evidence from a Chinese regional carbon market.
🏢実務担当者:Traders and compliance officers in carbon markets can leverage such models for short-term price predictions to inform trading strategies.
🏛政策担当者:Highlights the importance of accurate price forecasting for market stability and can inform the design of carbon pricing mechanisms.
📄 Abstract（原文）
The carbon allowance price series exhibits nonlinearity, non-stationarity, and high noise due to multiple factors. Accurate forecasting is crucial to the stability of the carbon market and to resource allocation. This paper proposes a forecasting framework using multi-scale decomposition and a TCN–LSTM hybrid model. First, the original carbon allowance price series is decomposed using CEEMDAN optimized by PSO. Then, VMD performs secondary decomposition of complex components based on sample entropy. Next, transfer entropy identifies causal relationships between each component and the original series, enabling reconstruction based on causality. Finally, a TCN–LSTM model uses reconstructed sequences to forecast carbon prices. The method achieves high-precision short-term forecasts using only the carbon allowance price series, avoiding reliance on external variables. Empirical results on the Hubei carbon market show an optimal lag of 3, with R2 = 0.8873, outperforming the single LSTM and TCN models and achieving a lower RMSE. The forecast using January–March 2026 data shows stable carbon prices with slight fluctuations. This study provides a reliable method for data-constrained short-term carbon price forecasting, supporting decision-making and policy assessment.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.3390/app16104758first seen 2026-05-17 07:24:10 · last seen 2026-05-20 05:16:29
🔔 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。