Journal of Environmental Management, Journal Year: 2024, Volume and Issue: 369, P. 122275 - 122275
Published: Aug. 31, 2024
Language: Английский
Citations
8Dual-stream Transformer-attention fusion network for short-term carbon price prediction
Energy, Journal Year: 2024, Volume and Issue: unknown, P. 133374 - 133374
Published: Oct. 1, 2024
Language: Английский
Citations
4Tail Dependence of Liquidity and Volatility in Carbon Futures Market: Evidence From EU ETS
Managerial and Decision Economics, Journal Year: 2025, Volume and Issue: unknown
Published: April 28, 2025
ABSTRACT This study constructs liquidity and volatility indicators based on the four phases of EU ETS analyses tail dependence using Copula models. The results indicate strong between in fourth phase. Amihud illiquidity ratio combined with stochastic model identifies high risks during scarcity, while Gibbs measure low risks. robustness is tested by classifying different periods structural breaks assessing dependence, applying machine learning algorithms to remove outliers before measuring dependence.
Language: Английский
Citations
0Carbon Price Point–Interval Forecasting Based on Two-Layer Decomposition and Deep Learning Combined Model Using Weight Assignment
Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: unknown, P. 144124 - 144124
Published: Oct. 1, 2024
Language: Английский
Citations
0TFR: A Temporal Feature‐Refined Multi‐Stage Carbon Price Forecasting
Energy Science & Engineering, Journal Year: 2024, Volume and Issue: unknown
Published: Dec. 17, 2024
ABSTRACT Accurate carbon price forecasting is crucial for effective market analysis and decision‐making. We propose a novel Temporal Feature‐Refined (TFR) model to address the challenges of complex dependencies high noise levels in time series data. The TFR integrates Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) signal decomposition, an Autoencoder feature optimization, Convolutional Network (TCN) capturing long‐range temporal dependencies. It incorporates both traditional economic factors unconventional determinants such as air quality, policy uncertainty, public sentiment. Experiments on Shanghai trading demonstrate that significantly outperforms existing methods, achieving 83.96% improvement MAE over Support Vector Regression (SVR) up 65.56% Long Short‐Term Memory (LSTM) networks. Further analyses, including comparisons different decomposition models ablation studies, confirm effectiveness each component overall model.
Language: Английский
Citations
0Carbon price prediction model based on EMD-ARMA-GRACH
Published: Oct. 18, 2024
Language: Английский
Citations
0