Carbon Price Point and Interval-Valued Prediction Based on a Novel Hybrid Model

Energies, Год журнала: 2025, Номер 18(5), С. 1054 - 1054

Опубликована: Фев. 21, 2025

Accurate carbon price forecasting enables the steady operation of trading market and optimal resource allocation while also empowering participants to understand dynamics make informed decisions, ultimately supporting sustainable development in market. While early research primarily focused on point single-value price, recent studies have shifted towards interval prediction, although there is still a lack dedicated developing models for interval-valued predictions. The importance lies its ability better capture upper lower bounds range across different time dimensions, thereby revealing intrinsic patterns trends fluctuations assisting comprehensively volatility. This study offers novel approach based CEEMDAN-CNN-BiLSTM-SENet hybrid model, providing framework both model makes more comprehensive analysis possible by combining predictions from these two approaches. In case using Hubei market’s data, mean absolute percentage error pricing was 0.8125%, with MAPE highest lowest prices being 1.8898% 1.7852%, respectively—both outperforming other comparative models. results demonstrate that this can measure effectively.

Язык: Английский

---

Assessment of urban flood susceptibility based on a novel integrated machine learning method

Environmental Monitoring and Assessment, Год журнала: 2024, Номер 197(1)

Опубликована: Дек. 5, 2024

Язык: Английский

---

Group dynamic game under bounded rationality in agreed transfer of China’s carbon trading secondary market

Computers & Industrial Engineering, Год журнала: 2025, Номер unknown, С. 110857 - 110857

Опубликована: Янв. 1, 2025

Язык: Английский

---

Carbon price prediction based on multidimensional association rules and optimized multi-factor LSTM model

Energy, Год журнала: 2025, Номер unknown, С. 136768 - 136768

Опубликована: Май 1, 2025

Язык: Английский

---