A novel grey multivariate convolution model based on the improved marine predators algorithm for predicting fossil CO2 emissions in China
The effective prediction of fossil carbon dioxide (CO2) emissions provides a foundation for environmental protection authorities to make relevant management and decisions. CO2 emissions are influenced by various factors and exhibit a nonlinear and complex trend. First, the weighted conformable fract...
Gespeichert in:
Veröffentlicht in: | Expert systems with applications 2024-06, Vol.243, p.122865, Article 122865 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The effective prediction of fossil carbon dioxide (CO2) emissions provides a foundation for environmental protection authorities to make relevant management and decisions. CO2 emissions are influenced by various factors and exhibit a nonlinear and complex trend. First, the weighted conformable fractional accumulation (WCFA) method is proposed. WCFA is a generalized form of the existing weighted accumulation and conformable fractional order accumulation. A nonlinear discrete grey Bernoulli multivariate convolution model is introduced to model the sequences processed by WCFA. Then, an improved marine predators algorithm (IMPA) is obtained by improving the marine predators algorithm by the tent map and cosine control parameter. The performance of IMPA is verified by algorithm comparison experiments and Friedman test. The feasibility and predictive effectiveness of the proposed model is validated through three case studies. In prediction of fossil CO2 emissions in China, the fitting and prediction errors of the proposed model reach 1.1773% and 0.5402%, respectively. Finally, the total fossil CO2 emissions in China from 2022 to 2026 are predicted and analyzed. The results indicate a gradual decrease in fossil CO2 emissions over the next five years. Some reasonable suggestions are made based on the prediction results and sources of fossil CO2 emissions. |
---|---|
ISSN: | 0957-4174 1873-6793 |
DOI: | 10.1016/j.eswa.2023.122865 |