A Novel Method for Predicting the Dynamics of Carbon Emissions for Air Transport Processes

• Main Authors: Liu, Jiaxue, Liu, Fangbin
• Format: Conference Proceeding
• Language: English
• Subjects: Air transport; Atmospheric modeling; Carbon dioxide; Carbon Emission Forecasting Models; Dynamic Forecasting; Heuristic algorithms; Least Squares Support Vector Machines; Prediction algorithms; Predictive models; Support vector machines; Time series analysis
• ISSN: 2161-2927
• DOI: 10.23919/CCC58697.2023.10240123

In order to improve the prediction accuracy of carbon dioxide emissions during air transport, a least squares support vector machine (LSSVM) based dynamic prediction method is proposed by analyzing the carbon emission process of aircraft flight time series, and the improved PSO method is constructed to optimize the LSSVM parameters so as to establish an improved PSO-LSSVM algorithm model. A horizontal and vertical two-dimensional driven dynamic prediction model is proposed to increase the prediction accuracy of carbon emissions. Finally, the effectiveness of the proposed method is verified by the actual data of passenger aircraft operation of an airline, and the accuracy and precision of the prediction results are compared with those of traditional BP and LSSVM. The simulation results show that the improved PSO-LSSVM model has better generalization ability and higher prediction accuracy. Its significance has important practical application value and economic benefits for airlines to achieve carbon control and emission reduction targets and promote the development of green civil aviation.