铁道运输与经济2024，Vol.46Issue(8)：49-57,9.DOI:10.16668/j.cnki.issn.1003-1421.2024.08.05
基于卷积神经网络的交通运输业碳排放预测研究
Transportation Carbon Emission Prediction Based on Convolutional Neural Network
摘要
Abstract
As one of the main sources of carbon emission,the low-carbon development of the transportation industry is of great practical significance for realizing China's double carbon goal.Based on the extended STIRPAT model,this paper selected the influencing factors of the transportation industry from five dimensions:population size,economic level,technology level,transportation level,and greening level.Then,according to the data of carbon emissions and influencing factors from 1997 to 2019,the paper built a convolutional neural network carbon emission prediction model.On this basis,the carbon emissions of the transportation industry in four municipalities were predicted under three different scenarios of low-carbon,baseline,and high-carbon.The results show that under the baseline scenario and the low-carbon scenario,the four municipalities all show an obvious trend of"fluctuation rising-peak-slow decline".However,under the high-carbon scenario,the four municipalities show a clear trend of continuous growth.Under the low-carbon scenario,the carbon peak time of the transportation industry of the four municipalities is earlier than 2030,and the peak value is significantly lower than that of the other two scenarios,which is more in line with the low-carbon development concept of the transportation industry.关键词
卷积神经网络/交通运输业/STIRPAT模型/影响因素/碳排放预测Key words
Convolutional Neural Network/Transportation Industry/STIRPAT Model/Influencing Factors/Carbon Emission Prediction分类
交通工程引用本文复制引用
焦柳丹,刘莹,吴雅,霍小森..基于卷积神经网络的交通运输业碳排放预测研究[J].铁道运输与经济,2024,46(8):49-57,9.基金项目
重庆市教委人文社会科学研究项目(23SKGH137) （23SKGH137）
