| 188 | 0 | 10 |
| 下载次数 | 被引频次 | 阅读次数 |
针对“一带一路”倡议背景下中欧贸易运输的碳达峰问题，基于2013—2022年中国与欧盟26国贸易的面板数据，采用多种机器学习算法构建不同预测模型对中欧贸易运输碳达峰情况进行预测。首先，基于STIRPAT模型使用Lasso回归筛选“一带一路”倡议下中欧贸易运输碳排放影响因素；其次，使用五个机器学习算法对“一带一路”倡议下中欧贸易运输碳排放进行仿真预测，并采用R2、RMSE、MAE作为模型的评价指标对比各算法预测精度，来选定最佳预测模型。结果表明，中国和欧盟各国的经济水平、人口规模、产业结构和能源结构是“一带一路”倡议下中欧贸易运输碳排放的主要影响因素，GWO-SVR算法表现最优，可以作为预测算法，在现有情景下，大多数欧盟国家与中国的贸易运输碳排放水平难以在2030年实现达峰，需要在政策上进行调整以推动中欧贸易运输碳达峰。
Abstract：In view of the problem of carbon peak in China-Europe trade and transportation under the background of the Belt and Road Initiative,based on the panel data of China’s trade with 26 EU countries from 2013 to 2022,this paper uses multiple machine learning algorithms to construct different prediction models to predict the situation of carbon peak in China-Europe trade and transportation.Firstly,using the STIRPAT model and Lasso regression,we screened the factors affecting carbon emissions in China-Europe trade and transportation under the Belt and Road Initiative;Secondly,five machine learning algorithms were used to simulate and predict the carbon emissions of China-Europe trade and transportation under the Belt and Road Initiative,and R2,RMSE,and MAE were used as evaluation metrics to compare the prediction accuracy of each algorithm and select the best prediction model.The results show that the economic level,population size,industrial structure and energy structure of China and EU countries are the main factors affecting the carbon emissions of China-EU trade and transportation under the Belt and Road Initiative.The GWO-SVR algorithm performs the best and can be used as a prediction algorithm.Under existing circumstances,it is difficult for most EU countries to achieve peak carbon emissions in trade transportation with China by 2030,and policy adjustments are needed to promote the peak of carbon emissions in Sino-European trade transportation.
[1]WU Y,CHEN C L,HU C.Does the Belt and Road initiative increase the carbon emission intensity of participating countries?[J].China & World Economy,2021,29(3):1-25.
[2]朱开伟，谭显春，顾佰和，等.“一带一路”共建国家低碳转型路径研究与气候合作建议[J].中国科学院院刊，2023，38(9)：1398-1406.
[3]韦志文，冯帆.数字贸易对碳排放的影响：基于“一带一路”沿线48国的经验证据[J].现代经济探讨，2023(8)：65-77.
[4]WANG Y Q,LIU J F,GUAN D B,et al.The volume of trade-induced cross-border freight transportation has doubled and led to 1.14 gigatons CO2 emissions in 2015[J].One Earth,2022,5(10):1165-1177.
[5]CRISTEA A,HUMMELS D,PUZZELLO L,et al.Trade and the greenhouse gas emissions from international freight transport[J].Journal of environmental economics and management,2013,65(1):153-173.
[6]TILLIG F,RINGSBERG J W,PSARAFTIS H N,et al.Reduced environmental impact of marine transport through speed reduction and wind assisted propulsion[J].Transportation Research Part D:Transport and Environment,2020,83:102380.
[7]TRAUT M,LARKIN A,ANDERSON K,et al.CO2 abatement goals for international shipping[J].Climate Policy,2018,18(8):1066-1075.
[8]CHENG Z,ZHAO L,WANG G,et al.Selection of consolidation center locations for China Railway express to reduce greenhouse gas emission[J].Journal of Cleaner Production,2021,305:126872.
[9]李创，昝东亮.基于LMDI分解法的我国运输业碳排放影响因素实证研究[J].资源开发与市场，2016，32(5)：518-521.
[10]LIN B,BENJAMIN N I.Influencing factors on carbon emissions in China transport industry.A new evidence from quantile regression analysis[J].Journal of Cleaner Production,2017,150:175-187.
[11]李颖.基于LMDI的安徽省交通运输业碳排放影响因素分析[J].环境保护与循环经济，2019，39(5)：5-8.
[12]ZHU C Z,GAO D W.A research on the factors influencing carbon emission of transportation industry in “the Belt and Road initiative” countries based on panel data[J].Energies,2019,12(12):2405.
[13]QUAN C G,CHENG X J,YU S S,et al.Analysis on the influencing factors of carbon emission in China’s logistics industry based on LMDI method[J].Science of the Total Environment,2020,734:138473.
[14]王李轩，李蓁，何吉成，等.基于STIRPAT模型的陕西省交通运输业碳排放影响因素分析[J].交通运输研究，2022，8(6)：98-107.
[15]王世进，蒯乐伊.中国交通运输业碳排放驱动因素与达峰路径[J].资源科学，2022，44(12)：2415-2427.
[16]刘吉毅，黄福友，陈斌.交通运输业碳排放影响因素及减排策略研究[J].公路，2023，68(5)：252-259.
[17]孙佳，孙启鹏，高捷，等.碳达峰约束下的运输结构优化研究[J].生态经济，2023,39(11)：54-59.
[18]CHEN X,SHUAI C Y,WU Y,et al.Analysis on the carbon emission peaks of China’s industrial,building,transport,and agricultural sectors[J].Science of the Total Environment,2020,709:135768.
[19]WANG W,WANG J.Determinants investigation and peak prediction of CO2 emissions in China’s transport sector utilizing bio-inspired extreme learning machine[J].Environmental Science and Pollution Research,2021,28(39):55535-55553.
[20]朱长征，杨莎，刘鹏博，等.中国交通运输业碳达峰时间预测研究[J].交通运输系统工程与信息，2022，22(6)：291-299.
[21]WANG J K,WANG T L,SHAO X Y.Carbon emission forecast of China transport industry based on grey-Markov[C]//2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP).IEEE,2022:984-990.
[22]LI C,ZHANG Z C,WANG L P.Carbon peak forecast and low carbon policy choice of transportation industry in China:Scenario prediction based on STIRPAT model[J].Environmental Science and Pollution Research,2023,30(22):63250-63271.
[23]ZHU C Z,WANG M,DU W B.Prediction on peak values of carbon dioxide emissions from the Chinese transportation industry based on the SVR model and scenario analysis[J].Journal of Advanced Transportation,2020,2020(1):1-14.
[24]ZHAO Y M,DING H,LIN X F,et al.Carbon emissions peak in the road and marine transportation sectors in view of cost-benefit analysis:A case of Guangdong province in China[J].Frontiers in Environmental Science,2021,9:754162.
[25]EHRLICH P R,HOLDREN J.Impact of population growth:Complacency concerning this component of man’s predicament is unjustified and counterproductive[J].Science,1971,171:1212-1217.
[26]YORK R,ROSA E A,DIETZ T.STIRPAT,IPAT and IMPACT:Analytic tools for unpacking the driving forces of environmental impacts[J].Ecological Economics,2003,46(3):351-365.
[27]ZHAO Y H,LIU R R,LIU Z S,et al.A review of macroscopic carbon emission prediction model based on machine learning[J].Sustainability,2023,15(8):6876.
[28]MIRJALILI S,MIRJALILI S M,LEWIS A.Grey wolf optimizer[J].Advances in Engineering Software,2014,69:46-61.
[29]KONG F,SONG J B,YANG Z Z.A daily carbon emission prediction model combining two-stage feature selection and optimized extreme learning machine[J].Environmental Science and Pollution Research,2022,29(58):87983-87997.
[30]张新生，魏志臻，陈章政，等.基于LASSO-GWO-KELM的工业碳排放预测方法研究[J].环境工程，2023，41(10)：141-149.
[31]曾炜，方泽慧，张燕华.湖北省碳达峰情景预测：基于STIRPAT扩展模型[J].环境科学与技术，2023，46(S2)：226-232.
[32]CARONE G,DENIS C,MC MORROW K,et al.Long-term labour productivity and GDP projections for the EU25 member states:A production function framework[R].European Economy-Economic Papers,2006,253:1-92.
[33]陈赟，沈浩，王晓慧，等.基于Mann-Kendall趋势检验的城市能源碳达峰评估方法[J].上海交通大学学报，2023，53(7)：928-938.
[34]张立，谢紫璇，曹丽斌，等.中国城市碳达峰评估方法初探[J].环境工程，2020，38(11)：1-5.
[35]European Commission.White Paper:Roadmap to a single European transport area:Towards a competitive and resource efficient transport system[R].Brussels,2011.
[36]曾志宏.减碳!减碳!欧洲铁路货运的新目标新举措加强和公路货运竞争优势[EB/OL].(2022-05-10)[2025-04-26].https://zhuanlan.zhihu.com/p/512019099.
[37]南方周末中国企业社会责任研究中心.达峰难、达峰晚，交通行业绿色转型谁能率先突围?丨2024企业双碳行动力调研[EB/OL].(2024-11-28)[2025-04-26].https://mp.weixin.qq.com/s?__biz=MzAxNzI5NzQ4OQ==&mid=2653188365&idx=1&sn=51e16f3add34ff3419bbd275988664ba&chksm=81c82f4ae94d94c45c150872aea00a1f54140a4a683e42e221a7d4993236ad01b1f857fd722a&scene=27.
(1)欧洲联盟统计地理等级单元(nomenclature of territorial Units for statistics city，NUTS)是欧洲统计局用于统计和社会经济分析的地理单位命名系统，NUTS分为三个级别，其中NUTS1级别为最高级别。
基本信息:
DOI：
中图分类号:F752.7;F755;X322
引用信息:
[1]程兆麟,李艳丽,唐洪雷等.基于机器学习的“一带一路”倡议背景下中欧贸易运输碳达峰预测[J].生态经济,2025,41(06):41-53.
基金信息:
国家社会科学基金一般项目“我国‘一带一路’运输碳排放结构‘锁定’难题及解锁策略”(22BJY186)