Research on carbon emission prediction of transportation industry based on MVMD decomposition

WANG Qing-rong; LIU Xin-kang; ZHU Chang-feng; WANG Jun-jie

PDF(1966 KB)

China Environmental Science ›› 2026, Vol. 46 ›› Issue (3) : 1725-1735.

Carbon Emission Control

Research on carbon emission prediction of transportation industry based on MVMD decomposition

WANG Qing-rong¹, LIU Xin-kang¹, ZHU Chang-feng², WANG Jun-jie¹

Author information +

History +

Abstract

To address the issue of volatility and nonlinearity in carbon emission data sequences from the transportation sector affecting prediction accuracy,this study proposes a carbon emission prediction model that integrates Multivariate Variational Mode Decomposition (MVMD), differential multi-head attention mechanism,improved iTransformer,and LSTM enhanced by Sparrow Search Algorithm(SSA). First, MVMD was introduced to decompose the transportation carbon emission feature data sequence into modal components of different frequencies. Sample entropy was then used to quantify the complexity of each component, which was categorized into high- and low-frequency data based on entropy values, thereby further mitigating the volatility and nonlinearity of the carbon emission data sequence. Subsequently, SSA-LSTM was employed to predict low-frequency data, capturing long-range dependencies, while LSTM combined with the improved iTransformer was applied to rapidly denoise and fit high-frequency data to avoid interference with the primary trend. Finally, the prediction results of high- and low-frequency data were combined using weights calculated based on the sizes of sample entropy values. The model was validated using carbon emission data from China's transportation sector from 2000 to 2022. The results showed that the proposed model achieved a root mean square error (RMSE), mean square error (MSE), and mean absolute percentage error (MAPE) of 10.31x10⁶t, 106.35x10⁶t, and 0.97%, respectively, outperforming other comparative models and confirming its effectiveness.

Key words

multivariate variational mode decomposition / differential multi-head attention mechanism / traffic crbon eission pediction / smple etropy / model otimization

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

WANG Qing-rong, LIU Xin-kang, ZHU Chang-feng, WANG Jun-jie. Research on carbon emission prediction of transportation industry based on MVMD decomposition[J]. China Environmental Science. 2026, 46(3): 1725-1735

References

[1] Gao M Y, Yang H L, Xiao Q Z, et al. A novel method for carbon emission forecasting based on Gompertz's law and fractional grey model: evidence from American industrial sector [J]. Renewable Energy, 2022,181:803-819.
[2] 王雪亭,郑非凡,许野,等.双碳目标背景下宁夏地区碳达峰预测 [J]. 中国环境科学, 2023,43(S1):347-356. Wang X T, Zheng F F, Xu Y, et al. Prediction of carbon peak in Ningxia region under the background of dual carbon goals [J]. China Environmental Science, 2023,43(S1):347-356.
[3] 赵金辉,李景顺,王潘乐,等.基于Lasso-BP神经网络模型的河南省碳达峰路径研究 [J]. 环境工程, 2022,40(12):151-156,164. Zhao J H, Li J S, Wang P L, et al. Research on Henan Province's carbon peak path based on Lasso-BP neural network model [J]. Environmental Engineering, 2022,40(12):151-156,164.
[4] Yang H J, O'Connell J F. Short-term carbon emissions forecast for aviation industry in Shanghai [J]. Journal of Cleaner Production, 2020,275:122734/1-12.
[5] 胡茂峰,郑义彬,李宇涵.多情景下湖北省交通运输碳排放峰值预测研究 [J]. 环境科学学报, 2022,42(4):464-472. Hu M F, Zheng Y B, Li Y H. Forecast of carbon emission peak of transportation in Hubei Province under multiple scenarios [J]. Acta Scientiae Circumstantiae, 2022,42(4):464-472.
[6] 刘慧甜,胡大伟.基于机器学习的交通碳排放预测模型构建与分析 [J]. 环境科学, 2024,45(6):3421-3432. Liu H T, Hu D W. Construction and analysis of transportation carbon emission prediction model based on machine learning [J]. Environmental Science, 2024,45(6):3421-3432.
[7] 曾弘锐,孙文昊,何卫,等.基于机器学习的铁路隧道施工碳排放预测模型研究 [J]. 现代隧道技术, 2023,60(6):29-39. Zeng H R, Sun W H, He W, et al. Research on prediction model of carbon emission from railway tunnel construction based on machine learning [J]. Modern Tunnelling Technology, 2023,60(6):29-39.
[8] 陈亮,王金泓,何涛,等.基于SVR的区域交通碳排放预测研究 [J]. 交通运输系统工程与信息, 2018,18(2):13-19. Chen L, Wang J H, He T, et al. Prediction of regional transportation carbon emissions based on SVR [J]. Journal of Transportation Systems Engineering and Information Technology, 2018,18(2):13-19.
[9] 夏晓圣,陈菁菁,王佳佳,等.基于随机森林模型的中国PM_2.5浓度影响因素分析 [J]. 环境科学, 2020,41(5):2057-2065. Xia X S, Chen J J, Wang J J, et al. Analysis of influencing factors of PM_2.5 concentration in China based on random forest model [J]. Environmental Science, 2020,41(5):2057-2065.
[10] 金雨洁,金晓斌,洪星明,等.基于Lasso-Transformer神经网络模型的海南省碳排放预测 [J/OL]. 环境科学, 1-19[2025-07-07]. Jin Y J, Jin X B, Hong X M, et al. Carbon emission prediction in Hainan Province based on Lasso-Transformer neural network model [J/OL]. Environmental Science, 1-19[2025-07-07].
[11] 刘淳森,曲建升,葛钰洁,等.基于LSTM模型的中国交通运输业碳排放预测 [J]. 中国环境科学, 2023,43(5):2574-2582. Liu C S, Qu J S, Ge Y J, et al. Prediction of carbon emissions from China's transportation sector based on LSTM model [J]. China Environmental Science, 2023,43(5):2574-2582.
[12] 高金武,贾志桓,王向阳,等.基于PSO-LSTM的质子交换膜燃料电池退化趋势预测 [J]. 吉林大学学报(工学版), 2022,52(9):2192-2202. Gao J W, Jia Z H, Wang X Y, et al. Degradation trend prediction of proton exchange membrane fuel cell based on PSO-LSTM [J]. Journal of Jilin University (Engineering and Technology Edition), 2022,52(9): 2192-2202.
[13] 汪恩良,田雨,刘兴超,等.基于WOA-BP神经网络的超低温冻土抗压强度预测模型研究 [J]. 力学学报, 2022,54(4):1145-1153. Wang E L, Tian Y, Liu X C, et al. Prediction model of compressive strength of ultra-low temperature frozen soil based on WOA-BP neural network [J]. Chinese Journal of Theoretical and Applied Mechanics, 2022,54(4):1145-1153.
[14] 祖林禄,柳平增,赵妍平,等.基于SSA-LSTM的日光温室环境预测模型研究 [J]. 农业机械学报, 2023,54(2):351-358. Zu L L, Liu P Z, Zhao Y P, et al. Research on environmental prediction model of solar greenhouse based on SSA-LSTM [J]. Transactions of the Chinese Society for Agricultural Machinery, 2023,54(2):351-358.
[15] 杨俊祺,范晓军,赵跃华,等.基于PSO-BP神经网络的山西省碳排放预测 [J]. 环境工程技术学报, 2023,13(6):2016-2024. Yang J Q, Fan X J, Zhao Y H, et al. Prediction of carbon emissions in Shanxi Province based on PSO-BP neural network [J]. Journal of Environmental Engineering Technology, 2023,13(6):2016-2024.
[16] 王庆荣,王俊杰,朱昌锋,等.基于BWO-VMD-ISSA-LSTM的交通运输业碳排放预测研究 [J/OL]. 计算机工程与应用, 1-16[2025-07-07]. Wang Q R, Wang J J, Zhu C F, et al. Research on carbon emission prediction of transportation industry based on BWO-VMD-ISSA- LSTM [J/OL]. Computer Engineering and Applications, 1-16[2025-07-07].
[17] 张新生,聂达文,陈章政.基于MIC特征提取与ICEEMD-RIME- DHKELM的建筑业碳排放预测模型 [J]. 环境工程, 2025,43(4): 46-58. Zhang X S, Nie D W, Chen Z Z. Prediction model of construction industry carbon emissions based on MIC feature extraction and ICEEMD-RIME-DHKELM [J]. Environmental Engineering, 2025,43 (4):46-58.
[18] 张玉敏,孙猛,吉兴全,等.基于模态分解与多任务学习模型的综合能源系统多元负荷短期预测 [J]. 高电压技术, 2025,51(7):3488- 3499. Zhang Y M, Sun M, Ji X Q, et al. Short-term multi-load forecasting for integrated energy system based on modal decomposition and multi-task learning model [J]. High Voltage Engineering, 2025,51(7): 3488-3499.
[19] Zhang H, Kong X, Ren C. Influencing factors and forecast of carbon emissions from transportation taking Shandong province as an example [J]. IOP Conference Series: Earth and Environmental Science, 2019,300(3):032063/1-7.
[20] Quan C, Cheng X, Yu S, et al. Analysis on the influencing factors of carbon emission in China’s logistics industry based on LMDI method [J]. The Science of the Total Environment, 2020,2020(734):138473/1-12.
[21] 王庆荣,王俊杰,朱昌锋,等.基于SD-ISSA-DALSTM的交通运输业碳排放预测 [J]. 华南理工大学学报(自然科学版), 2025,53(5): 66-81. Wang Q R, Wang J J, Zhu C F, et al. Carbon emission prediction of transportation industry based on SD-ISSA-DALSTM [J]. Journal of South China University of Technology (Natural Science Edition), 2025,53(5):66-81.
[22] 李姗姗,费翔,董洪光,等.基于LMDI和LEAP模型的山西省碳排放影响因素及预测 [J]. 中国环境科学, 2025,45(7):4052-4063. Li S S, Fei X, Dong H G, et al. Factors influencing and projection of carbon emissions in Shanxi Province based on LMDI and LEAP models [J]. China Environmental Science, 2025,45(7):4052-4063.
[23] 王火根,汪钰婷,肖丽香.基于IO-SDA法的2020~2060年中国行业CO₂排放预测与分析 [J]. 中国环境科学, 2024,44(3):1743-1755. Wang H G, Wang Y T, Xiao L X, et al. Projection and analysis of China’s sectoral CO₂ emissions from 2020 to 2060 based on IO-SDA method [J]. China Environmental Science, 2024,44(3):1743-1755.
[24] IPCC. 2006IPCC Guidelines for National Greenhouse Gas Inventories [R]. Cambridge: Cambridge University Press, 2006.
[25] 张新生,张红文,聂达文.基于二次分解与MAML-MHA-DELM的电力行业碳排放预测模型研究 [J/OL]. 安全与环境学报, 1-15[2025- 08-31]. Zhang X S, Zhang H W, Nie D W. Research on carbon emission prediction model of power industry based on quadratic decomposition and MAML-MHA-DELM [J/OL]. Journal of Safety and Environment, 1-15[2025-08-31].
[26] 杨青,江宇航,吴婵媛,等.基于CNN-LSTM-Attention的中国省域交通运输业碳达峰预测研究 [J/OL]. 安全与环境学报, 1-12[2025- 08-31]. Yang Q, Jiang Y H, Wu C Y, et al. Prediction of carbon peak in China's provincial transportation industry based on CNN-LSTM-Attention [J/OL]. Journal of Safety and Environment, 1-12[2025-08-31].
[27] 张雯,吴志彬,徐玖平.基于EMD-PSO-LSSVM的碳排分解集成预测方法 [J]. 控制与决策, 2022,37(7):1837-1846. Zhang W, Wu Z B, Xu J P. Decomposition ensemble prediction method for carbon emissions based on EMD-PSO-LSSVM [J]. Control and Decision, 2022,37(7):1837-1846.