收藏切换
Research on carbon emission prediction of transportation industry based on MVMD decomposition
收藏切换
Qing-rong WANG1, Xin-kang LIU1, *, Chang-feng ZHU2, Jun-jie WANG1
China Environmental Science | 2026, 46(3) : 1725 - 1735
Less
收藏切换
China Environmental Science | 2026, 46(3): 1725-1735
• Carbon Emission Control •
Research on carbon emission prediction of transportation industry based on MVMD decomposition
Full
Qing-rong WANG1, Xin-kang LIU1, *, Chang-feng ZHU2, Jun-jie WANG1
Affiliations
  • 1.School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
  • 2.School of Transportation, Lanzhou Jiaotong University, Lanzhou 730070, China
Published: 2026-03-20
Outline
收藏切换

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 10.31×106t, 106.35×106t, and 0.97%, respectively, outperforming other comparative models and confirming its effectiveness.

multivariate variational mode decomposition  /  differential multi-head attention mechanism  /  traffic crbon eission pediction  /  smple etropy  /  model otimization
王庆荣, 刘心康, 朱昌锋, 王俊杰. 基于MVMD分解的交通运输业碳排放预测. 中国环境科学, 2026 , 46 (3) : 1725 -1735 .
Qing-rong WANG, Xin-kang LIU, Chang-feng ZHU, Jun-jie WANG. Research on carbon emission prediction of transportation industry based on MVMD decomposition[J]. China Environmental Science, 2026 , 46 (3) : 1725 -1735 .
Year 2026 volume 46 Issue 3
60
16
Cite this Article
BibTeX
Article Info
  • Receive Date:2025-08-03
  • Online Date:2026-10-08
  • Published:2026-03-20
Article Data
Affiliations
History
  • Received:2025-08-03
Funding
Affiliations
    1.School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
    2.School of Transportation, Lanzhou Jiaotong University, Lanzhou 730070, China
References
Share
https://castjournals.cast.org.cn/joweb/zghjkx/EN/
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT