EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DK-VCA Net: A Topography-Aware Dual-Decomposition Framework for Mountain Traffic Flow Forecasting

Chuanhe Shi, Shuai Fu, Zhen Zeng, Nan Zheng, Haizhou Cheng, Xu Lei

Information · 24.04.2026 · 17 (5) · 407

DOI: 10.3390/info17050407 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 24.04.2026. Verfasst von Chuanhe Shi und 5 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: 2023 Opening Research Fund of Yunnan Key Laboratory ofDigital Communications, 2023 Opening Research Fund of Yunnan Key Laboratory of Digital Communications, Yunnan Province 546 Science and Technology Talents andPlatform Plan.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traffic flow prediction is important for traffic management and safety control in mountainous areas. In these environments, traffic flow is affected by complex terrain, changing weather, and mixed vehicle types, so the resulting time series often show strong fluctuation and poor stability. Many existing prediction models were developed for urban roads or flat highways, and their performance is therefore limited in mountainous scenarios. To address this problem, this paper proposes a hybrid model called DK-VCA Net. The model combines adaptive signal decomposition with a terrain-aware deep learning structure to separate useful traffic variation from complex noise. It also integrates traffic flow, speed, slope, and weather information to better describe mountain traffic conditions. The proposed method is evaluated using real traffic data collected at 5 min intervals from detection stations on the Guibi Expressway in Guizhou Province, China, during September 2020. Experimental results show that DK-VCA Net achieves better prediction accuracy than several representative baseline models, including 1D-CNN, LSTM, Transformer, STWave, and Mamba. Across the 15 min, 30 min, and 60 min forecasting tasks, the proposed model reduces the average RMSE by 14.8% compared with the conventional 1D-CNN model and by 8.9% compared with the baseline Transformer model. The ablation study further proves the effectiveness of the decomposition strategy, terrain-related features, and the attention mechanism. The results show that the proposed method is effective for traffic flow prediction in the studied mountainous highway scenario.

Förderung

  • 2023 Opening Research Fund of Yunnan Key Laboratory ofDigital Communications
  • 2023 Opening Research Fund of Yunnan Key Laboratory of Digital Communications
  • Yunnan Province 546 Science and Technology Talents andPlatform Plan
  • science and technology 547 research project of YCIC, China

Zitieren

APA

Shi, C., Fu, S., Zeng, Z., Zheng, N., Cheng, H., & Lei, X. (2026). DK-VCA Net: A Topography-Aware Dual-Decomposition Framework for Mountain Traffic Flow Forecasting. Information, 17(5), 407. https://doi.org/10.3390/info17050407

Vancouver

Shi C, Fu S, Zeng Z, Zheng N, Cheng H, Lei X. DK-VCA Net: A Topography-Aware Dual-Decomposition Framework for Mountain Traffic Flow Forecasting. Information. 2026;17(5):407. doi:10.3390/info17050407

BibTeX
@article{Shi2026,
  author = {Shi, Chuanhe and Fu, Shuai and Zeng, Zhen and Zheng, Nan and Cheng, Haizhou and Lei, Xu},
  title = {DK-VCA Net: A Topography-Aware Dual-Decomposition Framework for Mountain Traffic Flow Forecasting},
  journal = {Information},
  year = {2026},
  volume = {17},
  number = {5},
  pages = {407},
  doi = {10.3390/info17050407}
}
Kostenlos starten →