EUVIMEDEUVIMED entdecken
Crossref

Local XGBoost Ensemble for Station-Level Ridership Prediction: Modeling Built Environment and Spatial Heterogeneity

Xinyu Hu, Cong Qi, Yunpeng Zhao, Weiqi Zhang, Zhenjun Zhu, Kunyang Li

Journal of Transportation Engineering, Part A: Systems · 01.10.2026 · 152 (10)

DOI: 10.1061/jtepbs.teeng-9908 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Transportation Engineering, Part A: Systems, erschienen am 01.10.2026. Verfasst von Xinyu Hu und 5 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate metro ridership prediction is crucial for transit planning, particularly as urban rail networks expand and travel patterns vary across different travel scenarios. Existing models often rely on historical ridership data and may have limited adaptability to temporal and spatial heterogeneity. This study proposes a spatial proximity weighted eXtreme gradient boosting (XGBoost) ensemble to predict daily metro ridership under holidays, weekdays, and weekends. By integrating built environment variables and spatial adjacency, the proposed framework constructs local subdata sets using a nearest-neighbor approach and independently trains submodels. The model reduces dependence on continuous historical ridership sequences and is suitable for limited-data conditions. Using urban rail transit (URT) data from Nanjing, the proposed framework is compared with multiscale geographically weighted regression (MGWR) and global XGBoost. The results show that it achieves higher prediction accuracy in terms of R 2 , mean absolute error (MAE), and root mean squared error (RMSE). Feature importance analysis confirms the model’s interpretability, revealing temporal differences in the effects of variables. The proposed method effectively captures spatiotemporal heterogeneity in ridership dynamics, providing strong generalizability and practical value for urban transit planning and demand forecasting.

Zitieren

APA

Hu, X., Qi, C., Zhao, Y., Zhang, W., Zhu, Z., & Li, K. (2026). Local XGBoost Ensemble for Station-Level Ridership Prediction: Modeling Built Environment and Spatial Heterogeneity. Journal of Transportation Engineering, Part A: Systems, 152(10). https://doi.org/10.1061/jtepbs.teeng-9908

Vancouver

Hu X, Qi C, Zhao Y, Zhang W, Zhu Z, Li K. Local XGBoost Ensemble for Station-Level Ridership Prediction: Modeling Built Environment and Spatial Heterogeneity. Journal of Transportation Engineering, Part A: Systems. 2026;152(10). doi:10.1061/jtepbs.teeng-9908

BibTeX
@article{Hu2026,
  author = {Hu, Xinyu and Qi, Cong and Zhao, Yunpeng and Zhang, Weiqi and Zhu, Zhenjun and Li, Kunyang},
  title = {Local XGBoost Ensemble for Station-Level Ridership Prediction: Modeling Built Environment and Spatial Heterogeneity},
  journal = {Journal of Transportation Engineering, Part A: Systems},
  year = {2026},
  volume = {152},
  number = {10},
  doi = {10.1061/jtepbs.teeng-9908}
}
Kostenlos starten →