Predict Port Throughput Based on Probabilistic Forecast Model

  • Yihan Chen
  • Zhonghua Jin
  • Xuejun LiuEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 699)


When the service region of ports overlap, consignors’ selecting behaviors for shipping ports become homogeneous to commuters’ choosing behaviors on trips. The commuters’ travel behaviors can be described through a probabilistic model in transportation planning. In this study, we adopt the transportation probabilistic forecast model to forecast port throughput. First, we amend the model with a port attraction coefficient to forecast port throughput distributions between different ports. Then, forecast for each port throughput is obtained by reallocation of regional total port throughput to each nearby port. We use the port of Fuyang as an empirical research in this paper to validate the methodology. Results compared between this method and traditional regression model indicate that this method provides more persuasive reasoning.


Port throughput Probabilistic forecast model Port attraction coefficient Cargo distribution 



This research is funded by the Natural Science Foundation of Hubei [grant number 2014CFB709] and the National Natural Science Foundation of China [grant number 51579182].


  1. 1.
    Chou, M.T., Lee, H.S., Lin, K.: A study of forecasting the volume of trans and the harbor operation for port of Kaohsiung. J. Marit. Sci. 12(2), 235–250 (2003)Google Scholar
  2. 2.
    Baumont, C., Ertur, C., Gallo, J.: Spatial analysis of employment and population density: the case of the agglomeration of Dijon 1999. Geogr. Anal. 36(2), 146–176 (2004)CrossRefGoogle Scholar
  3. 3.
    Wang, J.-M., Zhu, F.-Y., Sui, B.-W., Jiang, Z.-J.: Research on demand forecasting and development pattern of port logistics for Guangxi beibu gulf port. Logist. Sci-Tech 12, 26–28 (2010)Google Scholar
  4. 4.
    Chou, C.-C., Chu, C.-W., Liang, G.-S.: A modified regression model for forecasting the volumes of Taiwan’s import containers. Math. Comput. Model. 47(9), 797–807 (2008)CrossRefGoogle Scholar
  5. 5.
    de Gooijer, J.G., Klein, A.: Forecasting the Antwerp maritime steel traffic flow: a case study. J. Forecast. 8(4), 381–398 (1989)CrossRefGoogle Scholar
  6. 6.
    Wei, C.H., Yang, Y.C.: A study on transit containers forecast in Kaohsiung port: applying artificial neural networks to evaluating input variables. J. Chin. Inst. Transp. 11(3), 1–20 (1999)Google Scholar
  7. 7.
    Xie, G., Wang, S., Zhao, Y., Lai, K.K.: Hybrid approaches based on LSSVR model for container throughput forecasting: a comparative study. Appl. Soft Comput. 13(5), 2232–2241 (2013)CrossRefGoogle Scholar
  8. 8.
    Xiao, J., Xiao, Y., Fu, J., Lai, K.K.: A transfer forecasting model for container throughput guided by discrete PSO. J. Syst. Sci. Complex. 27(1), 181–192 (2014)CrossRefzbMATHGoogle Scholar
  9. 9.
    Xu, L., Wang, S.: Analysis and forecasting of port logistics based on TEI@I methodology. J. Transp. Syst. Eng. Inf. Technol. 12(1), 173–179 (2012)Google Scholar
  10. 10.
    Huang, A., Lai, K., Li, Y., Wang, S.: Forecasting container throughput of Qingdao port with a hybrid model. J. Syst. Sci. Complex. 28(1), 105–121 (2015)CrossRefzbMATHGoogle Scholar
  11. 11.
    Zang, W.Y., et al.: Freight volume prediction for Chongqing water transport based on gray Markov. Port & Waterw. Eng. 462(1), 30–33 (2012)Google Scholar
  12. 12.
    Linsheng, F., Jianxin, D., Hao, M., Qi, Z.: Throughput forecasting of fangcheng port based on TEI@I methodology. Logist. Technol. 34(10), 75–79 (2015)Google Scholar
  13. 13.
    Yuan, H., Xie, Y.: On port’s throughput probabmty forecasting model. Port & Waterw. Eng. 16(4), 28–30 (2007)Google Scholar
  14. 14.
    Liu, X., Chen, Y.: A modified probabilistic forecast model of port throughput based on accessibility. Electron. J. Geotech. Eng. 07(21), 4845–4854 (2016)Google Scholar
  15. 15.
    Wei, W., Jiqian, X., Tao, Y.: Urban Traffic Planning and It’s Application. Southeast University Press, Nanjing (1998)Google Scholar
  16. 16.
    Paper, Fuyang Evening: The 13th Five-Year Plan of Fuyang is Formulated. In ed. (2016)Google Scholar
  17. 17.
    Shang, J.: Research of Demand Analysis and Forecast for Comprehensive Transportation Hub. Southwest Jiaotong University, Chengdu (2014)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2017

Authors and Affiliations

  1. 1.School of Urban DesignWuhan UniversityWuhan CityChina
  2. 2.Department of Urban Planning and Environmental PolicyTexas Southern UniversityHoustonUSA

Personalised recommendations