Abstract
Accurately forecasting container port throughput over the medium-term is crucial for making informed investment decisions by companies. However, current methods suffer from poor accuracy in dealing with complex, non-linear fluctuations and time series of uncertain demand. This research presents a novel hybrid framework that combines deep learning techniques with the distinctive features of seaborne transport to tackle this problem. The proposed approach employs variational mode decomposition (VMD) for decomposing the initial time series, thereby addressing prediction errors caused by disturbances and abrupt changes in the original data. In addition, Particle Swarm Optimization (PSO) is utilized to optimize the selection of parameters for VMD, aiming to achieve optimal outcomes in the decomposition process. Gated Recurrent Units (GRU) are then employed to accurately predict each intrinsic mode function (IMF) generated by the VMD. To obtain the final forecasts, the predictions of each IMF component are aggregated. Our results indicate that the proposed model performs better in demand forecasts, compared to traditional methods. According to our experimental results, the VMD has better numerical stability, noise removal, physical significance, and computational efficiency compared to other decomposing methods such as Ensemble Empirical Mode Decomposition (EEMD). The forecast results can approximate the development paths of the Guangzhou, Qingdao and Shanghai ports. This can help port operators and policymakers to prepare themselves for possible market fluctuations in the medium term, and make comprehensive adjustments and managemental decisions, such as capacity planning, on time.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Al Hajj Hassan, L., H.S. Mahmassani, and Y. Chen. 2020. Reinforcement learning framework for freight demand forecasting to support operational planning decisions. Transportation Research Part E: Logistics and Transportation Review. https://doi.org/10.1016/j.tre.2020.101926.
Alexander, D.W., and R. Merkert. 2021. Applications of gravity models to evaluate and forecast US international air freight markets post-GFC. Transport Policy (Oxf) 104: 52–62. https://doi.org/10.1016/j.tranpol.2020.04.004.
Cuong, T.N., L.N.B. Long, H.-S. Kim, and S.-S. You. 2022. Data analytics and throughput forecasting in port management systems against disruptions: A case study of Busan Port. Maritime Economics & Logistics 25 (1): 61–89. https://doi.org/10.1057/s41278-022-00247-5.
Dong, L., Z. Chen, R. Hua, S. Hu, C. Fan, and X. Xiao. 2023. Research on diagnosis method of centrifugal pump rotor faults based on IPSO-VMD and RVM. Nuclear Engineering and Technology 55 (3): 827–838. https://doi.org/10.1016/j.net.2022.10.045.
Dragomiretskiy, K., and D. Zosso. 2014. Variational mode decomposition. IEEE Transactions on Signal Processing 62 (3): 531–544. https://doi.org/10.1109/tsp.2013.2288675.
Du, B., S. Huang, J. Guo, H. Tang, L. Wang, and S. Zhou. 2022. Interval forecasting for urban water demand using PSO optimized KDE distribution and LSTM neural networks. Applied Soft Computing. https://doi.org/10.1016/j.asoc.2022.108875.
Eseye, A.T., M. Lehtonen, T. Tukia, S. Uimonen, and R. John Millar. 2019. Machine learning based integrated feature selection approach for improved electricity demand forecasting in decentralized energy systems. IEEE Access 7: 91463–91475. https://doi.org/10.1109/access.2019.2924685.
Eskafi, M., M. Kowsari, A. Dastgheib, G.F. Ulfarsson, G. Stefansson, P. Taneja, and R.I. Thorarinsdottir. 2021. A model for port throughput forecasting using Bayesian estimation. Maritime Economics & Logistics 23 (2): 348–368. https://doi.org/10.1057/s41278-021-00190-x.
Fan, L., and J. Luo. 2012. Study on waterway freight volume forecast based on grey Markov. 2012 IEEE International Conference on Computer Science and Automation Engineering, 22–24 June 2012. https://ieeexplore.ieee.org/document/6269419/
Farhan, J., and G.P. Ong. 2018. Forecasting seasonal container throughput at international ports using SARIMA models. Maritime Economics & Logistics 20 (1): 131–148.
Feng, F., W. Li, and Q. Jiang. 2018. Railway freight volume forecast using an ensemble model with optimised deep belief network. IET Intelligent Transport Systems 12 (8): 851–859. https://doi.org/10.1049/iet-its.2017.0369.
Gao, T., D. Niu, Z. Ji, and L. Sun. 2022. Mid-term electricity demand forecasting using improved variational mode decomposition and extreme learning machine optimized by sparrow search algorithm. Energy. https://doi.org/10.1016/j.energy.2022.125328.
Garrido, R.A., and H.S. Mahmassani. 2000. Forecasting freight transportation demand with the space–time multinomial probit model. Transportation Research Part B: Methodological 34 (5): 403–418. https://doi.org/10.1016/S0191-2615(99)00032-6.
Gilles, J. 2013. Empirical wavelet transform. IEEE Transactions on Signal Processing 61 (16): 3999–4010. https://doi.org/10.1109/tsp.2013.2265222.
Guo, Y., Y. Luo, J. He, and Y. He. 2022. Real-time deep learning-based market demand forecasting and monitoring. Computers and Electrical Engineering. https://doi.org/10.1016/j.compeleceng.2022.107878.
Guo, Z., W. Le, Y. Wu, and W. Wang. 2019. A multi-step approach framework for freight forecasting of river-sea direct transport without direct historical data. Sustainability. https://doi.org/10.3390/su11154252.
Huang, A., X. Liu, C. Rao, Y. Zhang, and Y. He. 2022. A new container throughput forecasting paradigm under COVID-19. Sustainability. https://doi.org/10.3390/su14052990.
Huang, N.E., Z. Shen, S.R. Long, M.C. Wu, H.H. Shih, Q. Zheng, N.-C. Yen, C.C. Tung, and H.H. Liu. 1998. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences 454 (1971): 903–995. https://doi.org/10.1098/rspa.1998.0193.
Huang, Y.-T., Y.-L. Bai, Q.-H. Yu, L. Ding, and Y.-J. Ma. 2022. Application of a hybrid model based on the Prophet model, ICEEMDAN and multi-model optimization error correction in metal price prediction. Resources Policy 7: 9. https://doi.org/10.1016/j.resourpol.2022.102969.
Lee, S.-Y., H. Lim, and H.-J. Kim. 2017. Forecasting container port volume: Implications for dredging. Maritime Economics & Logistics 19 (2): 296–314. https://doi.org/10.1057/s41278-016-0054-4.
Li, G., and X. Zhong. 2023. Parking demand forecasting based on improved complete ensemble empirical mode decomposition and GRU model. Engineering Applications of Artificial Intelligence. https://doi.org/10.1016/j.engappai.2022.105717.
Li, H., J. Bai, and Y. Li. 2019. A novel secondary decomposition learning paradigm with kernel extreme learning machine for multi-step forecasting of container throughput. Physica A: Statistical Mechanics and its Applications. https://doi.org/10.1016/j.physa.2019.122025.
Li, H., X. Wu, T. Liu, S. Li, B. Zhang, G. Zhou, and T. Huang. 2022. Composite fault diagnosis for rolling bearing based on parameter-optimized VMD. Measurement. https://doi.org/10.1016/j.measurement.2022.111637.
Li, J., Z. Song, X. Wang, Y. Wang, and Y. Jia. 2022. A novel offshore wind farm typhoon wind speed prediction model based on PSO–Bi-LSTM improved by VMD. Energy. https://doi.org/10.1016/j.energy.2022.123848.
Li, W., J. Dai, Y. Xiao, S. Yang, and C. Song. 2021. Estimating waterway freight demand at Three Gorges ship lock on Yangtze River by backpropagation neuralnetwork modeling. Maritime Economics & Logistics 23 (3): 495–521. https://doi.org/10.1057/s41278-020-00169-0.
Li, Y., R.W. Liu, Z. Liu, and J. Liu. 2019. Similarity grouping-guided neural network modeling for maritime time series prediction. IEEE Access 7: 72647–72659. https://doi.org/10.1109/access.2019.2920436.
Liu, Q., M. Liu, H.L. Zhou, and F. Yan. 2022. A multi-model fusion based non-ferrous metal price forecasting. Resources Policy. https://doi.org/10.1016/j.resourpol.2022.102714.
Liu, X., Z. Wang, M. Li, C. Yue, S.Y. Liang, and L. Wang. 2021. Feature extraction of milling chatter based on optimized variational mode decomposition and multi-scale permutation entropy. The International Journal of Advanced Manufacturing Technology 114 (9–10): 2849–2862. https://doi.org/10.1007/s00170-021-07027-0.
Lu, J., J. Yue, L. Zhu, D. Wang, and G. Li. 2021. An improved variational mode decomposition method based on the optimization of salp swarm algorithm used for denoising of natural gas pipeline leakage signal. Measurement 18: 5. https://doi.org/10.1016/j.measurement.2021.110107.
Moscoso-López, J.A., I.J. Turias Turias, M.J. Come, J.J. Ruiz-Aguilar, and M. Cerbán. 2016. Short-term forecasting of intermodal freight using ANNs and SVR: case of the port of Algeciras Bay. Transportation Research Procedia 18: 108–114. https://doi.org/10.1016/j.trpro.2016.12.015.
Niu, M., Y. Hu, S. Sun, and Yu. Liu. 2018. A novel hybrid decomposition-ensemble model based on VMD and HGWO for container throughput forecasting. Applied Mathematical Modelling 57: 163–178. https://doi.org/10.1016/j.apm.2018.01.014.
Notteboom, Theo. 2022. Port economics, management and policy. New York: Routledge.
Rajeh, T.M., T. Li, C. Li, M.H. Javed, Z. Luo, and F. Alhaek. 2023. Modeling multi-regional temporal correlation with gated recurrent unit and multiple linear regression for urban traffic flow prediction. Knowledge-Based Systems. https://doi.org/10.1016/j.knosys.2022.110237.
Rashed, Y., H. Meersman, E. Van de Voorde, and T. Vanelslander. 2017. Short-term forecast of container throughout: An ARIMA-intervention model for the port of Antwerp. Maritime Economics & Logistics 19 (4): 749–764. https://doi.org/10.1057/mel.2016.8.
Ruiz-Aguilar, J.J., I.J. Turias, and M.J. Jiménez-Come. 2015. A novel three-step procedure to forecast the inspection volume. Transportation Research Part C: Emerging Technologies 56: 393–414. https://doi.org/10.1016/j.trc.2015.04.024.
Ruiz-Aguilar, J.J., D. Urda, J.A. Moscoso-López, J. González-Enrique, and I.J. Turias. 2020. A freight inspection volume forecasting approach using an aggregation/disaggregation procedure, machine learning and ensemble models. Neurocomputing 391: 282–291. https://doi.org/10.1016/j.neucom.2019.06.109.
Shankar, S., P.V. Ilavarasan, S. Punia, and S.P. Singh. 2019. Forecasting container throughput with long short-term memory networks. Industrial Management & Data Systems 120 (3): 425–441. https://doi.org/10.1108/imds-07-2019-0370.
Smith, J.S. 2005. The local mean decomposition and its application to EEG perception data. J R Soc Interface 2 (5): 443–54. https://doi.org/10.1098/rsif.2005.0058.
Tan, M., S. Yuan, S. Li, Y. Su, H. Li, and F.H. He. 2020. Ultra-short-term industrial power demand forecasting using LSTM based hybrid ensemble learning. IEEE Transactions on Power Systems 35 (4): 2937–2948. https://doi.org/10.1109/tpwrs.2019.2963109.
Tang, S., S. Xu, and J. Gao. 2019. An optimal model based on multifactors for container throughput forecasting. KSCE Journal of Civil Engineering 23 (9): 4124–4131. https://doi.org/10.1007/s12205-019-2446-3.
Tian, W., P. Zhao, and K. Qiao. 2019. Railway Freight Volume Forecast Based on GRA-WD-WNN. 2019 4th International Conference on Intelligent Transportation Engineering (ICITE), 5-7 Sept. 2019. https://doi.org/10.1109/ICITE.2019.8880238
Veenstra, A.W., and H.E. Haralambides. 2001. Multivariate autoregressive models for forecasting seaborne trade flows. Transportation Research Part E-Logistics and Transportation Review 37 (4): 311–319. https://doi.org/10.1016/S1366-5545(00)00020-X.
Wan, C., Y. Zhao, D. Zhang, and L. Fan. 2023. A system dynamics-based approach for risk analysis of waterway transportation in a mixed traffic environment. Maritime Policy & Management 1–23. https://doi.org/10.1080/03088839.2023.2224328.
Wang, D., J. Gan, J. Mao, F. Chen, and L. Yu. 2023. Forecasting power demand in China with a CNN-LSTM model including multimodal information. Energy. https://doi.org/10.1016/j.energy.2022.126012.
Wang, J., and Z. Cheng. 2021. Wind speed interval prediction model based on variational mode decomposition and multi-objective optimization. Applied Soft Computing. https://doi.org/10.1016/j.asoc.2021.107848.
Wang, J., X. Niu, L. Zhang, and M. Lv. 2021. Point and interval prediction for non-ferrous metals based on a hybrid prediction framework. Resources Policy. https://doi.org/10.1016/j.resourpol.2021.102222.
Wei, Y., and M.-C. Chen. 2012. Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks. Transportation Research Part C: Emerging Technologies 21 (1): 148–162. https://doi.org/10.1016/j.trc.2011.06.009.
Xiao, Y., X. Xue, Y. Hu, and M. Yi. 2023. Novel decomposition and ensemble model with attention mechanism for container throughput forecasting at four ports in Asia. Transportation Research Record: Journal of the Transportation Research Board 2677 (6): 530–547. https://doi.org/10.1177/03611981221149434.
Xie, G., Y. Qian, and H. Yang. 2018. Forecasting container throughput based on wavelet transforms within a decomposition-ensemble methodology: A case study of China. Maritime Policy & Management 46 (2): 178–200. https://doi.org/10.1080/03088839.2018.1476741.
Xie, G., N. Zhang, and S. Wang. 2017. Data characteristic analysis and model selection for container throughput forecasting within a decomposition-ensemble methodology. Transportation Research Part E: Logistics and Transportation Review 108: 160–178. https://doi.org/10.1016/j.tre.2017.08.015.
Yang, C.-H., J.-C. Shao, Y.-H. Liu, P.-H. Jou, and Y.-D. Lin. 2022. Application of fuzzy-based support vector regression to forecast of international airport freight volumes. Mathematics. https://doi.org/10.3390/math10142399.
Yang, F., X. Tang, Y. Gan, X. Zhang, J. Li, X. Han, and I. Ahmad. 2021. Forecast of freight volume in Xi’an based on Gray GM (1, 1) model and Markov forecasting model. Journal of Mathematics 2021: 1–6. https://doi.org/10.1155/2021/6686786.
Yang, H., Y. Cheng, and G. Li. 2022. A new traffic flow prediction model based on cosine similarity variational mode decomposition, extreme learning machine and iterative error compensation strategy. Engineering Applications of Artificial Intelligence. https://doi.org/10.1016/j.engappai.2022.105234.
Yu, N., W. Xu, and K.-L. Yu. 2020. Research on regional logistics demand forecast based on improved support vector machine: a case study of Qingdao City under the new free trade zone strategy. IEEE Access 8: 9551–9564. https://doi.org/10.1109/access.2019.2963540.
Zhang, J., M. Jin, C. Wan, Z. Dong, and X. Wu. 2024. A Bayesian network-based model for risk modeling and scenario deduction of collision accidents of inland intelligent ships. Reliability Engineering & System Safety 243: 109816. https://doi.org/10.1016/j.ress.2023.109816
Zhao, M., J.Y.J. Chow, and S.G. Ritchie. 2015. An inventory-based simulation model for annual-to-daily temporal freight assignment. Transportation Research Part E: Logistics and Transportation Review 79: 83–101. https://doi.org/10.1016/j.tre.2015.04.001.
Acknowledgements
This work is supported by the National Natural Science Foundation of China (Grant No. 51909202); the Young Elite Scientist Sponsorship Program by CAST (Grant No. 2021QNRC001); the Hainan Provincial Joint Project of Sanya Yazhou Bay Science and Technology City (Grant No. 2021JJLH0012); and the Innovation and entrepreneurship team import project of Shaoguan City (Grant Nos. 201212176230928). We would like to thank the anonymous reviewers of MEL who have helped to improve the work to a great extent.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, D., Li, X., Wan, C. et al. A novel hybrid deep-learning framework for medium-term container throughput forecasting: an application to China’s Guangzhou, Qingdao and Shanghai hub ports. Marit Econ Logist 26, 44–73 (2024). https://doi.org/10.1057/s41278-024-00284-2
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1057/s41278-024-00284-2