Data-driven approach for port resilience evaluation
Data-driven approach for port resilience evaluation
As pivotal nodes in international trade, ports have faced unprecedented challenges, particularly in the context of the COVID-19 pandemic. From the perspective of port congestion, this study investigates port resilience based on a quantitative approach. Port resilience is specifically evaluated using five novel metrics derived from resilience capacities and port congestion indexes, employing data-driven approaches, which are then applied to analyze nine global ports across six regions. The findings of the study indicate that: 1) The ports of Southampton and Shanghai display better resilience levels, whereas New York/New Jersey and Los Angeles/Long Beach show poorer resilience performance during the research period. 2) Ports in West Coast North America demonstrate relatively low resilience levels, while those in South East Asia showcase superior resilience. 3) The changing dynamics and evolution of port resilience rankings across different years underscore the multifaceted nature of port resilience and its capacity to adapt to external factors such as global events. Our study emphasizes the importance of quantifying port resilience, with a specific focus on port congestion. It provides valuable insights that have significant implications for port management and disaster preparedness within the maritime industry.
Data-driven, Machine learning, Port congestion, Port resilience, Resilience metric
Gu, Bingmei
80136101-cef9-4089-82d4-b027561bcf49
Liu, Jiaguo
68736016-ee48-4fe6-a9e5-6f08e69dffa4
Ye, Xiaoheng
0eff21d7-6465-4915-aff8-4e5d7457a0b5
Gong, Yu
86c8d37a-744d-46ab-8b43-18447ccaf39c
Chen, Jihong
8250a1d0-e8d7-44dd-b84d-60512e8ca137
8 May 2024
Gu, Bingmei
80136101-cef9-4089-82d4-b027561bcf49
Liu, Jiaguo
68736016-ee48-4fe6-a9e5-6f08e69dffa4
Ye, Xiaoheng
0eff21d7-6465-4915-aff8-4e5d7457a0b5
Gong, Yu
86c8d37a-744d-46ab-8b43-18447ccaf39c
Chen, Jihong
8250a1d0-e8d7-44dd-b84d-60512e8ca137
Gu, Bingmei, Liu, Jiaguo, Ye, Xiaoheng, Gong, Yu and Chen, Jihong
(2024)
Data-driven approach for port resilience evaluation.
Transportation Research Part E: Logistics and Transportation Review, 186, [103570].
(doi:10.1016/j.tre.2024.103570).
Abstract
As pivotal nodes in international trade, ports have faced unprecedented challenges, particularly in the context of the COVID-19 pandemic. From the perspective of port congestion, this study investigates port resilience based on a quantitative approach. Port resilience is specifically evaluated using five novel metrics derived from resilience capacities and port congestion indexes, employing data-driven approaches, which are then applied to analyze nine global ports across six regions. The findings of the study indicate that: 1) The ports of Southampton and Shanghai display better resilience levels, whereas New York/New Jersey and Los Angeles/Long Beach show poorer resilience performance during the research period. 2) Ports in West Coast North America demonstrate relatively low resilience levels, while those in South East Asia showcase superior resilience. 3) The changing dynamics and evolution of port resilience rankings across different years underscore the multifaceted nature of port resilience and its capacity to adapt to external factors such as global events. Our study emphasizes the importance of quantifying port resilience, with a specific focus on port congestion. It provides valuable insights that have significant implications for port management and disaster preparedness within the maritime industry.
Text
Data-driven approach for port resilience evaluation
- Accepted Manuscript
Restricted to Repository staff only until 8 May 2027.
Request a copy
More information
Accepted/In Press date: 3 May 2024
e-pub ahead of print date: 8 May 2024
Published date: 8 May 2024
Keywords:
Data-driven, Machine learning, Port congestion, Port resilience, Resilience metric
Identifiers
Local EPrints ID: 492216
URI: http://eprints.soton.ac.uk/id/eprint/492216
ISSN: 1366-5545
PURE UUID: 48f26875-c753-4f5e-8a16-2b8c7c3ba94e
Catalogue record
Date deposited: 22 Jul 2024 16:41
Last modified: 23 Jul 2024 01:53
Export record
Altmetrics
Contributors
Author:
Bingmei Gu
Author:
Jiaguo Liu
Author:
Xiaoheng Ye
Author:
Jihong Chen
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics