Monitoring port congestion based on vessel stay behavior recognition: A case study of two US ports around COVID-19 pandemic
文献类型：期刊论文
| 作者 | Xin, Rui2; Zhu, Qianle2; Wang, Jiaoe1; Yang, Jian3; Pan, Jiale2 |
| 刊名 | JOURNAL OF TRANSPORT GEOGRAPHY
 |
| 出版日期 | 2026-04-01 |
| 卷号 | 132页码:104600 |
| 关键词 | Port congestion Automatic identification system (AIS) Vessel stay behavior COVID-19 Spatiotemporal evolution |
| ISSN号 | 0966-6923 |
| DOI | 10.1016/j.jtrangeo.2026.104600 |
| 产权排序 | 2 |
| 文献子类 | Article |
| 英文摘要 | Ports play a crucial role in maritime transportation, including cargo transshipment and ship maintenance. However, congestion hinders operational efficiency and disrupts the global supply chain. Vessel behavior provides near-real-time insights into port operations, making vessel-tracking data essential for understanding congestion dynamics. Currently, there is a lack of research on port congestion across different periods under the influence of external events, particularly in terms of accurately recognizing vessel behavior patterns. Therefore, this study proposes a research framework for identifying vessel stay behaviors and analyzing congestion using Automatic Identification System (AIS) data. By extracting spatiotemporal features of vessel trajectories and employing the eXtreme Gradient Boosting (XGBoost) classification model, this study accurately identifies anchoring and berthing behaviors. The framework designs indicators focusing on traffic flow, turnaround time, and congestion level to analyze port congestion dynamics. To this end, it is applied to real AIS data from the Ports of Los Angeles-Long Beach (LALB) and New York-New Jersey (NYNJ), analyzing the spatiotemporal evolution of port congestion across the COVID-19 pandemic phases. The findings highlight differing congestion characteristics and recovery patterns between the two ports, providing valuable insights for resource allocation and crisis response strategies. |
| URL标识 | 查看原文 |
| WOS关键词 | AIS DATA ; SYSTEM |
| WOS研究方向 | Business & Economics ; Geography ; Transportation |
| 语种 | 英语 |
| WOS记录号 | WOS:001695011700001 |
| 出版者 | ELSEVIER SCI LTD |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/220949]  |
| 专题 | 区域可持续发展分析与模拟院重点实验室_外文论文 |
| 通讯作者 | Wang, Jiaoe |
| 作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China; 2.Shandong Univ Sci & Technol, Coll Geodesy & Geomat, Qingdao 266590, Peoples R China; 3.Informat Engn Univ, Sch Geospatial informat, Zhengzhou 450052, Peoples R China |
| 推荐引用方式 GB/T 7714 | Xin, Rui,Zhu, Qianle,Wang, Jiaoe,et al. Monitoring port congestion based on vessel stay behavior recognition: A case study of two US ports around COVID-19 pandemic[J]. JOURNAL OF TRANSPORT GEOGRAPHY,2026,132:104600. |
| APA | Xin, Rui,Zhu, Qianle,Wang, Jiaoe,Yang, Jian,&Pan, Jiale.(2026).Monitoring port congestion based on vessel stay behavior recognition: A case study of two US ports around COVID-19 pandemic.JOURNAL OF TRANSPORT GEOGRAPHY,132,104600. |
| MLA | Xin, Rui,et al."Monitoring port congestion based on vessel stay behavior recognition: A case study of two US ports around COVID-19 pandemic".JOURNAL OF TRANSPORT GEOGRAPHY 132(2026):104600. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。