Collision risk assessment for ships’ routeing waters: An information entropy approach with Automatic Identification System (AIS) data

The ship's routing was adopted to organise marine traffic flow and reduce the risk of collision between ships in crowded waters. With the expansion of the world's fleet, ship traffic in shipping bottleneck and chokepoint areas became more and more busy and complex creating serious challeng...

Descripción completa

Detalles Bibliográficos
Autores: Feng, Hongxiang, Grifoll Colls, Manel|||0000-0003-4260-6732, Yang, Zhongzhen, Zheng, Pengjun
Tipo de recurso: artículo
Fecha de publicación:2022
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/380402
Acceso en línea:https://hdl.handle.net/2117/380402
https://dx.doi.org/10.1016/j.ocecoaman.2022.106184
Access Level:acceso abierto
Palabra clave:Nautical instruments
Automatic identification system (AIS)
Ship collision risk assessment
Information entropy
K-means clustering
Ningbo-zhoushan port
Navegació--Aparells i instruments
Navegació--Accidents
Àrees temàtiques de la UPC::Nàutica::Navegació marítima::Instrumentació i equipament per a la navegació
Àrees temàtiques de la UPC::Nàutica::Seguretat marítima::Accidents marítims
Descripción
Sumario:The ship's routing was adopted to organise marine traffic flow and reduce the risk of collision between ships in crowded waters. With the expansion of the world's fleet, ship traffic in shipping bottleneck and chokepoint areas became more and more busy and complex creating serious challenges for navigational safety. Therefore, quantitative collision risk assessment is significantly important for the ships' routeing waters. In this paper, the information entropy method which integrates the K-means clustering based on Automatic Identification System (AIS) data is introduced to quantitatively evaluate the collision risks in the ships' routeing waters. As a case study, the information entropy of Courses Over Ground (COG) for Ningbo-Zhoushan Port (the largest port in the world since 2009) is calculated by using historical AIS data. Then the K-means clustering is used to group the bytes of information entropy of the different legs in the shipping route. We find that in Ningbo-Zhoushan port Precautionary Area (PA) 2, 4 and 7 are the highest risk legs; PA 1, 5 and 6, Traffic Separation Scheme (TSS) 16, and 17 are medium-high risk areas. Therefore, ship collision risk prevention measures should be prioritised in those legs. Our contributions provide a novel approach to quantitatively assess ship collision risks in busy waters.