An advanced method for detecting possible near miss ship collisions from AIS data

Significance Statement

Marine transport is one of the important ways of developing an economy around the world, but involves financial and safety risk. Collisions and fires are the most frequent maritime accident types globally. There is a need to study the risks associated with these accidents and gain insight about the safety of maritime transportation.  A research team from the University of Washington in Seattle led by Dr. Weibin Zhang and Professor Yinhai Wang proposed an advanced method for detecting possible near miss ship collisions using Automatic Identification System (AIS) data. The research work is now published in peer-reviewed journal, Ocean Engineering. Other researchers contributed to the study were Dr. Floris Goerlandt and Professor Pentti Kujala from Aalto University in Finland.

According to the researchers, several risk analysis models and methodologies have been proposed for analyzing accident risk in maritime transportation and to rank the severity of collusion between two vessels based on distance between two ships, their relative speed, and the difference between their headings. Dr. Weibin Zhang the leading author in this study improved on his previous work (Zhang et al, Ocean Engineering 107, 60–69, 2015) by including the minimum distance to collision (MDTC) concept, which allows a better distinction of the risk levels at various encounter angles.

The research team uses data from the AIS, which is a system for information exchange between vessels and between vessels and shore facilities. They subjected the model into two tests, the discriminant and concurrent validity tests. The team stressed on the importance of ship size, this is because larger area are required for larger vessels to manoeuver.

In classifying the ship, they used clustering method to measure the length and breadth of the ship. To validate the newly developed vessel conflict ranking operator VCRO (Vessel Conflict Ranking Operator) model, the team carried out several validity tests.

According to the team, the new VCRO proposed is more reasonable than previous VCRO for considering the effect of ship size through a ship domain, and by better accounting for the criticality of the encounter direction through the MDTC concept.  The VCRO of two encountering vessels are found to be different due to the type of ship sizes, it will also affect the ship domain range and the safety distances. After observing the encounter severity, it is advised to retain only the maximum value of both VCRO values.

This study was able to successfully detect near miss ship-ship encounters on a coastal restricted and open sea area and the model developed by the authors was adequate to identify near misses information in making statements of maritime safety with a relation to collisions.  The most important aspect of the research undertaken was that the model can rank ship encounter conflicts without expert involvements. Nevertheless, the judgement whether the detected encounters qualify as near misses still needs to be based on expert knowledge.  

An advanced method for detecting possible near miss ship collisions from AIS data. Advances in Engineering

About the author

Yinhai Wang received the Master’s degree in computer science from University of Washington (UW), Seattle, WA, USA, and the Ph.D. degree in transportation engineering from University of Tokyo, Tokyo, Japan, in 1998.

He is a Professor in transportation engineering and the Founding Director of the Smart Transportation Applications and Research Laboratory (STAR Lab), University of Washington. He also serves as the Director for the Pacific Northwest Transportation Consortium (PacTrans), U.S. Department of Transportation University Transportation Center for Federal Region 10.

He has published over 100 peer-reviewed journal articles and delivered more than 110 invited talks and nearly 200 other academic presentations. His active research fields include traffic sensing, e-science of transportation, and transportation safety.

Dr. Wang is a member of the Transportation Information Systems and Technology Committee and the Highway Capacity and Quality of Service Committee of the Transportation Research Board. He is currently a member of the Steering Committee for the IEEE Smart Cities and chaired the First IEEE International Smart Cities Conference in 2015. He was an elected member of the Board of Governors for the IEEE Intelligent Transportation Systems Society from 2010 to 2013 and served on the Board of Governors for the ASCE Transportation and Development Institute during 2013–2015.

He is an Associate Editor of Journal of Intelligent Transportation Systems, Journal of Computing in Civil Engineering, and Journal of Transportation Engineering.

He was the winner of the ASCE Journal of Transportation Engineering Best Paper Award for 2003.  

About the author

Weibin Zhang received Ph.D. degree in automation from Xi’an Jiaotong University, China, in 2008. He has two years of postdoctoral research experience in Aalto University. From the end of 2014, he works as a research associate with the Department of Civil and Environmental Engineering, University of Washington, Seattle, WA.

His research interests are intelligent transportation systems, data-driven modeling, and marine safety. His current research focuses on application of big data in transportation, and machine learning techniques to transportation modeling, etc.  

Journal Reference

Weibin Zhang1, Floris Goerlandt2, Pentti Kujala2, Yinhai Wang1, an Advanced Method for Detecting Possible Near Miss Hip Collisions from AIS Data, Ocean Engineering124 (2016)141–156.

[expand title=”Show Affiliations”]
  1. University of Washington, Department of Civil and Environmental Engineering, Smart Transportation Applications and Research Laboratory, Seattle, WA, 98195 USA.
  2. Aalto University, School of Engineering, Department of Applied Mechanics, Marine Technology, Research Group on Maritime Risk and Safety, P.O. Box 12200, Aalto, FI-00076 Finland.
[/expand]

 

 

Go To Ocean Engineering

Check Also

Hygrothermal Characterization of Irish Building Stones: Bridging Heritage Conservation and Energy Retrofit - Advances in Engineering

Hygrothermal Characterization of Irish Building Stones: Bridging Heritage Conservation and Energy Retrofit