TY - JOUR
T1 - Can we trust the AIS destination port information for bulk ships?–Implications for shipping policy and practice
AU - Yang, Dong
AU - Wu, Lingxiao
AU - Wang, Shuaian
N1 - Funding Information:
This research is supported by the National Natural Science Foundation of China under grant numbers 71971185 and 72071173 and the NSFC/RGC Joint Research Scheme under grant numbers N_PolyU531/16 and 71661167009.
Publisher Copyright:
© 2021 Elsevier Ltd
PY - 2021/5
Y1 - 2021/5
N2 - The Automatic Identification System (AIS) is a shipping database that includes the physical characteristics and real-time dynamics of ships. It has attracted great attention from academia recently and has been broadly applied in solving various problems in different fields. The voyage destination report is a piece of information recorded in AIS that indicates the heading port in a ship's voyage. This information is widely referred to by port operators for traffic estimation, and by shipping traders for supply forecasting, etc. However, we find that a considerable proportion (nearly 40%) of this information has been erroneously entered, both intentionally and unintentionally. In this paper, we aim to propose targeted policies to correct the inaccurate reports based on assessing the probability of observing wrong destination port reports of ships in AIS. To this end, we first of all conduct extensive interviews with relevant shipping stakeholders to understand the reasons behind the wrong destination reports. Second, based on the interviews and relevant literature we propose the influence factors. Third, we generate a data sample set based on the voyages performed by Capesize and Panamax bulk ships around the globe in a year. To generate this sample set, we leverage data mining techniques to extract the information from an AIS database and other databases. Finally, a discrete choice model is built to achieve the proposed objective. The results demonstrate that our model has an 84.1% accuracy rate in ascertaining the correctness of destination reports observed in AIS. We also find that, for a voyage, the speed of the ship, the historical accuracy rate of destination reports made by the ship, and the distance between the recognized origin and the reported destination of the voyage, have the most significant impacts on the accuracy of the destination report. Based on the findings, we provide managerial and policy suggestions to ship operators, port authorities, and regulators.
AB - The Automatic Identification System (AIS) is a shipping database that includes the physical characteristics and real-time dynamics of ships. It has attracted great attention from academia recently and has been broadly applied in solving various problems in different fields. The voyage destination report is a piece of information recorded in AIS that indicates the heading port in a ship's voyage. This information is widely referred to by port operators for traffic estimation, and by shipping traders for supply forecasting, etc. However, we find that a considerable proportion (nearly 40%) of this information has been erroneously entered, both intentionally and unintentionally. In this paper, we aim to propose targeted policies to correct the inaccurate reports based on assessing the probability of observing wrong destination port reports of ships in AIS. To this end, we first of all conduct extensive interviews with relevant shipping stakeholders to understand the reasons behind the wrong destination reports. Second, based on the interviews and relevant literature we propose the influence factors. Third, we generate a data sample set based on the voyages performed by Capesize and Panamax bulk ships around the globe in a year. To generate this sample set, we leverage data mining techniques to extract the information from an AIS database and other databases. Finally, a discrete choice model is built to achieve the proposed objective. The results demonstrate that our model has an 84.1% accuracy rate in ascertaining the correctness of destination reports observed in AIS. We also find that, for a voyage, the speed of the ship, the historical accuracy rate of destination reports made by the ship, and the distance between the recognized origin and the reported destination of the voyage, have the most significant impacts on the accuracy of the destination report. Based on the findings, we provide managerial and policy suggestions to ship operators, port authorities, and regulators.
KW - AIS data
KW - Data mining
KW - Discrete choice model
KW - Shipping management
UR - http://www.scopus.com/inward/record.url?scp=85103706835&partnerID=8YFLogxK
U2 - 10.1016/j.tre.2021.102308
DO - 10.1016/j.tre.2021.102308
M3 - Journal article
AN - SCOPUS:85103706835
SN - 1366-5545
VL - 149
JO - Transportation Research Part E: Logistics and Transportation Review
JF - Transportation Research Part E: Logistics and Transportation Review
M1 - 102308
ER -