Ship arrival prediction and its value on daily container terminal operation

Yu, Jingjing; Tang, Guoan; Song, Xueguan; Yu, Xiaowei; Qi, Yue; Li, Da; Zhang, Yong

doi:10.1016/j.oceaneng.2018.03.038

Cited by 77 publications

(27 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Daily operations include berth and quay cranes allocation. It has been observed that only 20% of the ships arrived on time and the rest arrived either early or late [29]. The obtained results have shown that incorporating prediction into daily terminal operation planning improved the performance of daily terminal operations.…”

Section: Implementation Possibilities Of S-ais Data For Global Maritimentioning

confidence: 81%

“…Recently, S-AIS data have been considered for early delay detection [13] and Estimated Time of Arrival (ETA) prediction. Low punctuality and schedule reliability are causing delays and disruption for terminal and hinterland operations [6] [29]. However, the usage of S-AIS data has still been rarely considered in the research of arrival planning, delay detection and terminal organization.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Near Real-time S-AIS

Mrzljak

Žarković

Poljak³

2018

Pomorstvo (Online)

View full text Add to dashboard Cite

The Automatic identification System (AIS) has been mainly designed to improve safety and efficiency of navigation, environmental protection, coastal traffic monitoring simplifying identification and communication. Additionally, historical AIS data have been used in many other areas of maritime safety, economic and environmental research. The probability of the detection of terrestrial AIS signals from space was presented in 2003, following the advancements in micro satellite technology. Through constant development, research and cooperation between governmental and private sectors, Satellite AIS (S-AIS) has been continuously evolving. Advancements in signal and data processing techniques have resulted in an improved detection over vast areas outside of terrestrial range. Some of the challenges of S-AIS technology include satellite revisit times, message collision and ship detection probability. Data processing latency and lacking the continuous real-time coverage made it less reliable for end user in certain aspects of monitoring and data analysis. Recent developments and improvements by leading S-AIS service providers have reduced latency issues. Complementing with terrestrial AIS and other technologies, near real-time S-AIS can further enhance all areas of the global maritime monitoring domain with emerging possibilities for maritime industry.

show abstract

Section: Implementation Possibilities Of S-ais Data For Global Maritimentioning

confidence: 81%

Section: Introductionmentioning

confidence: 99%

Near Real-time S-AIS

Mrzljak

Žarković

Poljak³

2018

Pomorstvo (Online)

View full text Add to dashboard Cite

show abstract

“…Prediction models using fuzzy rule-based Bayesian network as a hybrid decision technique already exist [4]. A further study presents a prediction model applying data mining and the ML algorithm random forest [10]. Moreover, qualitative delay estimates resulting from ML such as random forest are provided in a comparison analysis of two container terminals [11].…”

Section: Literature Review 21 Theoretical Backgroundmentioning

confidence: 99%

Novel Data Analytics Meets Conventional Container Shipping: Predicting Delays by Comparing Various Machine Learning Algorithms

Viellechner¹,

Spinler²

2020

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Supply chain disruptions are expected to significantly increase over the next decades.In particular, delay of container vessels is likely to escalate due to rising congestion from continued growth of container shipping and higher frequency of extreme weather events. Predicting these delays could result in significant cost savings from optimizing operations. Both academic research and container shipping industry, however, lack analytical solutions to predict delay. To increase transparency on delay, we develop a prediction model based on 315 explanatory variables, 10 regression models, and 7 classification models. Using machine learning algorithms, we obtain best results for neural network and support vector machine with a prediction accuracy of 77 percent compared to only 59 percent of a naive baseline model. Various shipping players including sender, carrier, terminal operator, and receiver benefit from the easy-to-use prediction model to optimize operations such as buffers in schedules and the selection of ports and routes.

show abstract

“…Legato et al [41] presented a model-driven decision support system for integrated container handling with a queuing network model for resource blocking, locking, and vehicle interactions. Yu et al [42] applied data mining approaches to predict ship arrivals, and evaluated the value of ship arrival prediction on daily operation planning. Santos et al [43] presented a methodology for delimiting the potential hinterland of container terminals by using one of a set of possible intermodal or unimodal transportation solutions.…”

Section: Literature Reviewmentioning

confidence: 99%

Container Terminal Logistics Generalized Computing Architecture and Green Initiative Computational Pattern Performance Evaluation

Song

2019

Information

View full text Add to dashboard Cite

Container terminals are the typical representatives of complex supply chain logistics hubs with multiple compound attributes and multiple coupling constraints, and their operations are provided with the strong characteristics of dynamicity, nonlinearity, coupling, and complexity (DNCC). From the perspective of computational logistics, we propose the container terminal logistics generalized computing architecture (CTL-GCA) by the migration, integration, and fusion of the abstract hierarchy, design philosophy, execution mechanism, and automatic principles of computer organization, computing architecture, and operating system. The CTL-GCA is supposed to provide the problem-oriented exploration and exploitation elementary frameworks for the abstraction, automation, and analysis of green production at container terminals. The CTL-GCA is intended to construct, evaluate, and improve the solution to planning, scheduling, and decision at container terminals, which all are nondeterministic polynomial hard problems. Subsequently, the logistics generalized computational pattern recognition and performance evaluation of a practical container terminal service case study is launched by the qualitative and quantitative approach from the sustainable perspective of green production. The case study demonstrates the application, utilization, exploitation, and exploration of CTL-GCA preliminarily, and finds the unsustainable patterns of production at the container terminal. From the above, we can draw the following conclusions. For one thing, the CTL-GCA makes a definition of the abstract and automatic running architecture of logistics generalized computation for container terminals (LGC-CT), which provides an original framework for the design and implementation of control and decision mechanism and algorithm. For another, the CTL-GCA can help us to investigate the roots of DNCC thoroughly, and then the CTL-GCA makes for conducting the efficient and sustainable running pattern recognition of LGC-CT. It is supposed to provide a favorable guidance and supplement to define, design, and implement the agile, efficient, sustainable, and robust task scheduling and resource allocation for container terminals by computational logistics whether in the strategy level or the tactical one.

show abstract

Ship arrival prediction and its value on daily container terminal operation

Cited by 77 publications

References 40 publications

Near Real-time S-AIS

Near Real-time S-AIS

Novel Data Analytics Meets Conventional Container Shipping: Predicting Delays by Comparing Various Machine Learning Algorithms

Container Terminal Logistics Generalized Computing Architecture and Green Initiative Computational Pattern Performance Evaluation

Contact Info

Product

Resources

About