Note: i3lab

Abstract: The automatic identification system (AIS) enables authorities, shipping companies and researchers all over the world using ever better computer technologies to understand and track vessel movements. This publication focuses on analysing vessels’ waiting times for berth at anchoring places near ports using the example of the port of Rotterdam, Europe’s biggest port. The objective is to define clearly the concept of waiting, i.e. when a vessel waits and when not, and to investigate the amount of waiting vessels and the respective waiting times during a time span of more than two years, using solely AIS data. The indicated anchoring zones in front of the port of Rotterdam, where vessels wait, are clearly detected by visualizing the analysed data. The results of the conducted AIS data analysis show significant differences in waiting times between different vessel types, as well as a correlation between the number of waiting vessels and the average waiting time. The in detail described data pre-processing and statistical analysis are extendable and applicable to other regions and ports all over the world. Additionally, the presented data pre-processing approach is an optimal basis analysis of current waiting conditions and for applying machine learning to AIS data in order to predict future waiting times

Note: i3lab

Abstract: The automatic identification system (AIS) enables authorities, shipping companies and researchers all over the world using ever better computer technologies to understand and track vessel movements. This publication focuses on analysing vessels’ waiting times for berth at anchoring places near ports using the example of the port of Rotterdam, Europe’s biggest port. The objective is to define clearly the concept of waiting, i.e. when a vessel waits and when not, and to investigate the amount of waiting vessels and the respective waiting times during a time span of more than two years, using solely AIS data. The indicated anchoring zones in front of the port of Rotterdam, where vessels wait, are clearly detected by visualizing the analysed data. The results of the conducted AIS data analysis show significant differences in waiting times between different vessel types, as well as a correlation between the number of waiting vessels and the average waiting time. The in detail described data pre-processing and statistical analysis are extendable and applicable to other regions and ports all over the world. Additionally, the presented data pre-processing approach is an optimal basis analysis of current waiting conditions and for applying machine learning to AIS data in order to predict future waiting times

Note: i3lab

Abstract: The automatic identification system (AIS) enables authorities, shipping companies and researchers all over the world using ever better computer technologies to understand and track vessel movements. This publication focuses on analysing vessels’ waiting times for berth at anchoring places near ports using the example of the port of Rotterdam, Europe’s biggest port. The objective is to define clearly the concept of waiting, i.e. when a vessel waits and when not, and to investigate the amount of waiting vessels and the respective waiting times during a time span of more than two years, using solely AIS data. The indicated anchoring zones in front of the port of Rotterdam, where vessels wait, are clearly detected by visualizing the analysed data. The results of the conducted AIS data analysis show significant differences in waiting times between different vessel types, as well as a correlation between the number of waiting vessels and the average waiting time. The in detail described data pre-processing and statistical analysis are extendable and applicable to other regions and ports all over the world. Additionally, the presented data pre-processing approach is an optimal basis analysis of current waiting conditions and for applying machine learning to AIS data in order to predict future waiting times

Note: i3lab

Abstract: The automatic identification system (AIS) enables authorities, shipping companies and researchers all over the world using ever better computer technologies to understand and track vessel movements. This publication focuses on analysing vessels’ waiting times for berth at anchoring places near ports using the example of the port of Rotterdam, Europe’s biggest port. The objective is to define clearly the concept of waiting, i.e. when a vessel waits and when not, and to investigate the amount of waiting vessels and the respective waiting times during a time span of more than two years, using solely AIS data. The indicated anchoring zones in front of the port of Rotterdam, where vessels wait, are clearly detected by visualizing the analysed data. The results of the conducted AIS data analysis show significant differences in waiting times between different vessel types, as well as a correlation between the number of waiting vessels and the average waiting time. The in detail described data pre-processing and statistical analysis are extendable and applicable to other regions and ports all over the world. Additionally, the presented data pre-processing approach is an optimal basis analysis of current waiting conditions and for applying machine learning to AIS data in order to predict future waiting times

Note: i3lab

Abstract: The automatic identification system (AIS) enables authorities, shipping companies and researchers all over the world using ever better computer technologies to understand and track vessel movements. This publication focuses on analysing vessels’ waiting times for berth at anchoring places near ports using the example of the port of Rotterdam, Europe’s biggest port. The objective is to define clearly the concept of waiting, i.e. when a vessel waits and when not, and to investigate the amount of waiting vessels and the respective waiting times during a time span of more than two years, using solely AIS data. The indicated anchoring zones in front of the port of Rotterdam, where vessels wait, are clearly detected by visualizing the analysed data. The results of the conducted AIS data analysis show significant differences in waiting times between different vessel types, as well as a correlation between the number of waiting vessels and the average waiting time. The in detail described data pre-processing and statistical analysis are extendable and applicable to other regions and ports all over the world. Additionally, the presented data pre-processing approach is an optimal basis analysis of current waiting conditions and for applying machine learning to AIS data in order to predict future waiting times

Note: i3lab

Abstract: The automatic identification system (AIS) enables authorities, shipping companies and researchers all over the world using ever better computer technologies to understand and track vessel movements. This publication focuses on analysing vessels’ waiting times for berth at anchoring places near ports using the example of the port of Rotterdam, Europe’s biggest port. The objective is to define clearly the concept of waiting, i.e. when a vessel waits and when not, and to investigate the amount of waiting vessels and the respective waiting times during a time span of more than two years, using solely AIS data. The indicated anchoring zones in front of the port of Rotterdam, where vessels wait, are clearly detected by visualizing the analysed data. The results of the conducted AIS data analysis show significant differences in waiting times between different vessel types, as well as a correlation between the number of waiting vessels and the average waiting time. The in detail described data pre-processing and statistical analysis are extendable and applicable to other regions and ports all over the world. Additionally, the presented data pre-processing approach is an optimal basis analysis of current waiting conditions and for applying machine learning to AIS data in order to predict future waiting times

Note: i3lab

Abstract: The automatic identification system (AIS) enables authorities, shipping companies and researchers all over the world using ever better computer technologies to understand and track vessel movements. This publication focuses on analysing vessels’ waiting times for berth at anchoring places near ports using the example of the port of Rotterdam, Europe’s biggest port. The objective is to define clearly the concept of waiting, i.e. when a vessel waits and when not, and to investigate the amount of waiting vessels and the respective waiting times during a time span of more than two years, using solely AIS data. The indicated anchoring zones in front of the port of Rotterdam, where vessels wait, are clearly detected by visualizing the analysed data. The results of the conducted AIS data analysis show significant differences in waiting times between different vessel types, as well as a correlation between the number of waiting vessels and the average waiting time. The in detail described data pre-processing and statistical analysis are extendable and applicable to other regions and ports all over the world. Additionally, the presented data pre-processing approach is an optimal basis analysis of current waiting conditions and for applying machine learning to AIS data in order to predict future waiting times

Note: i3lab

Abstract: The automatic identification system (AIS) enables authorities, shipping companies and researchers all over the world using ever better computer technologies to understand and track vessel movements. This publication focuses on analysing vessels’ waiting times for berth at anchoring places near ports using the example of the port of Rotterdam, Europe’s biggest port. The objective is to define clearly the concept of waiting, i.e. when a vessel waits and when not, and to investigate the amount of waiting vessels and the respective waiting times during a time span of more than two years, using solely AIS data. The indicated anchoring zones in front of the port of Rotterdam, where vessels wait, are clearly detected by visualizing the analysed data. The results of the conducted AIS data analysis show significant differences in waiting times between different vessel types, as well as a correlation between the number of waiting vessels and the average waiting time. The in detail described data pre-processing and statistical analysis are extendable and applicable to other regions and ports all over the world. Additionally, the presented data pre-processing approach is an optimal basis analysis of current waiting conditions and for applying machine learning to AIS data in order to predict future waiting times

Note: i3lab

Abstract: The automatic identification system (AIS) enables authorities, shipping companies and researchers all over the world using ever better computer technologies to understand and track vessel movements. This publication focuses on analysing vessels’ waiting times for berth at anchoring places near ports using the example of the port of Rotterdam, Europe’s biggest port. The objective is to define clearly the concept of waiting, i.e. when a vessel waits and when not, and to investigate the amount of waiting vessels and the respective waiting times during a time span of more than two years, using solely AIS data. The indicated anchoring zones in front of the port of Rotterdam, where vessels wait, are clearly detected by visualizing the analysed data. The results of the conducted AIS data analysis show significant differences in waiting times between different vessel types, as well as a correlation between the number of waiting vessels and the average waiting time. The in detail described data pre-processing and statistical analysis are extendable and applicable to other regions and ports all over the world. Additionally, the presented data pre-processing approach is an optimal basis analysis of current waiting conditions and for applying machine learning to AIS data in order to predict future waiting times

Note: i3lab

Abstract: The automatic identification system (AIS) enables authorities, shipping companies and researchers all over the world using ever better computer technologies to understand and track vessel movements. This publication focuses on analysing vessels’ waiting times for berth at anchoring places near ports using the example of the port of Rotterdam, Europe’s biggest port. The objective is to define clearly the concept of waiting, i.e. when a vessel waits and when not, and to investigate the amount of waiting vessels and the respective waiting times during a time span of more than two years, using solely AIS data. The indicated anchoring zones in front of the port of Rotterdam, where vessels wait, are clearly detected by visualizing the analysed data. The results of the conducted AIS data analysis show significant differences in waiting times between different vessel types, as well as a correlation between the number of waiting vessels and the average waiting time. The in detail described data pre-processing and statistical analysis are extendable and applicable to other regions and ports all over the world. Additionally, the presented data pre-processing approach is an optimal basis analysis of current waiting conditions and for applying machine learning to AIS data in order to predict future waiting times

Note: i3lab

Abstract: The automatic identification system (AIS) enables authorities, shipping companies and researchers all over the world using ever better computer technologies to understand and track vessel movements. This publication focuses on analysing vessels’ waiting times for berth at anchoring places near ports using the example of the port of Rotterdam, Europe’s biggest port. The objective is to define clearly the concept of waiting, i.e. when a vessel waits and when not, and to investigate the amount of waiting vessels and the respective waiting times during a time span of more than two years, using solely AIS data. The indicated anchoring zones in front of the port of Rotterdam, where vessels wait, are clearly detected by visualizing the analysed data. The results of the conducted AIS data analysis show significant differences in waiting times between different vessel types, as well as a correlation between the number of waiting vessels and the average waiting time. The in detail described data pre-processing and statistical analysis are extendable and applicable to other regions and ports all over the world. Additionally, the presented data pre-processing approach is an optimal basis analysis of current waiting conditions and for applying machine learning to AIS data in order to predict future waiting times