Analysing the Effects of Weather Conditions on Container Terminal Operations Using Machine Learning

Abstract

Container ships transport a large number of valuable cargoes, and there is a demand for less expensive and faster transportation options. Weather, vessel type, and the nature and amount of the goods are all external elements that might impact container handling times, which are directly related to overall port stay time. In this scope, container terminal operations could be optimised with the help of historical data which provides access to classification and prediction of the cargo handling operations. In this study, the real-time data of a container terminal operation is analysed with different machine learning techniques along with the Fuzzy C-Means clustering method. The results show that Fuzzy C-Means clustering has a positive impact on the explanatory power of models in container terminal operations. The research revealed that an increase in wind speed influences cargo handling time for mobile cranes.

Handling uncertainty in the quay crane scheduling problem: a unified distributionally robust decision model

“…Weather conditions such as wind strength, rain, fog, and sea swell also impact the productivity of the cranes (Shang et al., 2016). For example, strong wind causes the swing of the cargo, which forces the crane operators to work slower (Atak et al., 2016). The existence of fog decreases the visibility of the crane operators, and, therefore, it also slows down the productivity of the cranes.…”