A Machine-Learning Model for Zonal Ship Flow Prediction Using AIS Data: A Case Study in the South Atlantic States Region

Abstract

Predicting traffic flow is critical in efficient maritime transportation management, coordination, and planning. Scientists have proposed many prediction methods, most of which are designed for specific locations or for short-term prediction. For the purpose of management, methods that enable long-term prediction for large areas are highly desirable. Therefore, we propose developing a spatiotemporal approach that can describe and predict traffic flows within a region. We designed the model based on a multiple hexagon-based convolutional neural network (mh-CNN) model that takes both the flow dynamics and environmental conditions into account. This model is highly flexible in that it predicts zonal traffic flow within variable time windows. We applied the method to measure and predict the daily and hourly traffic flows in the South Atlantic States region by taking the impacts of extreme weather events into consideration. Results show that our method outperformed other methods in daily prediction during normal days and hourly prediction during hurricane events. Based on the results, we also provide some recommendations regarding the future usage and customization of the model.

Is the Spatial-Temporal Dependence Model Reliable for the Short-Term Freight Volume Forecast of Inland Ports? A Case Study of the Yangtze River, China

“…Machine learning (ML) algorithms can handle an extensive amount of data without any constraint on the degree of complexity compared to conventional statistical techniques [17,38,39], and they can capture the underlying mechanism that governs that data [40]. ANN (Artificial Neural Network) is the most popular ML method for predicting freight volume.…”

Spatiotemporal dynamic network for regional maritime vessel flow prediction amid COVID-19

“…To bridge this gap, a series of spatiotemporal models have been proposed. For instance, the multiple hexagon-based convolutional neural network (MH-CNN) was utilised to predict the vessel traffic flow in a region considering the environmental conditions ( Wang et al, 2019 ). The bidirectional LSTM network was integrated with the CNN (BDLSTM-CNN) to predict the vessel traffic flow in all grids divided by the study domain ( Zhou et al, 2020 ).…”

“…Statistical and machine learning approaches have been utilised to explore the temporal dependency in vessel traffic flow ( Li et al, 2019 ; Wang et al, 2021 ). Wang et al (2019) and Zhou et al (2020) deemed the flow prediction a spatiotemporal sequence-forecasting problem. However, studies on the prediction framework and method have two demerits.…”

Sequence‐based centrality measures in maritime transportation networks

“…The increasing accessibility of tracking data provides new opportunities to examine and analyse human mobility at a fine spatiotemporal level [1, 2]. It is important to conduct centrality analysis, which facilitates the evaluation of performance of networks as well as the identification of travel behaviours.…”

“…To demonstrate the effectiveness of our approach, we have applied the measures to a maritime transportation network. Maritime transportation plays an important role in global economy [2]. Studying the spatial structure of maritime transportation networks can provide valuable information to support informed decision making.…”