Enhancing vessel arrival time prediction: A fusion-based deep learning approach

Abstract

The logistic community of shippers has struggled to predict the precise arrival time of the seagoing vessels with reliable certainty. While deep-learning approaches are promising, the existing methods fail to provide desirable results due to a shallow prediction architecture. This research work proposes a method to predict vessel arrival time that could eventually be incorporated into an intelligent decision support system that we call Vessel Arrival Time Prediction (VATP). VATP presents a hybrid architecture of Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), Attention mechanism, Dropout, and Dense layers to take advantage of the coarse-grained local features produced by CNN, the longitudinal nature of AIS (long-time dependencies) via LSTM and paying attention to the influence feature on the arrival time. While many prior approaches have relied solely on AIS data, and some incorporated a combination of AIS and vessel information, our method also integrates diverse data sources, including Automatic Identification System (AIS), Augmented information (Ain), and Maritime Weather Data (MWD). Furthermore, only a few methods have considered weather information, often using minimal weather-related features. In contrast, our approach involves a comprehensive range of weather-related features, and besides these data sources, we extracted specially crafted features.To verify the effectiveness of VATP, we conducted our experiment on large-scale datasets. The VATP model obtained a Root Mean Square Error (RMSE) of 10.63 and a Mean Absolute Percentage Error (MAPE) of 35.11 %. Our results demonstrate that VATP achieves significant performance. Furthermore, these positive results demonstrate that i) the accuracy of the VATP approach can be improved using the AIS, MWD, and Ain information; ii) learning from a unified feature set can result in a significant performance improvement compared to learning from a subset of the features; iii) we also obtained a superior performance in comparison with other well-known methods in the literature and various state-of-the-art baseline methods. Finally, our results illustrate the consistent performance of the VATP across different datasets.