Collision risk early warning is critical to sailing safety in vessel encounter situations because it provides ship officers with sufficient time to react to emergencies and take evasive actions in advance. In this study, we take spatiotemporal motion behaviors of encountering vessels into account since vessel motion behaviors have great influences on the occurrence of a dangerous situation. For this purpose, a data-driven approach is proposed to associate the motion behaviors with the future risk and early prediction of risk is achieved through classifying the behaviors into corresponding risk level. Specifically, we first derive a sequence of relative motion features between encountering vessels to characterize the spatial interactions that vary over time. Then a novel deep learning architecture, which combines bidirectional long short-term memory (BiLSTM) and attention mechanism, is developed to capture the spatial-temporal dependences of behaviors as well as their impacts on future risk. In particular, the BiLSTM is able to discover correlations among behaviors and the attention mechanism can emphasize the key information relevant to the risk prediction task. Exploiting the advantages of these two mechanisms makes the risk prediction more reasonable and reliable. Extensive experiments using ship trace data from the Yangtze River Estuary demonstrate that the proposed Attention-BiLSTM approach outperforms conventional LSTM in terms of accuracy and stability. Moreover, the real-time capability of the approach gives it a significant potential for use in predicting collisions at the early stages.

Accurate prediction of ship trajectories is crucial for ensuring safe and efficient navigation. However, predicting ship trajectories in complex and dynamic environments presents significant challenges. Ships exhibit multi-mode motions, manifesting as diverse motion patterns even under similar circumstances, influenced by factors such as navigational intentions and operational tasks. Moreover, trajectory prediction is further complicated by time-varying ship dynamics, encompassing sailing conditions, ship maneuvering, and environmental factors. In this paper, we propose a Bayesian multiple model with an online model selection strategy to dynamically represent the latent motion mode from early observations. Each sub-model integrates a variational Kalman filter and Gated Recurrent Unit (GRU) neural network, enabling the estimation of time-varying transition coefficients and the process noise specific to different motion modalities. This hybrid methodology leverages the strengths of probabilistic recursive estimation of the Kalman filter while benefiting from the capacity of a GRU network to learn complex temporal dependencies from historical data. The proposed method was evaluated on ship trajectories across different observation lengths and prediction horizons and outperformed the baseline in terms of both accuracy and plausibility.

Encounter risk prediction is critical for safe ship navigation, especially in congested waters, where ships sail very near to each other during various encounter situations. Prior studies on the risk of ship collisions were unable to address the uncertainty of the encounter process when ignoring the complex motions constituting the dynamic ship encounter behavior, which may seriously affect the risk prediction performance. To fill this gap, a novel AIS data-driven approach is proposed for ship encounter risk prediction by modeling intership behavior patterns. In particular, multidimensional features of intership behaviors are extracted from the AIS trace data to capture spatial dependencies between encountering ships. Then, the challenging task of risk prediction is to discover the complex and uncertain relationship between intership behaviors and future collision risk. To address this issue, we propose a deep learning framework. To represent the temporal dynamics of the encounter process, we use the sliding window technique to generate the sequences of behavioral features. The collision risk level at a future time is taken as the class label of the sequence. Then, the long short-term memory network, which has a strong ability to model temporal dependency and complex patterns, is extended to establish the relationship. The benefit of our approach is that it transforms the complex problem for risk prediction into a time series classification task, which makes collision risk prediction reliable and easier to implement. Experiments were conducted on a set of naturalistic data from various encounter scenarios in the South Channel of the Yangtze River Estuary. The results show that the proposed data-driven approach can predict future collision risk with high accuracy and efficiency. The approach is expected to be applied for the early prediction of encountering ships and as decision support to improve navigation safety.