Vessel risk analysis is critical for safe ship navigation and maritime safety management. Near-miss collisions by ships comprise an significant risk, which may be complicated by factors, such as the ship conditions, waterway environment, and driving behavior of any ships encountered. Previous studies have rarely considered how to automatically and adaptively estimate the risk of near-miss collisions for different situations, particularly in port areas. In this paper, we propose an automatic identification system-based approach for adaptively calibrating near-miss collision risk model and assessing a ship's near-miss collision risk by using the vessel's speed and course patterns to obtain a robust estimate of the collision risk. Six measures are employed to determine the hierarchical geographical distribution of the near-miss collision risk for ships in port areas and to identify the high-risk areas. Some predicted high-risk areas were validated as official precautionary areas in the Xiamen Port area. All predicted areas may help the port administration to plan monitoring areas to ensure safe traffic flow in the port.

The Russia–Ukraine conflict has influenced global LNG shipping patterns; nevertheless, current research about its effects on the nodes and local regions of the LNG shipping network remains insufficient. This study employs a series of network metrics and a robustness evaluation model to examine the evolution in the structure and functionality of the LNG shipping network amid the Russia–Ukraine conflict, integrating LNG vessel origin–destination data from 2021 to 2023 to analyze the network’s structure and robustness. The research indicated that: (1) The alteration in trade relations instigated by the Russia–Ukraine conflict modified global LNG flows, resulting in a fragmented overall network structure and diminished transportation efficiency. The Russia–Ukraine conflict catalyzed the enhancement of European ports, leading to a substantial rise in the significance of premier European ports within the LNG transport network. Significant export ports, such as Ras Laffan, hold substantial importance within the network. (2) Among various assault techniques, degree-based intentional attacks inflict the greatest harm on the LNG shipping network. The robustness of the LNG shipping network declined following the Russia–Ukraine conflict, rendering it particularly susceptible in 2023. The findings indicate that the Russia–Ukraine conflict altered the structure of the LNG transportation network and diminished its robustness. The work holds substantial theoretical importance for examining the influence of geopolitical events on LNG transportation and for improving the maritime industry’s ability to navigate complicated circumstances.

Virtual testing is one of the key methods for evaluating the collision avoidance capabilities of autonomous ships, and test scenarios provide the fundamental basis for its implementation. However, generating test scenarios that are both diverse and physically realistic remains a significant challenge in this field. This paper proposes a ship encounter scenario generation and dynamic simulation method for encounter situations based on a Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP). Specifically, the proposed framework consists of a Collision Risk Index-guided-WGAN-GP (CRI-WGAN-GP) for initial encounter scenario generation and a Physics-Informed Conditional WGAN-GP (PI-CWGAN-GP) for dynamic encounter scenario simulation. In the first stage, the CRI-WGAN-GP is developed to generate initial encounter scenarios with collision-risk characteristics. The Collision Risk Index (CRI) is directly embedded into the discriminator of the WGAN-GP. This mechanism forces the latent space to learn risk correlations, enabling effective exploration of high-risk boundaries and generating test cases with collision risks for the target ship. In the second stage, the PI-CWGAN-GP is designed to generate sequential dynamic simulation scenarios conditioned on the current encounter situation. By incorporating constraints related to ship motion performance, the PI-CWGAN-GP ensures that the generated ship behaviors are physically realistic. The proposed method is experimentally evaluated based on scenario diversity and physical realism, and the experimental results demonstrate that the proposed method can generate initial scenarios with collision risks and simulate ship behavior in encounter situations. Compared to existing random sampling and general generative adversarial network methods, the proposed approach shows significant advantages in generating more realistic and high-risk scenarios. In addition, a stress-test analysis is conducted based on a real encounter scenario, with the historical own-ship trajectory replayed as a reference response. Since no specific collision-avoidance algorithm is exposed to the generated scenarios in closed loop, the evaluation is limited to examining the encounter pressure imposed by the generated target-ship behaviors. The results show that the generated counterpart scenarios reduce the original spatial and temporal safety margins and create more demanding encounter conditions.

Introduction: Navigation risk assessment in complex bridge waters is challenged by intersecting traffic flows, localized risk hotspots, and inconsistencies between annual vessel movements and collision risk. Methods: AIS trajectories collected from 2022 to 2024 around Zhanjiang Bay Bridge and Tiaoshun Bridge were processed and matched to route legs. An AIS-informed route network was reconstructed using traffic density and observed crossing, merging, and diverging patterns. IWRAP MKII was used to estimate ship -ship collision and ship -bridge allision frequencies. A unified fixed-route network and sequential control scenarios were used to examine interannual differences. Results: AIS-observed vessel movements decreased from 7,199 in 2023 to 6,613 in 2024, whereas ship -ship collision frequency under the fixed-route network increased from 0.037870 to 0.062410 events/year, an increase of approximately 64.80%. Cumulative route-leg passage frequency increased by 31.36%. High-risk route legs and waypoints were concentrated near bridge approaches and intersections between the main channel and port-access routes. AREA-6188 and AREA-6190 exhibited relatively high ship -bridge allision frequencies. In the sequential control scenarios, adjusting annual vessel movements alone reduced the modeled collision frequency, while subsequent adjustments to ship-type composition and other AIS-derived characteristics produced smaller incremental changes. The C4 estimate was 0.064760 events/year, approximately 3.8% higher than the C5 reference value of 0.062410 events/year. Discussion: The results indicate that annual vessel counts alone do not fully represent traffic exposure within the route network. The proposed framework supports retrospective risk-hotspot identification and the prioritization of traffic management and bridge-pier protection, rather than real-time, vessel-specific collision prediction.