To effectively address the increase in maritime accidents and the challenges posed by the trend toward larger ships for maritime safety, it is crucial to rationally allocate the limited maritime search and rescue (MSAR) resources and enhance accident response capabilities. We present a comprehensive method for allocating MSAR resources, aiming to improve the overall efficiency of MSAR operations. First, we use long short-term memory to predict the number of future accidents and employ the K-medoids algorithm to identify the accident black spots in the studied area. Next, we analyze the multi-constraint conditions in the MSAR resource allocation process. A multi-objective integer programming model is constructed to minimize the response time and allocation cost. Finally, we use the non-dominated sorting genetic algorithm II (DNSGA-II) with Deb’s rules to solve the model, and we propose a multi-attribute decision optimization-based method for MSAR resource allocation. We found that the DNSGA-II exhibits better convergence and generates higher-quality solutions compared to the NSGA-II, particle swarm optimization (PSO), and enhanced particle swarm optimization (EPSO) algorithms. Compared with the existing MSAR resource emergency response system, the optimized scheme reduces the response time and allocation cost by $11.32\%$ and $6.15\%$, respectively. The proposed method can offer decision makers new insights when formulating MSAR resource allocation plans.

Smoke simulation is a crucial yet challenging aspect of constructing ship fire scenarios. For the Eulerian smoke simulation method, the low-resolution grid results in a loss of smoke detail, while the high-resolution grid faces significant computational costs. To address this issue, a detail enhancement approach is proposed for smoke simulation in ship fire scenarios based on vortex particles, aiming at high-realism smoke simulation on a low-resolution grid. The simulation domain is first discretized using a low-resolution grid to compute the basic flow. Next, the vortex particles are sampled within the grid, and the loss of vorticity is measured before and after vortex stretching to compensate for the missing smoke details. In our approach, a geometric method is employed to efficiently capture the stretching of vortex structures. The computational results demonstrate that turbulence details can be effectively captured in a low-resolution grid while maintaining the real-time performance of the simulation. The practical application value of our approach is demonstrated in improving the realism of ship fire scenarios.