The plumes generated during the collection of polymetallic nodules in the deep sea may have a significant impact on the marine ecosystem. Therefore, this article reviews the progress in deep-sea mining and monitoring technologies related to plumes. It is suggested that specific areas of environmental interest (APEIs) and positive altitude characteristic regions (such as seamounts and hills) in the process of polymetallic nodule collection can serve as refuges for benthic organisms and provide a biological basis for the recovery of biodiversity in mining areas. Water-supported vessels, pipeline lifting systems, and hydraulic collection methods are the least disruptive and most promising methods. By sorting out the deep-sea mining process, plumes can be roughly classified into seabed disturbance plumes and tailing plumes. The best way to address plume formation is at the source when developing environmentally friendly mining vehicles. The evaluation of plumes is crucial for the sustainable development of the environment and seabed resources. However, the mechanism is not clear at present. Therefore, laboratory simulation and in situ monitoring need to be coordinated, and attention should be paid to the impact on benthic marine organisms as much as possible during original operations. Plume research in the deep-sea mining process will also provide favorable support for the possible future development of seabed resources.

Ship trajectory tracking controllers based on deep reinforcement learning (DRL) are widely applied in various fields such as autonomous driving and robotics due to their strong adaptive learning capabilities and optimization decision-making ability. However, ship trajectory control faces challenges such as long training cycles and poor convergence performance. These issues are primarily caused by the unreasonable design of algorithm models and reward functions, which limit the performance optimization and energy efficiency improvements in real-world navigation. In this paper, we propose a ship trajectory tracking control algorithm based on deep reinforcement learning. The proposed algorithm introduces maximum entropy theory and experience replay techniques. Additionally, it enhances the reward function module by adding reward terms and fitting weight designs. A three-dimensional simulation environment is constructed to validate the proposed method. The results demonstrate that the controller designed in this study outperforms traditional DRL controllers in terms of fast convergence, convergence stability, and final reward values. The controller meets the requirements for tracking conventional trajectories and shows stable and efficient performance in both wide-area water search experiments and river channel traversal experiments. These experimental results provide valuable insights for future research directions.

Sediment plumes generated by seafloor mining vehicles represent a major environmental concern in polymetallic nodule harvesting operations. This study investigates plume dispersion induced by sediment disturbances during mining using numerical simulations based on the similarity principle. A representative mining region is modeled, and the motion of mining vehicles is simulated to define the sediment disturbance source. The simulations employ the experimentally validated P-T Euler model (Particle–Turbulence Interaction Euler model) to examine the effects of sediment release velocity and ambient current velocity on plume dispersion characteristics. The results show that increasing the sediment release velocity primarily enhances the initial turbidity flux and significantly expands the plume core diffusion range, indicating that mining disturbances dominate near-field plume behavior. In contrast, the ambient current velocity strongly controls plume morphology and transport, promoting upward transport, long-range advection, and enhanced turbulent dissipation that governs far-field dispersion. Overall, plume diffusion is initially controlled by mining-induced sediment release but becomes increasingly dominated by ambient flow during large-scale transport. These findings provide a theoretical basis for predicting sediment plume behavior and assessing potential environmental impacts in deep-sea mining areas.

Deep reinforcement learning (DRL) has demonstrated considerable potential for autonomous collision avoidance in unmanned surface vessels (USVs). However, its application in complex multi-agent maritime environments is often limited by challenges such as convergence issues and high computational costs. To address these issues, this paper proposes an expert-guided DRL algorithm that integrates a Dual-Priority Experience Replay (DPER) mechanism with a Hybrid Reciprocal Velocity Obstacles (HRVO) expert module. Specifically, the DPER mechanism prioritizes high-value experiences by considering both temporal-difference (TD) error and collision avoidance quality. The TD error prioritization selects experiences with large TD errors, which typically correspond to critical state transitions with significant prediction discrepancies, thus accelerating value function updates and enhancing learning efficiency. At the same time, the collision avoidance quality prioritization reinforces successful evasive actions, preventing them from being overshadowed by a large volume of ordinary experiences. To further improve algorithm performance, this study integrates a COLREGs-compliant HRVO expert module, which guides early-stage policy exploration while ensuring compliance with regulatory constraints. The expert mechanism is incorporated into the Soft Actor-Critic (SAC) algorithm and validated in multi-vessel collision avoidance scenarios using maritime simulations. The experimental results demonstrate that, compared to traditional DRL baselines, the proposed algorithm reduces training time by 60.37% and, in comparison to rule-based algorithms, achieves shorter navigation times and lower rudder frequencies.