Given the complexity of underwater environments and the variability of water as a medium, underwater images are inevitably subject to various types of degradation. The degradations present nonlinear coupling rather than simple superposition, which renders the effective processing of such coupled degradations particularly challenging. Most existing methods focus on designing specific branches, modules, or strategies for specific degradations, with little attention paid to the potential information embedded in their coupling. Consequently, they struggle to effectively capture and process the nonlinear interactions of multiple degradations from a bottom-up perspective. To address this issue, we propose JDPNet, a joint degradation processing network, that mines and unifies the potential information inherent in coupled degradations within a unified framework. Specifically, we introduce a joint feature-mining module, along with a probabilistic bootstrap distribution strategy, to facilitate effective mining and unified adjustment of coupled degradation features. Furthermore, to balance color, clarity, and contrast, we design a novel AquaBalanceLoss to guide the network in learning from multiple coupled degradation losses. Experiments on six publicly available underwater datasets, as well as two new datasets constructed in this study, show that JDPNet exhibits state-of-the-art performance while offering a better tradeoff between performance, parameter size, and computational cost.

The presence of multiple generator units (GUs) in the hybrid electric propulsion system (HEPS) of flying cars poses higher requirements for the design of energy management strategy (EMS) since the decision made by one GU impacts the state and decisions of others due to the coupling electrical dynamics of the system. In this paper, a data-driven cooperative differential game (CDG) based EMS is proposed to improve the performance of the fuel consumption and exhaust gas temperature (EGT) of those GUs as well as the stability of the state of charge (SOC) of the battery through coordination and cooperation. The energy management problem is first formulated as a general two-player differential game. To improve the computational efficiency as well as the control performance, a novel neural network-based adaptive dynamic programming (ADP) algorithm is proposed to approximate the Nash equilibrium (NE) and Pareto solution (PS) of the non-cooperative differential game (NCDG) and CDG During real-time application, and a comparison mechanism is designed so that the solution with a smaller cost is applied to the system to further improve performance. The simulation results indicate that the proposed CDG-based EMS can not only reduce the equivalent fuel consumption by 2.67% and 6.22% compared with that of NCDG and rule-based EMS, but also obtain a better overall and individual performance of the two GUs simultaneously, demonstrating the effectiveness of the proposed approach in reducing the fuel consumption, EGT as well as maintaining the state of charge (SOC) of the battery.