Chunze Zhang

Driven by anthropogenic disturbances, including cascade hydropower development, navigation channel regulation, and sand extraction, the hydrological processes and thermal regimes of the National Nature Reserve for Rare and Endemic Fishes in the upper reaches of the Yangtze River (hereafter referred to as the Reserve) have undergone profound alterations. These alterations have substantially degraded fish habitat conditions and generated persistent adverse effects on the completion of fish life-history processes. Therefore, elucidating the ecological response mechanisms of representative fish species to hydrological regime changes and accurately quantifying their habitat requirements across different life-history stages are crucial for effective fish population restoration and habitat rehabilitation in protected river reaches. In this study, the Four Major Chinese Carps were selected as target species, and a physically based coupled model was developed to establish an integrated framework for evaluating habitat suitability throughout their entire life cycle. According to species-specific life-history characteristics, the life cycle was divided into three key stages: spawning, foraging, and overwintering periods. By incorporating the distinct habitat preferences and ecological requirements of each stage, the corresponding ecological flow requirements of the Reserve were quantified for different seasonal periods. The results revealed that habitat suitability for Four Major Chinese Carps was highest during the foraging period, followed by the spawning period, and lowest during the overwintering period. This variation suggests that the current hydrodynamic conditions in the studied river reach are relatively favorable for habitat maintenance and population survival during the foraging period, whereas greater ecological constraints occur during overwintering. To optimize habitat conditions for Four Major Chinese Carps, an ecological flow regime of 4800–6000 m³/s is recommended during the spawning period (April–July), with appropriately timed flood pulses between April and June to trigger spawning behavior. During the foraging period (August–November), flows of 9600–12,000 m³/s should be maintained to support foraging and growth. During the overwintering period (December–March), when natural runoff is insufficient to meet habitat demands, adaptive regulation of upstream reservoirs should be implemented where feasible to enhance downstream discharge and improve overwintering habitat conditions in the large mountainous river ecosystems of the Reserve. The life-cycle habitat suitability assessment framework developed in this study, together with the stage-specific ecological flow requirements identified, provides a scientific basis for reservoir operation strategies, fish habitat evaluation, and targeted ecological restoration planning in regulated river systems.

Solving the shallow-water equations (SWEs) using the lattice Boltzmann method (LBM) can be computationally expensive on uniform grids. Here we develop a quadtree-based adaptive mesh refinement framework that preserves the Cartesian grid structure while enabling local refinement. A cell-centred data layout is used at coarse–fine interfaces, and hash-table indexing enables efficient neighbour lookup. We evaluate the model using six benchmarks: steady flow over a bed hump, a one-dimensional dam-break wave, rectangular and circular dam-break flows, long-wave resonance in a parabolic basin, and dam-break flow over a triangular sill. We further assess its performance on a natural reach of the lower Minjiang River in Leshan, China, with complex topography. The adaptive model achieves accuracy comparable to that of a uniformly fine grid while substantially reducing the lattice-node count and runtime. This framework provides a practical approach for applying LBM-SWE to moderate-scale real-world problems.

Fish achieve highly energy-efficient propulsion in complex hydrodynamic environments through a multi-level, tightly coupled “neural–musculoskeletal–body–fluid” system. This integrated mechanism provides a compelling biological blueprint for biomimetic underwater robots intended for long-endurance missions. Replicating this advantage in engineered platforms, however, requires more than kinematic descriptions and curve fitting: kinematics alone has limited ability to illuminate the control principles underlying efficient swimming. More fundamentally, the key is to identify and model the neuromuscular control principles that drive efficient swimming and their coordinated coupling with fluid–structure interactions (FSI). Guided by this view, we developed a physics-constrained deep reinforcement learning (DRL) framework for neuromuscular control simulation. The framework coupled DRL with a FSI solver, a Hill-type muscle model, and multibody dynamics in a closed-loop simulation. This platform can directly quantify the swimmer’s active and passive muscular work and characterize the entire dynamic chain of force transmission during swimming locomotion. Within this unified setting, a DRL agent learned end-to-end—without an explicitly prescribed control law—the spatiotemporal transformation from neural activation to muscle force generation to body deformation in a high-fidelity digital swimmer, while also capturing the resulting swimming speed and muscular work. After sufficient training, the agent found a clear, repeatable family of Pareto-optimal solutions and spontaneously discovers interpretable physical patterns consistent with prior experimental observations. These results demonstrate the value of DRL for exploration and optimization in high-dimensional, strongly coupled, effectively black-box physical systems, while also provide a testable quantitative framework for elucidating the neuromuscular control mechanisms underlying fish swimming, and offering valuable insights for actuator selection, structural design, and energy-management system design in biomimetic underwater robots.

Path planning is a core issue in fields such as robotics, autonomous driving, and unmanned navigation systems. Nevertheless, traditional path planning methods face substantial challenges in dynamic, nonlinear, and stochastic underwater environments. In this study, a fluid solver module capable of simulating fluid–structure interaction with high precision and efficiency was constructed based on the immersed boundary–lattice Boltzmann method. The perception and decision-making system of the bionic intelligent fish was constructed using deep reinforcement learning (DRL) algorithms, and a concise visual perception modality representation based on one-hot encoding was proposed. The obstacle avoidance performance of the bionic intelligent fish trained via end-to-end DRL was tested in both still-water environments and dynamic flow environments with complex geometries. The results demonstrate that the intelligent fish exhibits efficient local path planning and obstacle avoidance capabilities in both environments while possessing a certain robustness against disturbances in nonlinear environments. This research can provide a reference for the design of local path planning modules for bionic robotic fish and is expected to further enhance the mission execution capabilities of autonomous underwater vehicles in unmapped deep and far-sea areas with high uncertainty.

Understanding efficient fish locomotion offers insights for biomechanics, fluid dynamics, and engineering. Traditional studies often miss the link between neuromuscular control and whole-body movement. To explore energy transfer in carangiform swimming, we created a bio-inspired digital trout. This model combined multibody dynamics, Hill-type muscle modeling, and a high-fidelity fluid-structure interaction algorithm, accurately replicating a real trout's form and properties. Using deep reinforcement learning, the trout's neural system achieved hierarchical spatiotemporal control of muscle activation. We systematically examined how activation strategies affect speed and energy use. Results show that axial myomere coupling-with activation spanning over 0.5 body lengths-is crucial for stable body wave propagation. Moderate muscle contraction duration ([0.1,0.3] of a tail-beat cycle) lets the body and fluid act as a passive damping system, cutting energy use. Additionally, the activation phase lag of myomeres shapes the body wave; if too large, it causes antagonistic contractions that hinder thrust. These findings advance bio-inspired locomotion understanding and aid energy-efficient underwater system design.

Fish schooling, an adaptive strategy shaped by long-term evolution, is closely associated with core biological needs such as survival and reproduction. This study, having adopted a numerical simulation framework built by combining the deep reinforcement learning algorithm with the immersed boundary-lattice Boltzmann fluid–solid interaction simulation method, focused on investigating the effects of modal transitions on energy efficiency and array dynamics during large-scale turning of fish schools under low hydrodynamic pressure environments. Initially, strategic control was applied to two fish utilizing body–caudal fin propulsion, aiming to explore their schooling modes and the intrinsic energy-saving mechanisms inherent to each mode. Subsequently, the school size was expanded non-proportionally, and the influence of modal transitions on energy consumption was analyzed through a leader-guided turning strategy. Results indicated that under low hydrodynamic pressure, carangiform fish exhibited three modes in their modal composition, namely, the vortex action mode, the lateral force action mode, and the combined action mode. Additionally, with an increased number of schooling individuals, the modal transitions of carangiform fish demonstrated greater arbitrariness and flexibility. Notably, exclusive reliance on hydrodynamic information perception via the lateral line could enhance efficiency in small-scale schools. However, as the school expanded, the complex flow field limited the ability of this approach to significantly improve overall schooling performance; meanwhile, in low hydrodynamic pressure environments, the collective movement of fish schools does not depend solely on hydrodynamic information. These findings provide theoretical guidance and strategic foundations for the design of clustered bionic underwater intelligent robots with different undulatory propulsion modes.

Pumped storage power stations are effective stabilizers and regulators of the power grids. However, during the transient process, especially the operating point entering the S-shaped region, the internal flow patterns and pressure pulsations in the pump–turbine unit change violently, seriously affecting the safety of the power stations, which requires enough optimizations in the design stage of the pump–turbine. In this paper, to explore the key factors which influence the evolutions of flow patterns and pressure pulsations during the runaway process, three pump–turbine runners with different inlet blade lean, including positive angle, no angle and negative angle, were selected to simulate by using the three-dimensional method. The results show that the changes in the inlet blade lean angles have significant effects on the variation periods and maximum values of the macro parameters during the runaway process, and especially the runner with no lean angle results in the smallest oscillation periods and pressure pulsations but enlarges the runner radial forces. In addition, backflows generate from the hub side under the cases with positive or no blade lean angle, while those occur from the shroud side due to the negative angle. The results provide a basic reference for the design of the pump–turbine.

The design and optimization of fishways and other fish-passage facilities are one of the critical issues in hydraulic engineering. Traditional methods using physical experiments for fishway design and optimization face challenges such as the uncontrollability of fish behavior, limited non-intrusive measurement techniques, and nonlinear scale effects. Numerical simulation methods can provide the hydraulic performance information of fishways by analyzing flow velocity, turbulence energy, and flow patterns, but fail to account for the active responses of fish to the hydrodynamic characteristics of the environment. In this study, a research paradigm of using embodied intelligent fish to optimize eco-hydraulic facilities was attempted. The core of this research paradigm is a simulation platform for intelligent fish based on deep reinforcement learning (DRL) and the immersed boundary–lattice Boltzmann (IB-LB) coupling algorithm. Based on this platform, by endowing fish with biological tendencies and biometric features related to perception/feedback/decision-making at the individual scale, embodied intelligent fish can achieve multimodal perception and autonomous decision-making in complex fishway digital flow fields based on the potential habits of live fish. Using the proposed framework, conduct end-to-end deep reinforcement learning training on intelligent fish and then deploy the trained embodied intelligent fish in a virtual vertical-slot fishway for ecological hydrodynamic experiments. Comparative analyses were conducted on the fish-passage performance of three different fishway geometric shapes. The results demonstrated that the new research paradigm evaluates the structural characteristics of fishways through the adaptive response behavior of fish to the hydrodynamic environment, which can provide quantitative guidance for fishway design from the terms of passage path, passage time, energy consumption, etc. This study belonged to an individual-scale digital twin and was an innovative attempt to utilize virtual intelligent lifeforms at the individual scale to conduct simulation-based experimental research.

The study of fish swimming behavior and locomotion mechanisms holds substantial scientific and engineering significance. With the rapid progression of artificial intelligence, the integration of artificial intelligence with high-precision numerical simulation methods presents a novel and highly efficient tool for investigating fish behavior. In this paper, we proposed a fish perception model that more closely reflects natural logic. By introducing the individual vision and partially visibility model, a physics-based visual system that mirrored the sensory capabilities of live fish was developed. Furthermore, through the construction of a flow vision using conventional neural networks, we enhanced the intelligent fish's ability to detect unsteady hydrodynamic parameters via numerical lateral line. The validity of the new model was demonstrated through experiments, which the intelligent fish hunts complex moving targets in unsteady flow. Finally, we applied the model to study the refuge/predation behaviors of coral reef fish under varying unsteady flow pressures. The results indicated that swimming capabilities significantly impact fish survival strategies in high flow velocity, highly unsteady hydrodynamic environments, shaping distinct evolutionary decision-making traits. These insights may help to understand the niche competition mechanisms of fish in different flow conditions.

The reef ecosystem plays a vital role as a habitat for fish species with limited swimming capabilities, serving not only as a sanctuary and food source but also influencing their behavioral tendencies. Understanding the intricate mechanism through which fish adeptly navigate the moving targets within reef environments within complex water flow, all while evading obstacles and maintaining stable postures, has remained a challenging and prominent subject in the realms of fish behavior, ecology, and biomimetics alike. An integrated simulation framework is used to investigate fish predation problems within intricate environments, combining deep reinforcement learning algorithms (DRL) with high-precision fluid-structure interaction numerical methods-immersed boundary lattice Boltzmann method (lB-LBM). The Soft Actor-Critic (SAC) algorithm is used to improve the intelligent fish’s capacity for random exploration, tackling the multi-objective sparse reward challenge inherent in real-world scenarios. Additionally, a reward shaping method tailored to its action purposes has been developed, capable of capturing outcomes and trend characteristics effectively. The convergence and robustness advantages of the method elucidated in this paper are showcased through two case studies: one addressing fish capturing randomly moving targets in hydrostatic flow field, and the other focusing on fish counter-current foraging in reef environments to capture drifting food. A comprehensive analysis was conducted of the influence and significance of various reward types on the decision-making processes of intelligent fish within intricate environments.