Understanding the upstream-attempt behavior of fish in high-flow environments is important for refining behavioral simulations, optimizing fish-passage design, and protecting aquatic ecosystems. This study investigates Schizothorax oconnori, an endemic fish in the Yarlung Tsangpo River on the Qinghai–Tibet Plateau, using a multi-model analytical framework integrating a generalized linear mixed-effects model, Random Forest, SHapley Additive exPlanations, and GeoDetector. Results showed that remaining endurance and nominal flow velocity were positively associated with fish upstream-attempt initiation. Attempt termination reflected endurance depletion, initial endurance, and hydraulic variability. Model-predicted termination probability increased markedly when (i) cumulative endurance consumption during the current attempt exceeded ~11% or (ii) fish began an attempt with an initial endurance status below ~95%. These model-derived change points represent within-attempt endurance depletion and reduced endurance available at attempt initiation, respectively. Across attempt sequences, the dominant explanatory factors showed an apparent shift from physiological condition during the first attempt to hydraulic variability during subsequent attempts. This sequence-related pattern is consistent with behavioral adjustment based on repeated experience in the flow environment, although cumulative fatigue, stress, individual differences, and experimental procedures may also contribute. Hydraulic-variability metrics along the trajectory showed greater explanatory importance than several instantaneous hydraulic variables, and physiological condition and hydraulic variability together enhanced explanatory power. This study provides a quantitative multi-model framework for analyzing upstream-attempt behavior and offers a scientific basis for refining behavioral simulations and optimizing fish-passage facilities.

Fish can perceive and respond to local flow structures when selecting microhabitats, yet how scale-dependent hydrodynamic heterogeneity shapes behavioral habitat choice remains poorly understood. In this study, a multi-scale rock-array flow field was constructed using flume experiments, and the volitional swimming behavior of Schizothorax grahami was observed. Hydrodynamic parameters including velocity magnitude (U_mag), turbulent kinetic energy (TKE), and kinetic energy gradient (KEG) were analyzed. The results indicated that fish distribution changed with rock size: at a rock-element diameter of 0.12 m, fish were dispersed without forming stable high-utilization core areas; at 0.24 m, fish aggregated in the lee-side regions behind the rock elements; and at 0.50 m, fish shifted toward the upstream faces. The hydrodynamic variables significantly associated with fish microhabitat selection varied with rock-array scale: in the 0.24 m rock arrays, KEG differed significantly between high- and low-use units under all flow conditions; in the 0.50 m rock arrays, U_mag and TKE showed consistent and significant between-group differences across flow conditions. Moreover, cross-scale overlap analysis revealed that the utilization range of velocity magnitude had the highest overlap, followed by TKE, with KEG exhibiting the lowest overlap. Collectively, these findings support a hierarchical interpretation of fish microhabitat selection characterized by “velocity rigidity–turbulence elasticity,” providing a potential perspective for understanding differences in the hydrodynamic variables associated with fish microhabitat selection across studies. These results indicate that both mean velocity constraints and local turbulence-creating structures should be considered in river habitat restoration and roughness element configuration.