Fragmentation of rivers has a negative impact on river’s ecological status which can be improved by the construction of fishways next to obstacles in rivers that prevent a free migration. Flow field characteristics are key factors in the design process of hydraulically efficient fishways—flow and turbulence patterns in a functional fishway allow fish to enter, progress through and exit with minimum time/energy expenditure. The aim of this paper is an experimental study of the flow field characteristics measured in the physical fishway model with the goal of providing information on the Reynold’s shear stress distribution that would facilitate their design in accordance with the environmental requirements. The focus of the research was on the nominally hydraulically efficient con-figuration pool-type fishways—pool-orifice and vertical slot. Fishway geometry was varied for bottom slope (7.5%, 10% and 12.5%), pool length (45 cm, 60 cm and 90 cm) and orifice size (8 × 8 cm, 10 × 10 cm and 12 × 12 cm) in a model scaled 1:3 to the prototype. Since Reynold’s shear stress has been identified as the main turbulent parameter affecting fish swimming performance and behavior, it is used as the basis for the analyses. The velocity data were collected with Vectrino ADV and processed in all three planes—streamwise, horizontal and vertical. Reynold’s shear stress data were analyzed according to the injury (>50 N/m²) and disorientation (>30 N/m²) biocriteria boundaries defined in the literature. The percentage of the flow field exceeding the boundaries were analyzed depending on the fishway geometry. The results obtained in this research suggest that the critical design parameter is the orifice size for the pool-orifice fishways and the pool length for the VS fishway. The Reynold’s shear stress is generally the highest in the bottom layer for pool-orifice fishways and the surface layer for vertical slot fishways.

Modelling and prediction of mean monthly flow are of particular importance for long-term planning in hydrology and water resources management. Therefore, a simplified and robust modelling procedure, derived from clearly and concisely established methodology, can benefit both researchers and practitioners. The main objective of this study is to develop a robust yet simple model, capable of producing predictions of satisfactory accuracy on previously unseen data. Two chronological data allocation strategies (C1 and C2), differing in the proportions of training, calibration, and verification subsets, were evaluated to analyze their influence on model accuracy and reliability. Chain and ensemble modelling techniques were applied, resulting in several stacking regressors with different combinations of base models and final estimators. The best-performing ensemble (C2) consisted of a support vector machine, histogram gradient boosting regressor, elastic net, and two dummy regressors as base models, with an artificial neural network as the final estimator. Within the ensemble structure, dummy regressors and histogram gradient boosting regressor were used to extend the predictive range, while elastic net and support vector machine captured the overall flow bias and fundamental flow dynamics. The artificial neural network final estimator was used to integrate these components into the final flow prediction. Compared to C1, the C2 allocations strategy achieved improved generalization capability and narrower confidence intervals due to the larger training subset, indicating higher model reliability for long-term monthly flow forecasting. The study additionally emphasizes the importance of appropriate methodological workflow, careful dataset treatment, and comprehensive model evaluation using complementary statistical and hydrological analysis tools.