Drought is one of many critical problems that could arise as a result of climate change as it has an impact on many aspects of the world, including water resources and water scarcity. In this study, an assessment of hydrological drought in the Gidra River is carried out to characterize dry, normal, and wet hydrological situations by using the Slovak Hydrometeorological Institute (SHMI) methodology. The water bearing coefficient is used as the index of the hydrological drought. As machine and deep learning are increasingly being used in many areas of hydroinformatics, this study is utilized artificial neural networks (ANNs) and support vector machine (SVM) models to predict the hydrological drought in the Gidra River based on daily average discharges in January, February, March, and April of the corresponding year. The study utilized in total 58 years of daily average discharge values containing 35 normal and wet years and 23 dry years. The results of the study show high accuracy of 100% in predicting hydrological drought in the Gidra River. The early classification of the hydrological situation in the Gidra River shows the potential of integrating water management with the deep and machine learning models in terms of irrigation planning and mitigation of drought effects.

This study aims to develop an advanced deep learning model, Hydro-Informer, for accurate water level and flood predictions, emphasizing extreme event forecasting. Utilizing a comprehensive dataset from the Slovak Hydrometeorological Institute SHMI (2008–2020), which includes precipitation, water level, and discharge data, the model was trained using a ladder technique with a custom loss function to enhance focus on extreme values. The architecture integrates Recurrent and Convolutional Neural Networks (RNN, CNN), and Multi-Head Attention layers. Hydro-Informer achieved significant performance, with a Coefficient of Determination (R²) of 0.88, effectively predicting extreme water levels 12 h in advance in a river environment free from human regulation and structures. The model’s strong performance in identifying extreme events highlights its potential for enhancing flood management and disaster preparedness. By integrating with diverse data sources, the model can be used to develop a well-functioning warning system to mitigate flood impacts. This work proposes a novel architecture suitable for locations without water regulation structures.

The most appropriate method to protect settlements and economically important sites from flood hazard, is the implementation of flood protection measures in stream catchments and protected localities, which contribute to reduce the peak flow and distribution of the flood wave over a longer period of time. If such measures are not realistic or ineffective, it is necessary to focus on flood protection directly on the area of the protected side or its vicinity. Where the lag time between the flood threat detection and actual flood onset is short, one possible measure is to increase the capacity of the watercourse, very often in combination with other flood mitigation measures in the protected area. The engineering approach to flood protection is the subject of many scientific research studies. Permission for flood protection structures depends on their environmental impact assessment (EIA), according to Law no. 24/2002 Coll. on Environmental Impact Assessment in the Slovak Republic, annex no. 8 (list of activities subject to EIA). Based on the EIA, it is possible to select the best alternative of flood protection, i.e., the alternative with the lowest risk impact on the environment. This paper aims to analyse the flood protection measures along the Lukavica stream (central Slovakia), applying hydraulic models. The best alternative with the lowest impact on the environment, assessed using the risk analysis method, consists of detention reservoir construction. An effective combination of environmental impact assessment and hydraulic modelling contribute to the selection of an effective flood protection measure in the territory.

Nature-like fish passes are commonly designed as a preferred way to overcome barriers in rivers. However, meeting the recommended hydraulic parameters for these passes can be challenging. As a result, boulders or sills are often incorporated to supplement their structure. From a hydraulic standpoint, the crucial parameters under investigation are the depths and velocities (or the corresponding velocity field). In this study, a comprehensive analysis was conducted on a full-width rock-ramp fish pass constructed in a river, specifically targeting the barbel zone. The achieved parameters were assessed through direct field measurements, complemented by mathematical modeling using 1D and 2D HEC-RAS models (version 6.3.1). For the assessment of model accuracy, the error indices root mean square error (RMSE) and mean absolute error (MAE) were used. Based on their evaluation, the 1D model provides more precise results in the assessed profiles (the RMSE for depths (m) was 0.0663 (for velocities (m∙s⁻¹) 0.293) compared to the 2D model, where the RMSE for depths (m) was 0.070 (for velocities (m∙s⁻¹) 0.398), the MAE for the 1D model for depths (m) was 0.0350 (for velocities (m∙s⁻¹) 0.185) compared to the 2D model, where the MAE for depths (m) was 0.0375 (for velocities (m∙s⁻¹) 0.274)). The findings highlight the differences in the problem-solving approaches between the models as well as the potential for simplifications in practical applications.

The accurate estimation of Manning’s roughness coefficient (n) is critical for hydraulic modeling in open channels. In fish passes designed as close-to-nature structures, this coefficient has a strong influence on the overall design and operation. This study evaluates n for the Veľké Kozmálovce fish pass using high-resolution drone imagery and image analysis techniques to determine riverbed surface characteristics and extract a grain size distribution curve. Various empirical equations based on Strickler’s formula were applied to specific grain sizes, yielding average n values of 0.036 and 0.037. Cowan’s method, which considers surface material, irregularities, vegetation, obstructions, and meandering, provided an upper-bound estimate of 0.040. However, this method is known to overestimate roughness in some cases. The Step-by-Step method, applied with hydraulic field measurements, resulted in a narrower range of n from 0.027 to 0.037. Overall, estimated values across all methods ranged between 0.023 and 0.040, reflecting the structural complexity of the fish pass, which includes boulders embedded in concrete and coarse gravel infill. These findings highlight the limitations of using generalized tabulated values for artificial channels and demonstrate that drone-based photogrammetry combined with empirical and analytical approaches can effectively capture spatial variability in hydraulic roughness.

The article describes the process of redesigning the intake structure of the fish pass at the Žilina water structure in Slovakia. The existing intake structure does not meet the passability requirements for the target species of migratory fish. A design utilizing intake windows at various levels that cover fluctuations in the water level in the reservoir, which has been successfully used for other water structures, has been proposed. The new design was subjected to hydraulic calculations and simulations in the HECRAS 2D, 2D numerical model in order to achieve the required parameters such as the discharges, depths, and velocities within the limits for the specified fish zone.