Uncertainties of runoff projections arise from different sources of origin, such as climate scenarios (RCPs), global climate models (GCMs) and statistical downscaling (SD) methods. Assessment of uncertainties related to the mentioned sources was carried out for selected rivers of Lithuania (Minija, Nevėžis and Šventoji). These rivers reflect conditions of different hydrological regions (western, central and southeastern). Using HBV software, hydrological models were created for river runoff projections in the near (2021–2040) and far (2081–2100) future. The runoff projections according to three RCP scenarios, three GCMs and three SD methods were created. In the Western hydrological region represented by the Minija River, the GCMs were the most dominant uncertainty source (41.0–44.5%) in the runoff projections. Meanwhile, uncertainties of runoff projections from central (Nevėžis River) and southeastern (Šventoji River) regions of Lithuania were related to SD methods and the range of uncertainties fluctuates from 39.4% to 60.9%. In western Lithuania, the main source of rivers' supply is precipitation, where projections highly depend on selected GCMs. The rivers from central and southeastern regions are more sensitive to the SD methods, which not always precisely adjust the meteorological variables from a large grid cell of GCM into catchment scale.

The determination of river velocity is important for hydromorphological analyses and river monitoring systems. Indirect measurements of river velocity using videos recorded by unmanned aerial vehicles (UAV) allow fast and cost-effective processing of information about the river stretch. This paper presents a method for computing flow velocity of the river surface using deep supervised model RAFT to determine the optical flow in combination with image pre-processing by convolutional operations. Moreover, the windiness coefficients and variance score were proposed to evaluate reliability of the collected data and the obtained results of optical flow detection. Various image pre-processing techniques were applied, namely the selection of the analysed area and the number of convolutional operations to select the one with the lowest variance score. This score represents the consistency of the river flow velocity during the video and can be used to filter out unreliable results. The numerical experiments were performed using the videos and directly measured velocity values of 4 shallow rivers in Lithuania collected during the field surveys. The optical velocity estimation method showed good correspondence to the directly measured values for the velocity range from 0 m/s to 0.8 m/s in the points with low variance score up to 0.192 that represents the first quartile of the variance. The optical flow method tends to underestimate the velocity up to 0.5 m/s for the quartiles with the higher variance scores. It was shown that in most cases the lowest variance score value was obtained using pre-processing techniques without convolutional operations. However, the need to analyse various pre-processing techniques arises from the different origin of the objects moving on the river surface.

Hydromorphology of rivers assessed through direct measurements is a time-consuming and relatively expensive procedure. The rapid development of unmanned aerial vehicles and machine learning (ML) technologies enables the usage of aerial images to determine hydromorphological units (HMUs) automatically. The application of various direct and indirect data sources and their combinations for the determination of river HMUs from aerial images was the main aim of this research. Aerial images with and without the Sobel filter, a layer of boulders identified using Yolov5x6, and a layer of direct measurements of depth and streamflow velocity were used as data sources. Three ML models were constructed for the cases if one, two, or three data sources were used. The ML models for HMU segmentation were constructed of MobileNetV2 pre-trained on ImageNet data for the feature extraction part and U-net for the segmentation part. The stratified K-fold cross-validation with five folds was carried out to evaluate the performance of the model due to the limited dataset. The analysis of the ML results showed that the measured metrics of segmentation using direct measurements were close to the ones of the model trained only on the combination of boulder layer and aerial images with the Sobel filter. The obtained results demonstrated the potential of the applied approach for the determination of HMUs only from the aerial images, and provided a basis for further development to increase its accuracy.

Aquatic ecosystems are particularly vulnerable to anthropogenic activity and climate change. The changes in flow regimes in Lithuanian lowland rivers due to the operation of hydropower plants (HPPs) and the impact of altered flow on some fish species have already been studied. The impact of climate change on future natural river runoff and the structure of fish assemblages was also investigated. However, it is still unknown how the combined effect of climate change and flow regulation related to hydropower generation may affect fish assemblages in the downstream river reaches below the Lithuanian HPPs. In this study, the physical habitat modelling system MesoHABSIM was used to simulate spatial and temporal changes in aquatic habitats availability for different fish species under the influence of HPP at different climate change scenarios. Changes in the available habitat were assessed for common fish species in four HPP-affected rivers representing different hydrological regions of Lithuania. The modelling results showed that the operation of HPP under climate change conditions in most rivers could be beneficial for small benthic fish species such as gudgeon Gobio gobio and stone loach Barbatula barbatula. Meanwhile, for larger fish species (e.g., chub Squalius cephalus and vimba Vimba vimba) the alteration in the temporal availability of suitable habitat was relatively higher.