This thesis is aimed at assessment of drainage conditions at the river Loucna in the cadastral area of Dasice. The examined section is 3,88 km long and runs through out of the city and in the city of Dasice. On the left bank of the river there are several historic buildings that are potentially at risk for 100 years of flow. Capacity assessment is performed using the 1D mathematical program HEC - RAS in which the flow model is created and the calculation of the flow rates for individual N - year flows. On the basis of the results of the program is conducted conceptual desing of flood protection measure. At the same time is conducted conceptual desing of fish ladder on the weir and a sluice closure on the intake for the race.

This diploma thesis deals with a design of the reconstruction of a smixed weir on the Oslava river in Oslavany town. The introduction describes the site of interest and the the occurrence of ice events. There are several types of fish ladders described theoretically. Further on in the thesis there is desribed the state of the objects on the flow and the state of the river basin in the area of interest of Oslava river. Next part of the thesis deals with the design of a movable baying structure (a hollow flap) and fish ladder type bypass channel. An impact assessment of the current and newly proposed weir on flow in the HEC-RAS program was carried out. The project also includes the basin adjustment in overweir and an evaluation of the stability of the newly designed construction.

The purpose of the diploma thesis „Design of a movable weir on the Želivka river" is a design of the reconstruction of a fixed weir in Soutice village on the river Želivka at km 1,639. The first part of the thesis deals with the localization of the area of interest and a description of all documents needed for the weir design. The first part also includes a short search of the considered structures, the findings of which are further applied in the design of a movable weir structure. Furthermore, the work continues by determining the design flow and selecting a suitable structure of the fixed weir substructure and movable closure, which is fitted to the substructure. Based on the selected types of structures, hydrotechnical calculations are performed, which also include a partial assessment of the weir stability. The thesis ends with a technical description of the proposed objects and a final evaluation of the determined achievements of the work. Part of the study is a drawing part documenting designed objects.

Hydropower plants create blockages in fish migration routes. Fish ladders can serve as alternative routes but are complex to install and follow up to help adapt and develop them further. In this study, computer vision tools are considered in this regard. More specifically, object detection is applied to images collected in a hydropower plant fish ladder to localise and classify wild, farmed and unknown fish labelled according to the presence, absence or uncertainty of an adipose fin. Fish migration patterns are not deterministic, making it a challenge to collect representative and balanced data to train a model that is resilient to changing conditions. In this study, two data imbalances are addressed by modifying a YOLOv3 baseline model: foreground-foreground class imbalance is targeted using hard and soft resampling and positional imbalance using translation augmentation. YOLOv3 is a convolutional neural network predicting bounding box coordinates, class probabilities and confidence scores simultaneously. It divides images into grids and makes predictions based on grid cell locations and anchor box offsets. Performance is estimated across 10 random data splits and different bounding box overlap thresholds, using (mean) average precision as well as recall, precision and F1 score estimated at optimal validation set confidence thresholds. The Wilcoxon signed-ranks test is used for determining statistical significance. In experiments, the best performance was observed on wild and farmed fish, with F1 scores reaching 94.8 and 89.0 percent respectively. The inconsistent appearance of unknown fish appears harder to generalise to, with a corresponding F1 score of 65.7 percent. Soft sampling but especially translation augmentation contributed to enhanced performance and reduced variance, implying that the baseline model is particularly sensitive to positional imbalance. Spatial dependencies introduced by YOLOv3’s grid cell strategy likely produce local bias or overfitting. An experimental evaluation highlight the importance of not relying on a single data split when evaluating performance on a moderately large or custom dataset. A key challenge observed in experiments is the choice of a suitable confidence threshold, influencing the dynamics of the results. / Vattenkraftverk blockerar fiskars vandringsvägar. Fisktrappor kan skapa alternativa vägar men är komplexa att installera och följa upp för vidare anpassning och utveckling. I denna studie betraktas datorseende i detta avseende. Mer specifikt appliceras objektdetektering på bilder samlade i en fisktrappa i anslutning till ett vattenkraftverk, med målet att lokalisera och klassificera vilda, odlade och okända fiskar baserat på förekomsten, avsaknaden eller osäkerheten av en fett-fena. Fiskars migrationsmönster är inte deterministiska vilket gör det svårt att samla representativ och balanserad data för att trana en modell som kan hantera förändrade förutsättningar. I denna studie addresseras två obalanser i datan genom modifikation av en YOLOv3 baslinjemodell: klass-obalans genom hård och mjuk återanvändning av data och positionell obalans genom translation av bilder innan träning. YOLOv3 är ett convolutional neural network som simultant förutsäger avgränsnings-lådor, klass-sannolikheter och prediktions-säkerhet. Bilder delas upp i rutnätceller och prediktioner görs baserat på cellers position samt modifikation av fördefinierade avgränsningslådor. Resultat beräknas på 10 slumpmässiga uppdelningar av datan och för olika tröskelvärden för avgränsningslådors överlappning. På detta beräknas (mean) average precision, liksom recall, precision och F1 score med tröskelvärden för prediktions-säkerhet beräknat på valideringsdata. Wilcoxon signed-ranks test används för att avgöra statistisk signifikans. Bäst resultat observeras på vilda och odlade fiskar, med F1 scores som når 94.8 respektive 89.0 procent. Okända fiskars inkonsekventa utseenden verkar svårare att generalisera till, med en motsvarande F1 score på 65.7 procent. Mjuk återanvändning av data men speciellt translation bidrar till förbättrad prestanda och minskad varians, vilket pekar på att baslinjemodellen är särskilt känslig för positionell obalans. Spatiala beroenden skapade av YOLOv3s rutnäts-strategi producerar troligen lokal partiskhet eller överträning. I en experimentell utvärdering understryks vikten av multipel uppdelning av datan vid evaluering på ett måttligt stort eller egenskapat dataset. Att välja tröskelvärdet för prediktions-säkerhet anses utmanande och påverkar resultatens dynamik.