Janine Bryan | Geology Reports

USGS2024

Prefabricated Zero Ascend Omnispecies (ZAO) modular fish passage modules using advanced manufacturing techniques

The Zero Ascend Omnispecies (ZAO) fish passage attraction module “ZAO Attractor” is a novel system designed to facilitate upstream passage for a broad spectrum of fish species, with a particular focus on American shad and river herring (alewife and/or blueback herring). Combining the use of prefabricated, modular components with advanced manufacturing, the ZAO aims to provide a cost-effective and scalable solution for fish passage attractions across various hydropower sites. The system features a surface level entry, so fish do not need to climb. In addition, it is designed to be adjusted and repositioned to create the most effective attraction flows by managing the outflows from hydropower turbines. Budget Period 1 (BP1) focused on the design and modeling of the ZAO Attractor and demonstrated the engineering feasibility of a modular, prefabricated, hydrodynamically efficient structure with surface level entry and passage. During BP1, the hypothesis was that certain structural adaptations, such as the addition of long fins, could direct turbine outflows to create a desirable downstream flow. Simulations, however, were inconclusive, revealing the complex nature of fish preferences for hydraulic conditions. It was discovered that there were limited published studies on the direct correlation between quantified flow patterns and fish attraction, emphasizing the need for controlled studies to observe and measure these effects. In Budget Period 2 (BP2), controlled studies with live fish were prioritized to address these complexities. A partially scaled ZAO Attractor was evaluated in laboratory conditions using native river water to assess its capability to attract and guide fish. Despite challenges with flume flow conditions and the impact of flume dimensions on flow directionality and velocity, the studies provided insights into fish behavior and preferences, particularly the requirement for a consistent flow stream for migration cues. Adjustments to the fin structure demonstrated potential effectiveness in guiding fish toward the module. However, the hydraulic conditions within the flume environment did not accurately reflect typical in-river scenarios, therefore the results were inconclusive with respect to the optimal system configuration for in-river use. In the future, conducting comprehensive field studies can enhance understanding of the interactions between fish behavior and flow conditions created by the ZAO Attractor. Additionally, a design review is advised, particularly regarding the load scenarios throughout the seasons and positioning of the ZAO Attractor. These studies should continue to refine the design to achieve its intended benefits: economical and effective fish attraction and passage that can be adapted to specific site conditions while allowing for continued energy generation at sites up for re-licensure and adding hydropower generation to previously untapped resources in non-powered dams and new stream reaches. In conclusion, the ZAO fish passage attraction module presents a promising approach to fish passage at hydropower stations, with the potential to balance environmental concerns with renewable energy development. However, further field validation and optimization are necessary to ensure its effectiveness and practicality in real-world applications.

Final Technical Report↗

USGS2020

Advancements towards selective barrier passage by automatic species identification: Applications of deep convolutional neural networks on images of dewatered fish

Invasive species negatively affect enterprises such as fisheries, agriculture, and international trade. In the Laurentian Great Lakes Basin, threats include invasive sea lamprey ( Petromyzon marinus ) and the four major Chinese carps. Barriers have proven to be an effective mechanism for managing invasive species but are detrimental in that they also limit the migration of desirable, native species. Fish passage technologies that selectively pass desirable species while blocking undesirable species are needed. Key to an automated selective barrier passage system is a high precision fish classifier to assign fish to be passed or blocked. Presented is an evaluation of two classifiers developed using images of partially dewatered fish captured from a commercial, high-speed camera array. For a lamprey vs. non-lamprey classification task, an ensemble prediction approach achieved near perfect accuracy on both a validation and test dataset. For a species classification task for 13 species found in the Great Lakes region, an ensemble prediction approach achieved accuracies of 96% and 97% on a validation and test dataset, respectively. Both prediction approaches were based on deep convolutional neural networks constructed using transfer learning and image augmentation. The study provides an important proof-of-concept for the viability in fully automated, selective fish passage systems.

Illinois, Michigan,Ohio↗

USGS2020

Applications of deep convolutional neural networks to predict length, circumference, and weight from mostly dewatered images of fish

Simple biometric data of fish aid fishery management tasks such as monitoring the structure of fish populations and regulating recreational harvest. While these data are foundational to fishery research and management, the collection of length and weight data through physical handling of the fish is challenging as it is time consuming for personnel and can be stressful for the fish. Recent advances in imaging technology and machine learning now offer alternatives for capturing biometric data. To investigate the potential of deep convolutional neural networks to predict biometric data, several regressors were trained and evaluated on data stemming from the FishL™ Recognition System and manual measurements of length, girth, and weight. The dataset consisted of 694 fish from 22 different species common to Laurentian Great Lakes. Even with such a diverse dataset and variety of presentations by the fish, the regressors proved to be robust and achieved competitive mean percent errors in the range of 5.5 to 7.6% for length and girth on an evaluation dataset. Potential applications of this work could increase the efficiency and accuracy of routine survey work by fishery professionals and provide a means for longer‐term automated collection of fish biometric data.

Illinois, Michigan, Ohio↗