Geology topics

Daniel Zielinski

Publications and source records attributed to Daniel Zielinski.

6 recordsLinked to original sources

USGS2025

Designing sortable guilds for multispecies selective fish passage

The importance of connectivity for freshwater organisms is widely recognised, yet in-stream barriers associated with population declines and increased risk of extinction remain globally ubiquitous. Despite their negative consequences, these barriers can protect aquatic communities by limiting the spread of invasive species, leading to conflicting management goals in some regions. Selective fish passage is a solution for the conflicting goals of passing native, desirable species while restricting the spread of invasives. Approaches that can target groups of species sharing similar attributes (i.e. guilds) are likely to be more efficient than those that target species individually, particularly in taxonomically diverse systems. We explored the guild structure of 220 Great Lakes freshwater fishes based on morphological, phenological, physiological and behavioural attributes associated with passage and movement. We identified five distinct guilds as well as the attributes most important for defining these groupings: maximum total length, trophic level, relative eye size, spawning temperature, spawning season, presence/absence of ampullary electroreceptors and the presence/absence of hearing specialisations. The approaches outlined in this work can be generalised to enhance selective fish passage in aquatic ecosystems worldwide.

Fish and Fisheries↗

USGS2025

A real-time fish detection system for partially dewatered fish to support selective fish passage

Recent advances in fish transportation technologies and deep machine learning-based fish classification have created an opportunity for real-time, autonomous fish sorting through a selective passage mechanism. This research presents a case study of a novel application that utilizes deep machine learning to detect partially dewatered fish exiting an Archimedes Screw Fish Lift (ASFL). A MobileNet SSD model was trained on images of partially dewatered fish volitionally passing through an ASFL. Then, this model was integrated with a network video recorder to monitor video from the ASFL. Additional models were also trained using images from a similar fish scanning device to test the feasibility of this approach for fish classification. Open source software and edge computing design principles were employed to ensure that the system is capable of fast data processing. The findings from this research demonstrate that such a system integrated with an ASFL can support real-time fish detection. This research contributes to the goal of automated data collection in a selective fish passage system and presents a viable path towards realizing optical fish sorting.

Michigan↗

USGS2022

Test of a screw-style fish lift for introducing migratory fish into a selective fish passage device

Barriers are an effective mechanism for managing invasive species like sea lamprey in the Lau-rentian Great Lakes, but are detrimental because they limit the migration of desirable, native species. Fish passage technologies that selectively pass desirable species while blocking unde-sirable species are needed. Optical sorting tools combined with newly developed computer learning algorithms could be used to identify invasive species from high resolution imagery and potentially isolate them from an assortment of Great Lakes fishes. Many existing barriers lack fishways and optical sorting may require fish to be dewatered for image capture. The Archimedes screw, a device originating from 234 BC, offers the potential to continuously lift fish and water over low-head barriers or into an optical sorting device. To test the efficacy of an Archimedes screw fish lift to capture and pass Great Lakes fishes, we built a field-scale prototype and installed it at the Cheboygan Dam, Michigan USA in 2021. The fish lift safely transported 704 fish (688 of which were suckers) in 11 days. Passage of suckers through the fish lift increased with water temperature and attraction flow. There were no observed injuries in transported fish or mortalities in a subset of suckers held post-transport.

Michigan↗

USGS2021

Behavioral responses of sea lamprey (Petromyzon marinus) and white sucker (Catostomus commersonii) to turbulent flow during fishway passage attempts

An understanding of how undesirable and desirable fish species respond behaviorally to turbulent flow in fishways would guide development of selective fish passage techniques. We applied high-resolution computational fluid dynamics modeling and competing risks analysis towards the development of predictive selective passage models. Sea lamprey ( Petromyzon marinus ; an invasive fish in the Great Lakes Basin, North America) upstream passage probability declined from 0.73 to 0.03 as flow conditions became increasingly turbulent, while declines in white sucker ( Catostomus commersonii , a native fish in the region) upstream passage probability were less substantial (0.53 to 0.44). Deploying a sea lamprey trap in the fishway did not effectively reduce sea lamprey upstream passage probability, though capture rate increased during trials with cooler water temperature and low total kinetic energy. Bifurcated fishways that maintain low turbulent flow in the entrapment route and high turbulent flow in the upstream passage route could increase the effectiveness of trapping sea lamprey in fishways as a means to advance selective passage goals.

Wisconsin↗

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↗