An acoustic telemetry receiver was mounted on a gliding robotic fish, a novel type of autonomous underwater vehicle (AUV) during a series of field trials in a freshwater lake. Like underwater gliders, gliding robotic fish (dubbed GRACE, for Gliding-Robot-ACE) achieve locomotion primarily through buoyancy-driven gliding or spiraling. They are also equipped with an active tail fin that can provide extra propulsion (e.g., “swimming” against current), act as a rudder to improve steering during glide/spiral, and improve maneuverability via asymmetrical flapping (e.g., tight turns on the surface or during gliding). Consequently, gliding robotic fish combine the energy-efficient nature of underwater gliders with the high-maneuverability of robotic fish (a type of bio-inspired surface robots) and hence hold great potential in long-duration monitoring of a broad spectrum of aquatic environments. Data are comprised of characteristics of the receivers, transmitters, mobile platform (gliding robotic fish), and environment at time when each tag signal was emitted.

Autonomous underwater vehicles (AUVs) are increasingly being used to collect physical, chemical, and biological information in the marine environment. Recent efforts have been made to merge AUV technology with acoustic telemetry to provide information on the distribution and movements of marine fish. During 2010, we conducted a study in coastal waters near Juneau, Alaska to determine the feasibility of using AUVs to locate marine species under rigorous field conditions, and to compare this approach with traditional vessel-based tracking. Tracking surveys were conducted with a REMUS 100 AUV equipped with an integrated acoustic receiver and hydrophone. The AUV was programmed to navigate along predetermined routes to detect acoustic transmitters within the area. Comparable surveys were conducted with a boat equipped with acoustic tracking gear. Moorings with transmitters at 20-500 m were deployed to provide acoustic targets at known locations and depths. Marine fishes and crabs were tagged to provide mobile targets. Transmitter depth had a major impact on tracking performance. The AUV was equally effective or better detecting reference transmitters in shallow water, and significantly better than the boat for transmitters at deeper depths. Similar results were observed for the tagged animals. Crabs at moderate depths were recorded by both tracking methods, while only the AUV detected fish at depths exceeding 500 m. The AUV periodically had difficulty navigating and maintaining course due to the strong currents and extreme depths in the area. AUVs with greater cruising speeds, increased operating depths, and improved navigation would enhance AUV performance in marine environments.

Acoustic telemetry allows detailed observations of the movement behaviour of many species and as tags get smaller, smaller organisms may be tagged. The number of studies using acoustic telemetry to evaluate marine invertebrate movement is growing, but novel attachment methods include unknowns about the effects of tagging procedures on individual survival and behaviour. This study compared methods of tag attachment on green sea urchins (Strongylocentrotus droebachiensis) to determine the feasibility of using acoustic transmitters to track echinoid movement. Four tagging methods were compared in the lab and tag retention, urchin condition, and survival analysed. Two tagging methods (Dyneema® fishing line and T-bar tags) were evaluated in the field using an existing acoustic telemetry array. Urchins were tagged and the study area revisited one week and 2 months post-release by scuba divers to estimate movement and tag retention. The best methods in the lab, with high tag retention, survival, and minimal effects on urchin condition, were fishing line methods. T-bar tags, although showing high tag retention, caused significant mortality and had deleterious long-term effects on urchin condition and behaviour. After 2 months in the field, as in the lab, fishing line was a more effective tagging method. Urchins tagged with fishing line showed increased estimates of space occupancy compared to T-bar-tagged urchins and a single fishing-line tagged individual was found by divers in good health after 80 days. Combined, these laboratory and field results demonstrate the feasibility of using acoustic telemetry to observe urchin movement. Results strongly suggest that surgical attachment methods that minimize injuries at the attachment site should be prioritized for echinoid tagging studies. Together, lab and field tests indicate that acoustic telemetry is a promising method to examine marine echinoid movement over ecologically relevant spatial and temporal scales. The data available includes the laboratory data (tag retention, survival, diameter, wet weight, gonad weight and condition/righting time) and the field data (metadata and acoustic telemetry detections for tagged individuals, results of diver searches and 2-day estimates of movement measured in the field). Data from the laboratory experiment and diver observations in the field have been verified and undergone a control for quality. Acoustic telemetry detections are raw detection files (unfiltered); see the published article for a description of how the data were treated for analyses (https://doi.org/10.1186/s40317-022-00309-8).

This TEAMER RFTS 1 (Request for Technical Support) project supported the flume tank testing of a long range, high endurance unmanned underwater vehicle (UUV) to monitor maritime space. Today, battery-powered remotely operated vehicles (ROVs) lack the duration to make persistent, wide-area data collection possible.The proposed solution, an Electrically Engaged UnduLation (EEL) drone, can sustain missions for longer duration through hydrodynamic energy harvesting. Power is provisioned via the piezoelectric effect, a material-led phenomenon that converts applied stress into electricity. The EEL subsystems include power, propulsion, navigation, ballast, telemetry, and instrumentation. By mimicking the gait of aquatic eels, EEL can counter currents during maneuvering and level-flight. The identified opportunity is in the future capability of extreme endurance UUVs in swarms. The specific goal for the EEL development is to expand the spatio-temporal coverage of the existing ocean observation mission by overcoming significant challenges of autonomous robotics. Some of the challenges presented include novel compliant mechanism for robust actuation, bio-inspired design to emulate efficient locomotion, smart material-based energy harvesting for sustained power, and swarming architecture through enabled autonomy.

In this study, passive acoustic monitoring was conducted at Lock No. 19 near Keokuk, Iowa on the Upper Mississippi River between 20 June – 26 August 2019 to coincide with peak navigation use. Sound pressure levels were calculated from .wav files collected with passive SoundTrap hydrophones at six locations in the downstream lock approach. This data set consists of the location and calibration information for the six hydrophones. The data were used to understand the background sound levels in the lock approach to inform the installation and operation of an underwater acoustic deterrent system. Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government.

This repository includes data, object detection models, and processing scripts necessary to evaluate the accuracy of the object detection models created for the underwater target detection software demonstration on the RivGen turbine project and to reproduce the performance metrics (precision, recall, mAP50, mAP50-95) presented in the report. - Contents - The included data consist of "images" and "labels". Images and labels were curated from 2021 and 2024 smolt outmigration periods at the project site in Igiugig, AK. Images are monochrome 8-bit images of objects (smolt, debris, and other) passing through the field of view of the deployed cameras during various operational stages of the RivGen turbine. Labels are text files indicating the class and bounding polygon of each object in an image. The provided labels use the "YOLO" label format, described in detail here: https://docs.ultralytics.com/datasets/detect/. Each image has an associated label with the same time string in its file name (e.g., 2024_05_25_09_01_57.98.jpg and 2024_05_25_09_01_57.98.txt). Time strings have the format %yyyy_%mm_%dd_%HH_%MM_%SS.%3f. The 2021 and 2024 test datasets are included. These data were used to evaluate the accuracy of models version 1 (V1), V2, and V3, as described in the report. These data are organized into test directories found in the 2021 and 2024 directories, e.g., /data/2021/test/. The "train" and "val" directories are also present as the presence of these directories is necessary for the included script to run successfully, though the associated data is not included. The model weights files are included for models V1, V2, and V3 in the models directory, e.g., /models/v1_model_train_2021_val_2021_test_2021.pt. Finally, the python script "test_models.py" is included, which loads each model and tests it against the associated test dataset. The resulting accuracy metrics are saved to figures in a ./runs/detect/ directory, which will be created when the script is run on the user's machine. Instructions for installing and using the python script are included in the README. - Requirements - All instructions assume the user is using a computer using Ubuntu Linux 20.04+ with Python3.8+. Operation on other operating systems may require some modification to these instructions. Models will run on your computer's CUDA-capable NVIDIA GPU if one is available. The README.md provides instruction for installing the requirements from the requirements.py file. The included data was revised/updated to reflect the post-access report for the project. Resource titles and descriptions were updated to reflect the most up-to-date resources. The file names were updated by adding a "_Ver1" to the end of the outdated file and a "_Ver2" to the end of the revised file.

The Fish Detection AI project aims to improve the efficiency of fish monitoring around marine energy facilities to comply with regulatory requirements. Despite advancements in computer vision, there is limited focus on sonar images, identifying small fish with unlabeled data, and methods for underwater fish monitoring for marine energy. A Faster R-CNN (Region-based Convolutional Neural Network) was developed using sonar images from Alaska Fish and Games to identify, track, and count fish in underwater environments. Supervised methods were used with Faster R-CNN to detect fish based on training using labeled data of fish. Customized filters were specifically applied to detect and count small fish when labeled datasets were unavailable. Unsupervised Domain Adaptation techniques were implemented to enable trained models to be applied to different unseen datasets, reducing the need for labeling datasets and training new models for various locations. Additionally, elastic shape analysis (ESA), hyper-image analysis, and various image preprocessing methods were explored to enhance fish detection. In this research we achieved: 1. Faster R-CNN for Sonar images - Applied Faster R-CNN reached > 0.85 average precision (AP) for large fish detection, providing robust results for higher-quality sonar images. - Integrated Norfair tracking to reduce double-counting of fish across video frames, enabling more accurate population estimates. 2. Small Fish Identification - Established customized filtering methods for small, often unlabeled fish in noisy acoustic images. This submission of data includes several sub-directories: - FryCounting: contains information on how to count small fish (i.e., fry) in the sonar image data - SG_aldi_addons: contains additions to the ALDI code (SG = Steven Gutstein, primary author) such as the trained models used in this experiment, which should match the models achieved when the training instructions are followed, and code for how to make the sonar images into movies - Summaries_Dir: contains information on how to set up the foundation to perform these experiments, such as installing all required packages and versions, and creating the PyTorch and ALDI environments These experiments boil down to a 2-part structure as described in the uploaded readme file: Part I: Installing and Using ALDI & Norfair Code - This is used for tracking and counting fish, and is a replication of the article that is linked, namely the Align and Distill (Aldi) work done by Justin Kay and others - This part relates to the Summaries_Dir subfolder, and the SG_aldi_addons sub-folder Part II: Installing and Using Fry Code - This is used to track and count smaller fish (aka fry) - This relates to the FryCounting sub-directory Also included here are links to the downloadable sonar data and the article that was replicated in this study.

New York Bight SW Slocum glider. Woods Hole Oceanographic Institution (WHOI) data from a local source.