Geology topics

Jesse Eickholt

Publications and source records attributed to Jesse Eickholt.

5 recordsLinked to original sources

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↗

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↗

USGS2018

An underwater observation dataset for fish classification and fishery assessment

Using Dual-Frequency Identification Sonar (DIDSON), fishery acoustic observation data was collected from the Ocqueoc River, a tributary of Lake Huron in northern Michigan, USA. Data were collected March through July 2013 and 2016 and included the identification, via technology or expert analysis, of eight fish species as they passed through the DIDSON’s field of view. A set of short DIDSON clips containing identified fish was curated. Additionally, two other datasets were created that include visualizations of the acoustic data and longer DIDSON clips. These datasets could complement future research characterizing the abundance and behavior of valued fishes such as walleye ( Sander vitreus ) or white sucker ( Catostomus commersonii ) or invasive fishes such as sea lamprey ( Petromyzon marinus ) or European carp ( Cyprinus carpio ). Given the abundance of DIDSON data and the fact that a portion of it is labeled, these data could aid in the creation of machine learning tools from DIDSON data, particularly for invasive sea lamprey which are amply represented and a destructive invader of the Laurentian Great Lakes.

Scientific Data↗

USGS2018

A distributed pipeline for DIDSON data processing

Technological advances in the field of ecology allow data on ecological systems to be collected at high resolution, both temporally and spatially. Devices such as Dual-frequency Identification Sonar (DIDSON) can be deployed in aquatic environments for extended periods and easily generate several terabytes of underwater surveillance data which may need to be processed multiple times. Due to the large amount of data generated and need for flexibility in processing, a distributed pipeline was constructed for DIDSON data making use of the Hadoop ecosystem. The pipeline is capable of ingesting raw DIDSON data, transforming the acoustic data to images, filtering the images, detecting and extracting motion, and generating feature data for machine learning and classification. All of the tasks in the pipeline can be run in parallel and the framework allows for custom processing. Applications of the pipeline include monitoring migration times, determining the presence of a particular species, estimating population size and other fishery management tasks.

Conference Paper↗