We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Papers
61,005 resultsShowing papers similar to Estimating precision and accuracy of automated video post-processing: A step towards implementation of AI/ML for optics-based fish sampling
ClearAssessment of sustainable baits for passive fishing gears through automatic fish behavior recognition
Researchers developed biodegradable cockle-based fishing baits and used machine learning to automatically track and classify fish behavior from underwater video, finding that while the bio-baits attracted fewer fish than natural bait initially, they sustained fish interest longer. This work offers a lower-waste alternative to conventional fishing bait while advancing automated tools for monitoring fish behavior.
Data Study Group Final Report: Centre for Environment, Fisheries and Aquaculture Science
Machine learning was applied to the challenge of automatically classifying plankton species from underwater images collected by fisheries monitoring systems. The AI classifier could identify dozens of plankton categories with high accuracy, reducing the need for time-consuming manual identification. Automated plankton monitoring improves understanding of marine food web health and ecosystem responses to environmental change.
A Machine Learning Approach To Microplastic Detection And Quantification In Aquatic Environments
This study developed a machine learning approach for detecting and quantifying microplastics in aquatic environments, demonstrating that automated image analysis can improve throughput and accuracy compared to manual microscopic counting for environmental monitoring applications.
Improving YOLOv11 for marine water quality monitoring and pollution source identification
Researchers improved the YOLOv11 computer vision model to better detect and identify marine pollution sources, including oil spills, debris, and turbid water, in complex underwater environments. The enhanced model achieved higher detection accuracy and faster processing speeds compared to the standard version. The study demonstrates that advanced AI-based monitoring tools can meaningfully improve our ability to track and respond to marine pollution in real time.
Aquatic Trash Detection and Classification: a Machine Learning and Deep Learning Perspective
This review examines machine learning and deep learning approaches for detecting and classifying aquatic trash in waterways, evaluating how computer vision algorithms trained on underwater and surface imagery can automate pollution monitoring for faster, more scalable ocean cleanup.
Detection of microplastics in fish using computed tomography and deep learning
CT scanning combined with deep learning neural networks enabled non-destructive, automated detection and localization of microplastics in fish with high accuracy, overcoming the contamination risk and time-consuming nature of conventional dissection-based methods.
Utilizing Artificial Intelligence (AI) for the Identification and Management of Marine Protected Areas (MPAs): A Review
This review examined how artificial intelligence and automation can improve the identification and management of marine protected areas, including advances in data gathering, monitoring, and analysis for more effective marine conservation.
Automatic Detection of Microplastics in the Aqueous Environment
Researchers developed a deep-learning system for real-time detection and counting of microplastics in freshwater, achieving high accuracy for particles 1 mm and larger.
Battle Models: Inception ResNet vs. Extreme Inception for Marine Fish Object Detection
Not relevant to microplastics — this paper compares two deep learning models (Inception ResNet and Xception) for detecting and classifying marine fish species in underwater images, with no connection to plastic pollution.
SMACC: A System for Microplastics Automatic Counting and Classification
Researchers developed an automated computer vision system (SMACC) that uses image analysis to count and classify plastic particles in beach samples, demonstrating that machine learning can substantially reduce the time and effort required for large-scale beach microplastic monitoring.
AI-Driven Framework Development for Predictive Classification of Microplastic Concentration of Aquatic Systems in the United States
Researchers compared four machine learning models—logistic regression, random forest, support vector machine, and a neural network—for predicting microplastic density in US coastal waters across three regions. The support vector machine performed best with 93.94% average accuracy, demonstrating the potential of AI-driven tools for microplastic monitoring.
High-resolution, non-invasive animal tracking and reconstruction of local environment in aquatic ecosystems
Researchers developed an open-source, affordable framework using computer vision and tracking algorithms to monitor animal behavior in aquatic environments at high resolution. The tool enables detailed behavioral studies across a wide range of species without requiring expensive commercial equipment.
Automatic Counting and Classification of Microplastic Particles
Researchers developed an automatic system for counting and classifying microplastic particles in marine samples, applying image analysis techniques to address the growing problem of plastic debris entering the food chain via marine species ingestion.
Plankton classification with high-throughput submersible holographic microscopy and transfer learning
Researchers used underwater holographic microscopes and transfer learning — an AI technique that applies knowledge from one task to another — to automatically classify diverse plankton species from images, including rare forms. The system shows promise for large-scale, automated ocean monitoring without needing constant human analysis.
AI – Driven Marine Debris Detection for Ocean Conservation
Researchers developed an AI-driven marine debris detection system using the YOLOv8 deep learning model trained to identify plastic waste in challenging underwater conditions including low visibility and complex backgrounds. The system aims to provide scalable, automated monitoring to support ocean conservation and guide debris removal efforts.
Robust and Fair Undersea Target Detection with Automated Underwater Vehicles for Biodiversity Data Collection
Researchers developed a robust and fair underwater target detection system for automated underwater vehicles (AUVs) to support marine biodiversity data collection, addressing unique challenges of subsea imaging compared to above-ground remote sensing.
Predicting Aquaculture Water Quality Using Machine Learning Approaches
Researchers compared four machine learning approaches for predicting water quality parameters in industrial aquaculture systems, finding that back propagation and radial basis function neural networks outperformed support vector machine models for most parameters. The models achieved sufficient accuracy to support real-time management decisions without continuous in-situ monitoring.
From microplastics to pixels: Testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification.
Researchers tested the robustness of two automated machine learning approaches combined with Nile red fluorescent staining for marine microplastic identification, specifically evaluating performance on environmentally weathered particles that challenge the reliability of methods developed using pristine laboratory plastics.
Detection and identification of environmental faunal proxies in digital images and video footage from northern Norwegian fjords and coastal waters using deep learning object detection algorithms
Researchers developed deep learning object detection algorithms to automate the detection and identification of environmental faunal proxies in digital images and video footage from Norwegian fjords and coastal waters, as part of the ICT+ ocean surveying project at UiT The Arctic University of Norway. The preliminary work aimed to automate identification of objects ranging from foraminifera and microplastics at the micrometre scale to boulders and shipwrecks at the metre scale, replacing labour-intensive manual processing.
Deep-Sea Debris Identification Using Deep Convolutional Neural Networks
Researchers developed a deep convolutional neural network classifier to identify and distinguish deep-sea debris from seafloor imagery, demonstrating that automated AI-based detection can support submersible clean-up operations targeting marine debris in deep-sea environments.
Automatic Identification and Classification of Marine Microplastic Pollution Based on Deep Learning and Spectral Imaging Technology
Researchers developed an AI system combining deep learning with multispectral imaging to automatically identify and classify marine microplastics, using a feature-selection method called ReliefF to reduce noise in complex ocean samples. The approach achieved high accuracy and offers a scalable solution for large-scale ocean microplastic monitoring that outperforms traditional manual inspection.
A new approach to classifying polymer type of microplastics based on Faster-RCNN-FPN and spectroscopic imagery under ultraviolet light
Scientists developed an AI-based method using UV light photography to automatically identify and classify different types of microplastics, achieving 86-88% accuracy. This approach is faster and cheaper than traditional lab analysis methods that require expensive equipment. Better detection tools like this are essential for understanding how widespread microplastic contamination really is in coastal environments where people live and eat seafood.
Enhancing marine debris identification with convolutional neural networks
A deep learning model was developed to identify and classify marine debris components captured by underwater remotely operated vehicle imagery, addressing the challenge of widely distributed ocean waste including microplastics. The convolutional neural network demonstrated improved accuracy for debris detection and classification compared to conventional image analysis methods.
A Comprehensive Review of Deep Learning Algorithms for Underwater Trash Detection: Advancements, Challenges, and Future Directions
This review examines deep learning approaches for automated underwater trash detection, covering CNN-based architectures including YOLO and Faster R-CNN, and finds they outperform traditional sonar and manual inspection methods while identifying key challenges such as low visibility and limited labeled datasets.