We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Exploratory data analysis of visual sea surface imagery using machine learning
AI summary Read the abstract
An anomaly detection algorithm based on contrastive learning and supervised machine learning successfully identified floating marine litter, birds, and unusual glare in optical sea surface imagery. Scalable, automated surface monitoring tools are critical for tracking plastic debris distribution and density across the open ocean where manual surveys are impractical.
Introduction Marine litter is an issue affecting all regions of the World Ocean. To address the problem of World Ocean pollution, it is essential first and foremost to develop observation methodologies capable of providing objective assessments of marine litter density and its sources. Methods One of the most accessible yet still objective observation methods is visual imaging of the ocean surface followed by the analysis of the imagery acquired. The goal of our study is to develop a method for analyzing marine surface imagery capable of detecting anomalies, given that some of the anomalies would represent floating marine litter. Results For this purpose, we apply our algorithm based on artificial neural networks trained within the contrastive learning framework, along with a classifier based on supervised machine learning method for analyzing optical imagery of sea surface. Discussion The approach we present in this study is capable of detecting anomalies such as floating marine litter, birds, unusual glare, and other atypical visual phenomena. We explored capabilities of the artificial neural networks we use in this study within two training approaches with subsequent comparison of the results. Within our sampling approach, we propose to utilize the ergodic property of sea wave fields, leading to significant spatial autocorrelation of image elements with a substantial correlation radius.
More Papers Like This
Modern Floating Marine Macrolitter Monitoring Approaches and Methods and Integration of Machine Learning Techniques
AI summary Read the abstract
This review examined modern methods and approaches for detecting floating marine macrolitter, including visual observations, trawling, radar remote sensing, and deep learning techniques. The authors analyzed recent advances in artificial neural networks and machine learning that have significantly improved the accuracy of identifying and classifying marine litter at the sea surface, with key challenges including object diversity and partial submersion.
Deep-Feature-Based Approach to Marine Debris Classification
AI summary Read the abstract
This study applied deep learning to classify marine debris from images, demonstrating that feature-based neural network approaches can effectively distinguish plastic types and other debris categories to support automated ocean monitoring.
A Comparison of Self-Supervised and Supervised Deep Learning Approaches in Floating Marine Litter and Other Types of Sea-Surface Anomalies Detection
AI summary Read the abstract
Comparing supervised (YOLOv11) and self-supervised (MoCo + CatBoost) machine learning on Arctic sea-surface imagery found that self-supervised learning outperformed object detection for identifying visually ambiguous floating marine litter (40% vs. 10% F1-score), while object detection excelled for distinct targets like birds. Automated detection of floating marine debris using self-supervised methods represents a scalable approach for monitoring the distribution and transport of macro-plastic litter that ultimately fragments into microplastics in Arctic waters.
Efficient Classification of Marine Debris using SVM with Noise Removal and Feature Extraction Techniques with Improved Performances
AI summary Read the abstract
This study evaluated different image processing filters for reducing noise in underwater photos of marine debris, then applied support vector machine (SVM) classification to automatically identify debris types. Automated marine debris detection technology is important for scaling up plastic pollution monitoring in ocean environments.
Enhancing marine debris identification with convolutional neural networks
AI summary Read the abstract
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.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.