We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Deep-MAP: A user-friendly platform for deep learning-based microplastics classification
AI summary Read the abstract
Deep-MAP, a deep learning platform built on YOLOv8 segmentation, achieved a Mask mAP@0.50 of 0.873 for automated microplastic classification from microscope images, outperforming two-stage and preprocessing-based models. By making automated MP analysis accessible via Google Colaboratory, this tool addresses a major bottleneck in large-scale microplastic monitoring and research.
Abstract In recent years, microplastic (MPs) pollution in rivers and oceans has become a serious environmental problem, raising concerns about its impact on ecosystems and human health. While the identification and quantification of MPs using microscope images are essential for understanding the extent of this pollution, manual analysis is time-consuming, labor-intensive, and prone to analyst-dependent bias. To address this challenge, this study aimed to establish a high-precision automated analysis method for MPs images using deep learning. Specifically, we systematically compared and evaluated three different models: 1) an end-to-end segmentation model (YOLOv8m-seg), 2) a two-stage model for detection and classification, and 3) a model combined with classical image pre-processing. The results showed that the end-to-end segmentation model without pre-processing achieved the highest performance, with a Mask mAP@0.50–0.95 of 0.555 and a Mask mAP@0.50 of 0.873. It was also found that aggressive background removal during pre-processing degraded performance due to the loss of boundary information essential for model recognition. Based on these findings, we developed Deep-MAP, a user-friendly analysis tool built on the best-performing model and implemented on Google Colaboratory. With this tool, users can upload microscope images and automatically obtain aggregated outputs on MPs count, types, areas, and colors. Deep-MAP helps bridge the gap between developers and end-users by eliminating the need for specialized knowledge.
More Papers Like This
YOLOv8-Based Microplastic Detection and Quantification in River Water Microscopic Images
AI summary Read the abstract
Researchers trained a YOLOv8 deep learning model on 300 microscopic images of river water from three Indonesian sites, achieving 0.786 precision and 0.731 mAP@0.5 for detecting microplastics, with higher image resolution improving accuracy and FTIR laboratory validation confirming compositional agreement with model detections.
A Deep Learning Approach for Microplastic Segmentation in Microscopic Images
AI summary Read the abstract
Researchers developed a deep learning model for automated segmentation and classification of microplastics in microscopic images, identifying five distinct categories including fibers, fragments, spheres, foam, and film. The model achieved high accuracy while maintaining low computational requirements, making it suitable for high-throughput deployment in environmental monitoring. The study offers a tool that could help overcome the measurement bottleneck in microplastic characterization for toxicological and risk assessment studies.
Deep Learning-Based Image Recognition System for Automated Microplastic Detection and Water Pollution Monitoring
AI summary Read the abstract
This study developed a deep learning image recognition system to automate the detection and classification of microplastics from microscopy images of water samples. The system achieved high accuracy across particle types and sizes, offering a scalable and less labor-intensive alternative to manual microscopy for large-scale water pollution monitoring.
WaveFilter: Advanced Imaging for Marine Microplastic Monitoring
AI summary Read the abstract
This paper describes WaveFilter, a deep-learning system based on the YOLOv5 model trained to automatically detect microplastics in images of aquatic environments, achieving about 80% precision in identifying plastic particles even against complex backgrounds. The model is compact enough for real-time deployment, offering a faster and more scalable alternative to tedious manual counting methods. Automated detection tools like this could make large-scale marine microplastic monitoring more practical and consistent.
A Fully Automated YOLO-SAM Framework for High-Precision Microplastic Analysis in Environmental Sample
AI summary Read the abstract
Researchers built an automated computer program that combines two AI tools to detect and outline microplastic particles in microscope images. Tested on 5,653 images, the fully automatic system matched particle shapes accurately, and performed even better when given some manual guidance, outperforming an existing method by more than 22%.
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.