We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Development of a YOLO-guided automated (microplastic) particle analysis workflow.
AI summary Read the abstract
Scientists have developed an AI-powered tool that automatically finds and analyzes microplastic particles in water and other samples, making detection faster and more accurate than older methods. This matters because tracking microplastics, tiny plastic bits increasingly found in our water, food, and even our bodies, is a crucial first step in understanding their potential health risks, and faster, more reliable monitoring tools help researchers keep better tabs on our exposure to this pollutant.
Microplastics (MPs) are an emerging pollutant of global concern, creating an urgent need for rapid and accurate monitoring workflows. Deep learning-based computer vision has demonstrated strong performance in finding particles in microscopy images, but its use as a front-end module for automated IR/Raman microscope-based MP analysis remains insufficiently developed, particularly in workflows that convert image-level particle detection results into microscope-executable operations for particle morphological characterization and spectral acquisition planning. Here, we aim to address this gap. First, reference MPs were deposited on Anodisc filters and glass slides, from which 626 bright-field micrographs containing 7010 particles were collected. The dataset was randomly split into training, validation, and test sets in a 7 : 2 : 1 ratio, and an Ultralytics YOLO11 instance segmentation model was developed. At an intersection-over-union (IoU) threshold of 0.7, testing achieved precision, recall, and F1 scores of 0.86, 0.93, and 0.89, respectively, outperforming two benchmark methods: a threshold-based method (F1 = 0.25) and Mask R-CNN (F1 = 0.84). On another test set prepared from tap water (with a relatively clean background), the model achieved precision, recall, and F1 scores of 0.78, 0.90, and 0.83 at IoU = 0.7. However, particle detection performance decreased with dirtier image backgrounds, as shown by testing on the sample prepared from commercial salt. We addressed key technical challenges required for end-to-end automation, including per-field autofocus, recovering true microscope coordinates from YOLO style outputs, converting detections into particle descriptors for downstream characterization, and programmatic microscope control for image collection and spectrum acquisition planning. Full implementation, code, and well annotated data are released openly, enabling adoption and extension of this workflow for broader MP monitoring applications.
More Papers Like This
Rapid and Accurate Quantification of Microplastics in Surface Water using Improved YOLO Model
AI summary Read the abstract
Scientists developed a faster, more accurate AI tool to detect and count tiny plastic particles (microplastics) in water samples. This matters because microplastics are showing up everywhere, including our drinking water, and better detection tools help researchers track this pollution more efficiently, which is a key step toward understanding its health risks and creating solutions to reduce our exposure.
Real-time intelligent monitoring of microplastics under microscopy: An improved data strategy and YOLOv11-based approach
AI summary Read the abstract
Scientists have built a smart AI system that can spot tiny plastic particles under a microscope automatically, instead of relying on tired human eyes to find them one by one. This matters because faster, more reliable microplastic detection could help researchers better track how much plastic pollution is around us, including in our food, water, and eventually our bodies, which is a key step toward understanding potential health risks. Note: this study focuses on improving the detection technology itself, not on new findings about health effects.
Detecting Microplastics in Aquatic Bodies Using Object Detection Model
AI summary Read the abstract
Microplastics—tiny plastic particles that pollute water and can work their way up the food chain into the fish and seafood we eat—are hard to track using traditional methods. This research shows that AI-powered image recognition tools (specifically YOLO models, a type of "smart camera" software) can automatically spot and count microplastics in water much faster than manual methods, with a newer version performing better than its predecessor. Faster, more accurate detection means scientists and regulators could monitor plastic pollution more effectively, which is an important step toward understanding and reducing our exposure to these contaminants.
Microplastic Spot Analyzer: Automated Image-Based Detection and Quantification of Microplastic Particles
AI summary Read the abstract
Scientists have created a new software tool that automatically spots and measures microplastic particles in microscope images, replacing the slow, error-prone process of counting them by hand. This matters because faster, more consistent microplastic detection makes it easier for researchers to study how much of this material is in our water, food, and environment, a key step toward understanding its potential health risks. Note that this paper introduces the tool itself rather than new findings about microplastics' health effects.
Deep Learning-Based Prediction and Classification of Microplastics in Water Samples
AI summary Read the abstract
Researchers built an AI tool that can automatically spot and identify tiny plastic particles in drinking water samples, correctly catching them about 92% of the time — much faster than manual lab methods. This matters because it could help water utilities quickly find contamination hotspots and monitor water quality in real time, making it easier to protect drinking water from microplastic pollution before it reaches your tap.
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.