We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Direct identification of microplastics in marine sediments by hyperspectral imaging and machine learning
AI summary Read the abstract
Scientists tested a faster way to detect tiny plastic bits (microplastics) hiding in ocean floor sediment, using a special camera and computer smarts instead of slow, traditional lab methods. They found thousands of plastic particles per kilogram of seafloor mud near Taranto, Italy, with the smallest, most broken-down plastic bits piling up most in fine sediments — a concerning sign since smaller plastic fragments are easier for marine life (and eventually us, through seafood) to absorb. This quicker detection method could help researchers track plastic pollution more efficiently, which is a key step toward understanding
This study presents an innovative approach for the direct identification of microplastics (MPs) in marine sediments. Hyperspectral imaging (HSI) in the short-wave infrared range (SWIR: 1000–2500 nm) with machine learning techniques was applied to marine sediments from the Mar Piccolo basin (Taranto, Italy). Samples were collected from eight different sites across both bays of Mar Piccolo using a grab sampler and then sieved. Nine granulometric classes (from -4 mm to +180 μm) were analyzed by HSI using two instrumental setups based on particle size. Reference polymer particles were acquired and used to train classification models. Preprocessing algorithms were applied to enhance spectral differences between material classes. Principal Component Analysis (PCA) was employed to explore spectral variability and reduce data dimensionality. Two supervised classification models were developed: Hierarchical Partial Least Squares-Discriminant Analysis (Hi-PLS-DA) and Error Correcting Output Codes-Support Vector Machine (ECOC-SVM). Both models successfully identified MPs of different polymers within sediment samples. Classification results were validated using Attenuated Total Reflectance Fourier Transform Infrared (ATR-FTIR) spectroscopy. MP concentrations ranged from 58 to 17,930 MPs/kg, with higher levels in finer sediment fractions and hotspot identified in MP_01 site, collected in proximity to the river mouth. Polypropylene (PP) was the most abundant polymer, followed by polyethylene (PE), polystyrene (PS), polyethylene terephthalate (PET) and polyvinyl chloride (PVC). PET was detected exclusively in the finest size classes, suggesting advanced fragmentation. The HSI-based strategy demonstrates high potential as a rapid tool for MP detection in complex environmental matrices, significantly reducing sample preparation and analysis time.
More Papers Like This
Simple and rapid detection of microplastics in seawater using hyperspectral imaging technology
AI summary Read the abstract
Researchers developed a hyperspectral imaging technique for rapid detection and identification of microplastics in seawater, demonstrating it could analyze multiple particles simultaneously and significantly reduce the time burden compared to traditional individual-particle identification protocols.
Issues with the detection and classification of microplastics in marine sediments with chemical imaging and machine learning
AI summary Read the abstract
Researchers tested near-infrared hyperspectral imaging combined with four common machine learning algorithms to detect microplastics directly in marine sediment samples, finding that the method produced a large proportion of false positives and false negatives even in simple test conditions. The results raise serious concerns about the reliability of this widely used approach for environmental microplastic monitoring.
Hyperspectral imaging and self-organizing map approach for non-destructive monitoring of microplastic contamination in sandy substrates
AI summary Read the abstract
Scientists developed a camera-based scanning technique that can spot and measure tiny plastic fragments, including pieces smaller than 1mm, buried in sand, without destroying the samples. This matters because microplastics on beaches and in soil are notoriously hard to detect and measure accurately, and better detection tools are a key first step toward understanding how much of this pollution surrounds us and eventually ends up in our bodies and food chain.
A multi-level preprocessing and modelling framework for spectral imaging of microplastics
AI summary Read the abstract
Scientists have developed a smarter, faster way to identify tiny plastic particles (microplastics) using a technique called spectral imaging, which essentially takes a chemical "fingerprint" of samples. Their new method cleans up messy data and groups similar particles together before matching them to known plastics, making the process both faster and more accurate at telling different plastic types apart. This matters because reliable microplastic detection is a key step toward understanding how much of this plastic pollution we're exposed to in our food, water, and environment, and what it might mean for our health.
Hyperspectral Imaging and Data Analysis for Detecting and Determining Plastic Contamination in Seawater Filtrates
AI summary Read the abstract
Researchers tested whether hyperspectral imaging combined with multivariate data analysis could detect and identify plastic particles on filters from seawater samples, finding the method could locate plastic contamination and distinguish polymer types. This approach could offer a faster and more automated alternative to manual microscopy for environmental microplastic monitoring.
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.