We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Qualitative and quantitative analysis of microplastics in chicken based on portable near-infrared spectroscopy and interpretable machine learning.
AI summary Read the abstract
Researchers tested chicken samples mixed with tiny amounts of three plastic types using a portable light-based scanning tool and computer models. The tool could detect which plastic was present and estimate how much, with accuracy ranging from moderate to high depending on the plastic type, suggesting potential for quick on-site testing of poultry products.
Portable near-infrared (NIR) spectroscopy combined with interpretable machine learning was employed for the qualitative and quantitative analysis of polypropylene (PP), polyvinyl chloride (PVC), and polyethylene terephthalate (PET) in chicken. A total of 244 samples were prepared, including pure chicken and PP-, PVC-, and PET-spiked chicken (61 samples per type, mass fractions: 0.01-0.8%). NIR spectra were acquired over 900-1700 nm. After optimal preprocessing and outlier removal via Monte Carlo cross-validation (MCCV), competitive adaptive reweighted sampling (CARS) was selected over the successive projections algorithm (SPA) for characteristic wavelength extraction prior to modeling. For qualitative analysis, a data-driven soft independent modeling of class analogy (DD-SIMCA) model was constructed, achieving sensitivities of 85.71-92.86% and specificities of 82.93-100%. For quantitative analysis, the optimal model varied with microplastic (MP) type: CARS-SVR (support vector regression) for PET (Rp2 = 0.8923, RPD = 3.0468); CARS-ElasticNet for PP (Rp2 = 0.8267, RPD = 2.4022), and CARS-PLS (partial least squares) for PVC (Rp2 = 0.8969, RPD = 3.0397). SHAP-based interpretability analysis was further employed to quantify each wavelength's spectral contribution and identify MP-specific absorption bands. This study innovatively integrates portable NIR spectroscopy with SHAP-based interpretable machine learning for MP detection in chicken and demonstrates the potential of this strategy for rapid on-site screening of MP contamination in poultry products.
More Papers Like This
Qualitative and Quantitative Detection of Microplastics in Chicken Feed Using Portable Near-Infrared Spectroscopy
AI summary Read the abstract
Scientists tested a portable scanning tool that uses infrared light to detect tiny plastic particles hidden in chicken feed, and it correctly identified the type of plastic about 96% of the time. This matters because microplastics in animal feed could end up in the meat and eggs we eat, and this faster, non-destructive testing method could eventually help catch contaminated feed before it enters the food supply, though it still needs more testing in real-world conditions with mixed plastic types.
Rapid detection of microplastics in chicken feed based on near infrared spectroscopy and machine learning algorithm
AI summary Read the abstract
Near-infrared (NIR) spectroscopy combined with machine learning was applied to rapidly detect microplastic contamination in chicken feed, achieving accurate classification of contaminated versus non-contaminated samples. The method offered a fast, non-destructive screening tool for monitoring MP contamination in animal feed supply chains.
Rapid and Nondestructive On-Site Classification Method for Consumer-Grade Plastics Based on Portable NIR Spectrometer and Machine Learning
AI summary Read the abstract
Researchers used a portable near-infrared spectrometer combined with machine learning to rapidly identify and classify seven types of consumer plastic waste on-site without damaging the samples. Faster and cheaper plastic identification tools are important for improving plastic recycling efficiency and ultimately reducing the amount of plastic that ends up as microplastic pollution.
The Prediction of the Concentration of Artificially Added Microplastics in Different Foods and Feed Ingredients Using Near-Infrared Spectroscopy—Instrument Type, Limit of Detection and Quantification
AI summary Read the abstract
Researchers tested whether a light-based scanning tool (near-infrared spectroscopy) could detect tiny plastic pieces mixed into banana, spinach, breadcrumbs, and insect meal at known amounts. Both a portable and a tabletop version of the device predicted plastic levels with reasonable accuracy, with the portable instrument performing slightly better.
Microplastic adulteration in homogenized fish and seafood - a mid-infrared and machine learning proof of concept
AI summary Read the abstract
Researchers used infrared spectroscopy combined with machine learning to detect microplastics added to ground fish and seafood samples. The method successfully identified contamination, offering a rapid tool for food safety testing that could detect microplastic contamination in seafood products.
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.