We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Microplastic
AI summary Read the abstract
This entry describes a FTIR hyperspectral image dataset of an environmental plankton sample spiked with microplastics ranging from 10 to 200 micrometers, covering common polymer types including polyethylene, polypropylene, and polystyrene. The dataset was used to train machine learning classifiers for automated microplastic identification.
This FTIR hyperspectral image shows an environmental plankton sample which has been spiked with microplastics in the size range between 10 and 200 µm. The added particles are one of the following polymer types: polyethylene polypropylene polystyrene poly(methyl methacrylate) polyacrylonitrile This hyperspectral image has been used as a source for training data for the creation of random decision forest classifiers. For a closer description of the dataset and the sample preparation see Hufnagl et al. (2019). If you reuse this dataset please cite Hufnagl, B., Steiner, D., Renner, Löder, M. G. J., Laforsch, C. and Lohninger, H. A Methodology for the Fast Identification and Monitoring of Microplastics in Environmental Samples using Random Decision Forest Classifiers, Analytical Methods, 2019, DOI:10.1039/C9AY00252A
More Papers Like This
Microplastic
AI summary Read the abstract
This FTIR hyperspectral image dataset shows a plankton environmental sample spiked with microplastics of five polymer types (PE, PP, PS, PMMA, PAN) in the 10-200 micrometer size range, used to develop and train random decision forest classifiers for automated microplastic identification. The dataset supports machine learning approaches to faster and more consistent microplastic detection in complex biological samples.
Exploratory analysis of hyperspectral FTIR data obtained from environmental microplastics samples
AI summary Read the abstract
Hyperspectral infrared imaging is an effective method for finding and characterizing microplastics in environmental samples, and this paper explores analytical approaches for extracting useful information from the large datasets it generates. Better analytical tools make it faster and more accurate to identify and classify microplastics in real-world samples.
Random forest microplastic classification using spectral subsamples of FT-IR hyperspectral images
AI summary Read the abstract
A random forest classification model was built using spectral subsamples of FT-IR hyperspectral data to rapidly identify the 11 most common environmental microplastic polymer types. By selecting highly discriminative wavenumbers, the model reduced computational load while maintaining strong classification accuracy.
Developing and testing a workflow to identify microplastics using near infrared hyperspectral imaging
AI summary Read the abstract
Researchers developed a near-infrared hyperspectral imaging workflow with an open spectral database to rapidly identify microplastics by polymer type, achieving over 88% accuracy for polypropylene, polyethylene, PET, and polystyrene particles larger than 500 micrometers.
Development of a rapid detection protocol for microplastics using reflectance-FTIR spectroscopic imaging and multivariate classification
AI summary Read the abstract
Reflectance-FTIR spectroscopy was evaluated as a faster and more automated detection method for microplastics in environmental samples, with results showing strong potential for high-throughput screening. The method could reduce the time and cost of routine microplastic monitoring programs.
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.