We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Identification of marine microplastics by a combined method of principal component analysis and random forest for fluorescence spectrum processing
AI summary Read the abstract
Researchers developed a combined principal component analysis and random forest method to identify microplastics from overlapping fluorescence spectra. The technique achieved 99.7% accuracy for component identification and a correlation coefficient exceeding 0.99 for predicting microplastic concentrations. The model, initially trained on commercial plastic samples, was also successfully applied to identify real marine microplastics.
The severely overlapped laser-induced fluorescence spectra between different microplastics pose significant challenges on fluorescence-based particle identification and quantification. To address this problem, this paper proposes a combined method of principal component analysis (PCA) and random forest (RF) for fluorescence spectrum processing. The key idea is to identify the overlapped PCA scores of the first three principal components of fluorescence spectra by the random forest method. Both pure and mixed microplastics samples were used to verify the accuracy of this method. It was demonstrated that both the compositions of the samples and mass concentration of one specific microplastics can be accurately identified. The accuracy for component identification reaches 99.7 % and the correlation coefficient between the predicted and actual concentration exceeds 0.99. Furthermore, the PCA-RF model established with commercial plastic samples was also applied for real marine microplastics identification with good identification results obtained.
More Papers Like This
Identification of marine microplastics based on laser-induced fluorescence and principal component analysis
AI summary Read the abstract
Researchers developed a method to identify different types of marine microplastics using laser-induced fluorescence combined with principal component analysis. The technique successfully distinguished nine types of microplastics based on their fluorescence signatures and could detect microplastic concentrations as low as 0.03% by mass. The study suggests this approach could be a practical tool for rapid microplastic identification in marine environments.
PCA combined with SVM assisted fluorescence spectroscopy for classification of microplastics
AI summary Read the abstract
Researchers combined principal component analysis (PCA) and support vector machine (SVM) classifiers with fluorescence spectroscopy to classify six types of microplastics, achieving 100% classification accuracy on a test set of 2,400 spectral samples while substantially reducing computation time compared to the baseline SVM model. The study demonstrates that PCA dimensionality reduction can maintain classification accuracy while improving the speed of machine learning-based microplastic identification.
Rapid identification of marine microplastics by laser-induced fluorescence technique based on PCA combined with SVM and KNN algorithm
AI summary Read the abstract
Researchers developed a laser-based fluorescence method combined with machine learning algorithms to rapidly identify different types of marine microplastics. The system achieved classification accuracy above 97 percent for four common plastic types at various concentrations. The technique offers a fast, non-destructive alternative to traditional laboratory methods for monitoring microplastic pollution in ocean environments.
Machine learning based workflow for (micro)plastic spectral reconstruction and classification
AI summary Read the abstract
A machine learning pipeline combining two spectral reconstruction models with four classification algorithms can identify microplastic polymer types from spectral data with up to 98% accuracy on processed spectra. Applied to real environmental samples, the best model achieved 71% top-one accuracy and over 90% top-three accuracy. Automated, high-accuracy microplastic identification tools are critical for scaling up environmental monitoring and making large-scale surveys practical.
A methodology for the fast identification and monitoring of microplastics in environmental samples using random decision forest classifiers
AI summary Read the abstract
Researchers developed a methodology using random decision forest classifiers for the fast identification and monitoring of microplastics in environmental samples. The approach provides a machine learning-based tool to accelerate microplastic detection and reduce the analytical burden of characterising particles across diverse environmental matrices.
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.