We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Adaptable microplastic classification using similarity learning on µFTIR spectra collected from µFTIR focal plane array imaging
AI summary Read the abstract
Researchers trained a one-dimensional convolutional neural network via similarity learning on µFTIR spectra from 45 manufactured microplastic samples across 11 polymer compositions, achieving an F1-score of 0.973 under pristine conditions and 0.905 on spectra with high exogenous background contamination. The similarity learning approach outperformed cross-entropy training and classical machine learning algorithms, and enabled detection of polymer classes not present in the training set.
Deep learning on micro-Fourier transform infrared (µFTIR) spectra has the potential to provide a reliable, automated approach to classify and identify microplastics. However, deep learning models often come with certain limitations, including exhaustive dataset requirements, overfitting, and the need to retrain when new classes are introduced or new data are substantially different from the training set. This work explores a similarity learning approach to training deep learning models to address these issues for microplastic classification. A one-dimensional convolutional neural network (CNN) was trained by similarity learning on a dataset of µFTIR spectra acquired from 45 manufactured microplastic samples of 11 plastic compositions and compared with cross-entropy training of the same CNN architecture as well as classical machine learning algorithms. The CNN trained by similarity learning consistently yielded the highest accuracies (up to a 0.973 F1-score) across the multiple classes of microplastics. Notably, despite only training on microplastic spectra collected under pristine conditions, the CNN trained via similarity learning maintained the highest accuracy (up to a 0.905 F1-score) on a "noisy" dataset consisting of microplastics spiked onto filters with high amounts of exogenous background material. Furthermore, similarity learning combined with support-vector classifiers also allowed for the detection and separation of microplastic polymer-composition classes not contained in the training set. Overall, this approach is able to achieve high accuracy in microplastic classification despite challenges posed by the diversity of microplastic polymer compositions, limited time and resources for dataset preparation, and high amounts of background noise that are common in FTIR spectra collected from real-world microplastic samples.
More Papers Like This
Development of a machine‐learning model for microplastic analysis in an FT‐IR microscopy image
AI summary Read the abstract
Researchers developed a machine-learning model using a 1D convolutional neural network to classify FT-IR microscopy spectra of microplastics into 16 polymer types. The model addresses inaccuracies caused by secondary materials on real environmental samples, improving the speed and reliability of automated microplastic identification.
Spectral Classification of Large-Scale Blended (Micro)Plastics Using FT-IR Raw Spectra and Image-Based Machine Learning
AI summary Read the abstract
Researchers developed and compared four machine learning classifiers for identifying microplastic types from Fourier transform infrared spectroscopy data using large-scale blended plastic datasets. The study found that a 1D convolutional neural network achieved the best overall accuracy at over 97%, outperforming decision tree and random forest models, offering a scalable alternative to traditional library-search methods for microplastic identification.
Leveraging deep learning for automatic recognition of microplastics (MPs) via focal plane array (FPA) micro-FT-IR imaging
AI summary Read the abstract
Researchers developed PlasticNet, a deep learning neural network for identifying microplastics in environmental samples using infrared imaging, achieving over 95% accuracy across 11 common plastic types. The study demonstrates that this approach overcomes challenges posed by surface modifications and additives that make conventional spectral classification difficult.
A Comparative Study of Machine Learning and Deep Learning Models for Microplastic Classification using FTIR Spectra
AI summary Read the abstract
Researchers compared machine learning and deep learning models for classifying microplastics using FTIR spectra, evaluating multiple algorithmic approaches against standardised spectral datasets. The study assessed classification accuracy and computational efficiency, identifying which model architectures best discriminate between polymer types in environmental microplastic samples.
Computer-Assisted Analysis of Microplastics in Environmental Samples Based on μFTIR Imaging in Combination with Machine Learning
AI summary Read the abstract
Researchers developed machine learning approaches for automated microplastic identification in environmental samples from micro-FTIR imaging data, demonstrating improved accuracy and speed compared to traditional spectral library search methods for scalable analysis.
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.