We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Customizable Machine-Learning Models for Rapid Microplastic Identification Using Raman Microscopy
AI summary Read the abstract
A strategy for building customizable machine learning models for Raman spectroscopy-based microplastic identification was developed using a high-resolution full-window spectral database, enabling generation of random forest, K-nearest neighbor, and neural network classifiers that remain accurate despite equipment variability. The approach addresses a key barrier to developing shared analytical tools across research groups using different instruments.
Raman spectroscopy is commonly used in microplastics identification, but equipment variations yield inconsistent data structures that disrupt the development of communal analytical tools. We report a strategy to overcome the issue using a database of high-resolution, full-window Raman spectra. This approach enables customizable analytical tools to be easily created─a feature we demonstrate by creating machine-learning classification models using open-source random-forest, K-nearest neighbors, and multi-layer perceptron algorithms. These models yield >95% classification accuracy when trained on spectroscopic data with spectroscopic data downgraded to 1, 2, 4, or 8 cm-1 spacings in Raman shift. The accuracy can be maintained even in non-ideal conditions, such as with spectroscopic sampling rates of 1 kHz and when microplastic particles are outside the focal plane of the laser. This approach enables the creation of classification models that are robust and adaptable to varied spectrometer setups and experimental needs.
More Papers Like This
Machine Learning Method for Microplastic Identification Using a Combination of Machine Learning and Raman Spectroscopy
AI summary Read the abstract
Researchers developed a machine learning method for identifying microplastics using a combination of multiple spectroscopic techniques, improving classification accuracy beyond single-method approaches and enabling automated polymer identification.
Rapid identification of microplastic using portable Raman system and extra trees algorithm
AI summary Read the abstract
Researchers developed a portable Raman spectroscopy system combined with a machine learning algorithm to rapidly identify and classify different types of microplastics in the field. Portable real-time identification tools are important for environmental monitoring programs that need to quickly characterize microplastics without sending samples to a laboratory.
Machine Learning of polymer types from the spectral signature of Raman spectroscopy microplastics data
AI summary Read the abstract
Researchers applied machine learning to Raman spectroscopy data to classify microplastic polymer types, finding the approach particularly valuable for identifying environmentally weathered particles that are harder to analyze with standard methods. Machine learning tools could improve the speed and accuracy of microplastic identification in environmental monitoring.
Inter-instrument definition of valid criteria for the automatic identification of microplastics by micro-Raman spectroscopy
AI summary Read the abstract
Researchers developed a standardized methodology for automatically identifying microplastics using micro-Raman spectroscopy across different laboratory instruments. They determined optimal match algorithms and threshold values that achieved a 95% true positive rate with minimal false positives, even when spectra were collected on different spectrometers. The study addresses a key barrier to reliable, reproducible microplastic identification in environmental and health research.
Characterization and identification of microplastics using Raman spectroscopy coupled with multivariate analysis
AI summary Read the abstract
Researchers developed a new method using Raman spectroscopy combined with machine learning to identify and classify seven types of microplastics with over 98% accuracy for most polymer types. The approach was also able to correctly identify real-world microplastic samples from snack boxes, water bottles, juice bottles, and medicine vials. This technique could make microplastic detection faster and more reliable compared to manual analysis methods.
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.