The identification of microplastics based on vibrational spectroscopy data – A critical review of data analysis routines

Weißer, Jana; Pohl, Teresa; Heinzinger, Michael; Ivleva, Natalia P.; Hofmann, Thomas; Glas, Karl

doi:10.1016/j.trac.2022.116535

Cited by 24 publications

(13 citation statements)

References 101 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As described in Weisser et al [11], unsupervised machine learning techniques such as principal component analysis (PCA) seem promising to extract potential MP particles from a hyperspectral image. In brief, PCA and other techniques, such as intensity filtering, allow detection of patterns in a dataset, such as background and potential MP spectra.…”

Section: First Hypothesis: Masking Of Background Pixels Increases The...mentioning

confidence: 99%

“…This is where boon and bane of the technique lies: all spectra gathered need to be analyzed. Different data analysis routines (DARs) have been proposed, ranging from traditional database matching [2][3][4][5] to unsupervised [6][7][8] and supervised machine learning models [9,10]; an overview can be found in Weisser et al [11]. Commonly, DARs are evaluated on a single-spectrum level, meaning that a set of test spectra is assigned to their respective types by the DAR and that these assignments are checked for correctness by the user.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Know What You Don’t Know: Assessment of Overlooked Microplastic Particles in FTIR Images

et al. 2022

Self Cite

View full text Add to dashboard Cite

Assessing data analysis routines (DARs) for microplastics (MP) identification in Fourier-transform infrared (FTIR) images left the question ‘Do we overlook any MP particles in our sample?’ widely unanswered. Here, a reference image of microplastics, RefIMP, is presented to answer this question. RefIMP contains over 1200 MP and non-MP particles that serve as a ground truth that a DAR’s result can be compared to. Together with our MatLab® script for MP validation, MPVal, DARs can be evaluated on a particle level instead of isolated spectra. This prevents over-optimistic performance expectations, as testing of three hypotheses illustrates: (I) excessive background masking can cause overlooking of particles, (II) random decision forest models benefit from high-diversity training data, (III) among the model hyperparameters, the classification threshold influences the performance most. A minimum of 7.99% overlooked particles was achieved, most of which were polyethylene and varnish-like. Cellulose was the class most susceptible to over-segmentation. Most false assignments were attributed to confusion of polylactic acid for polymethyl methacrylate and of polypropylene for polyethylene. Moreover, a set of over 9000 transmission FTIR spectra is provided with this work, that can be used to set up DARs or as standard test set.

show abstract

Section: First Hypothesis: Masking Of Background Pixels Increases The...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Know What You Don’t Know: Assessment of Overlooked Microplastic Particles in FTIR Images

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In view of the importance of monitoring MNPs in environmental media, both spectroscopic and thermo-analytical approaches have been put into practice over recent years. − Spectroscopic methods such as FTIR and Raman spectroscopy have exhibited excellent performance for monitoring of microplastics in environments. , However, FTIR and Raman spectroscopy methods are limited to the MNP sizes, with thresholds of approximately 10 μm for FTIR and 100 nm for Raman, leading to the fact that tiny particles cannot be identified. ,− On the other hand, in analyses via thermo-analytical methods, polymers must first undergo degradation into micromolecules so as to prepare samples sufficiently for separation, identification, and determination by gas chromatography–mass spectrometry (GC-MS) or other MS techniques. , Although thermo-analytical methods cannot provide information regarding the size distribution of polymers in samples due to the destructive approach of such methods, information pertaining to their mass concentration and type of MNPs present in samples can be gathered. Moreover, in comparison to spectroscopic methods, thermo-analytical methods are faster, cover a wider MNP range, and do not necessitate rigorous purification .…”

Section: Introductionmentioning

confidence: 99%

“…6−9 Spectroscopic methods such as FTIR and Raman spectroscopy have exhibited excellent performance for monitoring of microplastics in environments. 10,11 However, FTIR and Raman spectroscopy methods are limited to the MNP sizes, with thresholds of approximately 10 μm for FTIR and 100 nm for Raman, leading to the fact that tiny particles cannot be identified. 6,12−16 On the other hand, in analyses via thermo-analytical methods, polymers must first undergo degradation into micromolecules so as to prepare samples sufficiently for separation, identification, and determination by gas chromatography−mass spectrometry (GC-MS) or other MS techniques.…”

Section: Introductionmentioning

confidence: 99%

Quantitative Determination of Poly(methyl Methacrylate) Micro/Nanoplastics by Cooling-Assisted Solid-Phase Microextraction Coupled to Gas Chromatography–Mass Spectrometry: Theoretical and Experimental Insights

Xu,

Li,

Xiao

et al. 2024

Anal. Chem.

View full text Add to dashboard Cite

Determinations of micro/nanoplastics (MNPs) in environmental samples are essential to assess the extent of their presence in the environment and their potential impact on ecosystems and human health. With the aim to provide a sensitive method with simplified pretreatment steps, cooling-assisted solid-phase microextraction (CA-SPME) coupled to gas chromatography−mass spectrometry (GC-MS) is proposed as a new approach to quantify mass concentrations of MNPs in water and soil samples. The herein proposed CA-SPME method offers the unique advantage of integrating the thermal decomposition of MNPs and enrichment of signature compounds into one step. Poly(methyl methacrylate) (PMMA) was used as a model substance to verify the method performance in this work. Theoretical insights demonstrated that pyrolysis is the rate-determining step during the extraction process and that PMMA is effectively decomposed at 350 °C with an estimated incubation time of 13 min. Eight compounds were identified in the pyrolysis products by CA-SPME-GC-MS with the use of a DVB/ CAR/PDMS coating, wherein methyl methacrylate was considered as the best indicator and dimethyl 2-methylenesuccinate was selected as the confirmation compound. Under the optimized conditions, the proposed method exhibited wide linearity (0.5−2000 μg for water and 5−1000 μg for soil) and high sensitivity, with limits of detection of 0.014 and 0.28 μg for water and soil, respectively. Finally, the proposed method was successfully applied for determinations of PMMA MNPs in real water and soil samples with satisfactory recoveries attained. The method only required the employment of a filter membrane for water analysis, while soil samples were analyzed directly without any pretreatment. The solvent-free approach, straightforward operation, and high sensitivity of the proposed method show great potential for the analysis of MNPs in different environmental samples.

show abstract

“…35 The rapid development of machine-learning (ML) algorithms provides many accessible tools that are being explored to improve microplastic analysis protocols. 36 An ML classification model based on the random forest (RF) algorithm trained on 306 Raman spectra from the open-source SLOPP and SLOPP-E databases was found to be capable of 89% classification accuracy. 37 This value was boosted to 94% with extensive pre-processing of the spectra to increase compatibility.…”

Section: ■ Introductionmentioning

confidence: 99%

Customizable Machine-Learning Models for Rapid Microplastic Identification Using Raman Microscopy

et al. 2022

View full text Add to dashboard Cite

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.

show abstract

The identification of microplastics based on vibrational spectroscopy data – A critical review of data analysis routines

Cited by 24 publications

References 101 publications

Know What You Don’t Know: Assessment of Overlooked Microplastic Particles in FTIR Images

Know What You Don’t Know: Assessment of Overlooked Microplastic Particles in FTIR Images

Quantitative Determination of Poly(methyl Methacrylate) Micro/Nanoplastics by Cooling-Assisted Solid-Phase Microextraction Coupled to Gas Chromatography–Mass Spectrometry: Theoretical and Experimental Insights

Customizable Machine-Learning Models for Rapid Microplastic Identification Using Raman Microscopy

Contact Info

Product

Resources

About