Machine learning assisted Raman spectroscopy: A viable approach for the detection of microplastics

Journal of Water Process Engineering, Год журнала: 2024, Номер 60, С. 105150 - 105150

Опубликована: Март 23, 2024

The accumulation of microplastics (MPs) resulting from disposal plastic waste into water sources, poses a significant threat to aquatic organisms. These are readily ingested by organisms, leading the harmful substances, disrupting their biological processes. Current methods for identifying have notable drawbacks, including low resolution, extended imaging time, and restricted particle size analysis. Integrating Raman spectroscopy with machine learning (ML) proves be an effective approach classifying MPs, especially in scenarios where they found environmental media or mixed various types. Machine can vital tool assisting analysis, owing its robust feature extraction capabilities. This comprehensive review outlined utilization techniques conjunction spectral features diverse investigations related microplastics. methodologies discussed encompass Principal Component Analysis, K-Nearest Neighbour, Random Forest, Support Vector Machine, deep algorithms.

Язык: Английский

---

Using artificial intelligence to rapidly identify microplastics pollution and predict microplastics environmental behaviors

Journal of Hazardous Materials, Год журнала: 2024, Номер 474, С. 134865 - 134865

Опубликована: Июнь 12, 2024

Язык: Английский

---

Discovery and solution for microplastics: New risk carriers in food

Food Chemistry, Год журнала: 2025, Номер unknown, С. 142784 - 142784

Опубликована: Янв. 1, 2025

Язык: Английский

---

Advances in microplastics detection: A comprehensive review of methodologies and their effectiveness

TrAC Trends in Analytical Chemistry, Год журнала: 2023, Номер 170, С. 117440 - 117440

Опубликована: Ноя. 17, 2023

Язык: Английский

---

Fast Detection and Classification of Microplastics below 10 μm Using CNN with Raman Spectroscopy

Analytical Chemistry, Год журнала: 2024, Номер 96(17), С. 6819 - 6825

Опубликована: Апрель 16, 2024

In light of the growing awareness regarding ubiquitous presence microplastics (MPs) in our environment, recent efforts have been made to integrate Artificial Intelligence (AI) technology into MP detection. Among spectroscopic techniques, Raman spectroscopy is preferred for detection particles measuring less than 10 μm, as it overcomes diffraction limitations encountered Fourier transform infrared (FTIR). However, spectroscopy's inherent limitation its low scattering cross section, which often results prolonged data collection times during practical sample measurements. this study, we implemented a convolutional neural network (CNN) model alongside tailored interpolation strategy expedite within 1–10 μm range. Remarkably, achieved classification plastic types individual with mere 0.4 s exposure time, reaching an approximate confidence level 85.47(±5.00)%. We postulate that result significantly accelerates aggregation microplastic distribution diverse scenarios, contributing development comprehensive global map.

Язык: Английский

---

Advancements and challenges in microplastic detection and risk assessment: Integrating AI and standardized methods

Marine Pollution Bulletin, Год журнала: 2025, Номер 212, С. 117529 - 117529

Опубликована: Янв. 4, 2025

Язык: Английский

---

Exploring Innovative Approaches for the Analysis of Micro- and Nanoplastics: Breakthroughs in (Bio)Sensing Techniques

Biosensors, Год журнала: 2025, Номер 15(1), С. 44 - 44

Опубликована: Янв. 13, 2025

Plastic pollution, particularly from microplastics (MPs) and nanoplastics (NPs), has become a critical environmental health concern due to their widespread distribution, persistence, potential toxicity. MPs NPs originate primary sources, such as cosmetic microspheres or synthetic fibers, secondary fragmentation of larger plastics through degradation. These particles, typically less than 5 mm, are found globally, deep seabeds human tissues, known adsorb release harmful pollutants, exacerbating ecological risks. Effective detection quantification essential for understanding mitigating impacts. Current analytical methods include physical chemical techniques. Physical methods, optical electron microscopy, provide morphological details but often lack specificity time-intensive. Chemical analyses, Fourier transform infrared (FTIR) Raman spectroscopy, offer molecular face challenges with smaller particle sizes complex matrices. Thermal including pyrolysis gas chromatography–mass spectrometry (Py-GC-MS), compositional insights destructive limited in analysis. Emerging (bio)sensing technologies show promise addressing these challenges. Electrochemical biosensors cost-effective, portable, sensitive platforms, leveraging principles voltammetry impedance detect adsorbed pollutants. Plasmonic techniques, surface plasmon resonance (SPR) surface-enhanced spectroscopy (SERS), high sensitivity nanostructure-enhanced detection. Fluorescent utilizing microbial enzymatic elements enable the real-time monitoring plastic degradation products, terephthalic acid polyethylene terephthalate (PET). Advancements innovative approaches pave way more accurate, scalable, environmentally compatible solutions, contributing improved remediation strategies. This review highlights advanced section on prospects that address could lead significant advancements monitoring, highlighting necessity testing new sensing developments under real conditions (composition/matrix samples), which overlooked, well study peptides novel recognition element microplastic sensing.

Язык: Английский

---

MPs Entering Human Circulation through Infusions: A Significant Pathway and Health Concern

Environment & Health, Год журнала: 2025, Номер unknown

Опубликована: Фев. 14, 2025

Язык: Английский

---

Machine Learning-Assisted Surface-Enhanced Raman Spectroscopy Detection for Environmental Applications: A Review

Environmental Science & Technology, Год журнала: 2024, Номер 58(47), С. 20830 - 20848

Опубликована: Ноя. 13, 2024

Surface-enhanced Raman spectroscopy (SERS) has gained significant attention for its ability to detect environmental contaminants with high sensitivity and specificity. The cost-effectiveness potential portability of the technique further enhance appeal widespread application. However, challenges such as management voluminous quantities high-dimensional data, capacity low-concentration targets in presence interferents, navigation complex relationships arising from overlapping spectral peaks have emerged. In response, there is a growing trend toward use machine learning (ML) approaches that encompass multivariate tools effective SERS data analysis. This comprehensive review delves into detailed steps needed be considered when applying ML techniques Additionally, we explored range applications where different were integrated detection pathogens (in)organic pollutants samples. We sought comprehend intricate considerations benefits associated these contexts. explores future synergizing real-world applications.

Язык: Английский

---

Quantitative analysis of microplastics in water environments based on Raman spectroscopy and convolutional neural network

The Science of The Total Environment, Год журнала: 2024, Номер 926, С. 171925 - 171925

Опубликована: Март 24, 2024

Язык: Английский

---