Enhanced spectral signatures with Ag nanoarrays in hyperspectral microscopy for CNN-based microplastics classfication

Frontiers in Chemistry, Journal Year: 2025, Volume and Issue: 13

Published: March 21, 2025

Microplastics are a pervasive pollutant in aquatic ecosystems, raising critical environmental and public health concerns driving the need for advanced detection technologies. Microscopic hyperspectral imaging (micro-HSI), known its ability to simultaneously capture spatial spectral information, has shown promise microplastic analysis. However, widespread application is hindered by limitations such as low signal-to-noise ratios (SNR) reduced sensitivity smaller particles. To address these challenges, this study investigates use of Ag nanoarrays reflective substrates micro-HSI. The localized surface plasmon resonance (LSPR) effect enhances resolution suppressing background reflections isolating reflection bands from interference. This improvement results significantly increased SNR more distinct features. When analyzed using 3D-2D convolutional neural network (3D-2D CNN), integration improved classification accuracy 90.17% 98.98%. These enhancements were further validated through Support Vector Machine (SVM) analyses, demonstrating robustness reliability proposed approach. demonstrates potential combining with CNN models enhance micro-HSI performance, offering novel effective solution precise microplastics advancing chemical analysis, monitoring, related fields.

Language: Английский

---

A Review of Materials for the Removal of Micro- and Nanoplastics from Different Environments

Micro, Journal Year: 2025, Volume and Issue: 5(2), P. 17 - 17

Published: April 9, 2025

Microplastics (MPs) and nanoplastics (NPs) have emerged as persistent environmental pollutants, posing significant ecological human health risks. Their widespread presence in aquatic, terrestrial, atmospheric ecosystems necessitates effective removal strategies. Traditional methods, including filtration, coagulation, sedimentation, demonstrated efficacy for larger MPs but struggle with nanoscale plastics. Advanced techniques, such adsorption, membrane photocatalysis, electrochemical shown promising results, yet challenges remain scalability, cost-effectiveness, impact. Emerging approaches, functionalized magnetic nanoparticles, AI-driven detection, laser-based remediation, present innovative solutions tackling MP NP contamination. This review provides a comprehensive analysis of current emerging strategies, evaluating their efficiency, limitations, future prospects. By identifying key research gaps, this study aims to guide advancements sustainable scalable microplastic technologies, essential mitigating implications.

Language: Английский

---

Machine Learning Advancements and Strategies in Microplastic and Nanoplastic Detection

Environmental Science & Technology, Journal Year: 2025, Volume and Issue: unknown

Published: April 28, 2025

Microplastics (MPs) and nanoplastics (NPs) present formidable global environmental challenges with serious risks to human health ecosystem sustainability. Despite their significance, the accurate assessment of MP NP pollution remains hindered by limitations in existing detection technologies, such as low resolution, substantial data volumes, prolonged imaging times. Machine learning (ML) provides a promising pathway overcome these enabling efficient processing complex pattern recognition. This systematic Review aims address gaps examining role ML techniques combined spectroscopy improving characterization NPs. We focused on application key tools detection, categorizing literature into aspects: (1) Developing tailored strategies for constructing models optimize plastic while expanding monitoring capabilities. Emphasis is placed harnessing unique molecular fingerprinting capabilities offered spectroscopy, including both infrared (IR) Raman spectra. (2) Providing an in-depth analysis issues encountered current approaches detection. highlights critical advancing our further, deeper investigation widespread presence By identifying challenges, this valuable insights future direction management public protection.

Language: Английский

---

The use of vibrational spectroscopy and supervised machine learning for chemical identification of plastics ingested by seabirds

Journal of Hazardous Materials, Journal Year: 2024, Volume and Issue: 476, P. 134996 - 134996

Published: June 21, 2024

Plastic pollution is now ubiquitous in the environment and represents a growing threat to wildlife, who can mistake plastic for food ingest it. Tackling this problem requires reliable, consistent methods monitoring ingested by seabirds other marine fauna, including identifying different types of plastic. This study presents robust method rapid, reliable chemical characterisation plastics 1-50 mm size range using infrared Raman spectroscopy. We analysed 246 objects Flesh-footed Shearwaters (Ardenna carneipes) from Lord Howe Island, Australia, compared data yielded each technique: 92 % visually identified as were confirmed spectroscopy, 98 those low density polymers such polyethylene, polypropylene, or their copolymers. Ingested exhibit significant spectral evidence biological contamination reports, which hinders identification conventional library searching. Machine learning be used identify vibrational spectra with up 93 accuracy. Overall, we find that more effective technique range, appropriately trained machine models superior searching plastics.

Language: Английский

---

Data driven AI (artificial intelligence) detection furnish economic pathways for microplastics

Journal of Contaminant Hydrology, Journal Year: 2024, Volume and Issue: 264, P. 104365 - 104365

Published: May 1, 2024

Language: Английский

---

A Green Approach to Nanoplastics Detection: SERS with Untreated Filter Paper for Polystyrene Nanoplastics

The Analyst, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

Plastic pollution at the nanoscale continues to pose adverse effects on environmental sustainability and human health. However, detection of nanoplastics (NPLs) remains challenging due limitations in methodology instrumentation. Herein, a "green approach" for surface-enhanced Raman spectroscopy (SERS) was exploited detect polystyrene nanospheres (PSNSs) water, employing untreated filter paper simple syringe-filtration set-up. This SERS protocol not only enabled filtration nano-sized PSNSs, which are smaller than pore size ordinary paper, but also offered enhancement by utilizing quasi-spherical-shaped silver nanoparticles (AgNPs) as SERS-active substrate. The filtering NPLs accomplished adding an aggregating agent nanoparticle mixture, caused aggregation AgNPs, resulting larger cluster more hot spots detection. optimal its concentration, well volume ratio between AgNPs NPLs, were optimized. method successfully detected quantified PSNSs various sizes (

Language: Английский

---

Raman Spectroscopy Based Approaches for Microplastics Investigations

Emerging contaminants and associated treatment technologies, Journal Year: 2024, Volume and Issue: unknown, P. 647 - 672

Published: Jan. 1, 2024

Language: Английский

---

Practical guidelines and challenges in the isolation and characterization of microplastics/microfibers by Raman microscopy

Marine Pollution Bulletin, Journal Year: 2024, Volume and Issue: 209, P. 117133 - 117133

Published: Oct. 25, 2024

Language: Английский

---

State-of-the-art review on various applications of machine learning techniques in materials science and engineering

Chemical Engineering Science, Journal Year: 2024, Volume and Issue: unknown, P. 121147 - 121147

Published: Dec. 1, 2024

Language: Английский

---