Automatic quantification and classification of microplastics in scanning electron micrographs via deep learning

Rapid detection of microfibres in environmental samples using open-source visual recognition models

Microplastics, particularly microfibres (< 5 mm), are a significant environmental pollutant. Detecting and quantifying them in complex matrices is challenging and time-consuming. This study presents two open-source visual recognition models, YOLOv7 and Mask R-CNN, trained on extensive datasets for efficient microfibre identification in environmental samples. The YOLOv7 model is a new introduction to the microplastic quantification research, while Mask R-CNN has been previously used in similar studies. YOLOv7, with 71.4 % accuracy, and Mask R-CNN, with 49.9 % accuracy, demonstrate effective detection capabilities. Tested on aquatic samples from Seyðisfjörður, Iceland, YOLOv7 rapidly identifies microfibres, outperforming manual methods in speed. These models are user-friendly and widely accessible, making them valuable tools for microplastic contamination assessment. Their rapid processing offers results in seconds, enhancing research efficiency in microplastic pollution studies. By providing these models openly, we aim to support and advance microplastic quantification research. The integration of these advanced technologies with environmental science represents a significant step forward in addressing the global issue of microplastic pollution and its ecological and health impacts.

Microplastics monitoring in freshwater systems: A review of global efforts, knowledge gaps, and research priorities

The escalating production of synthetic plastics and inadequate waste management have led to pervasive microplastic (MP) contamination in aquatic ecosystems. MPs, typically defined as particles smaller than 5 mm, have become an emerging pollutant in freshwater environments. While significant concern about MPs has risen since 2014, research has predominantly concentrated on marine settings, there is an urgent need for a more in-depth critical review to systematically summarize the current global efforts, knowledge gaps, and research priorities for MP monitoring in freshwater systems. This review evaluates the current understanding of MP monitoring in freshwater environments by examining the distribution, characteristics, and sources of MPs, alongside the progression of analytical methods with quantitative evidence. Our findings suggest that MPs are widely distributed in global freshwater systems, with higher abundances found in areas with intense human economic activities, such as the United States, Europe, and China. MP abundance distributions vary across different water bodies (e.g., rivers, lakes, estuaries, and wetlands), with sampling methods and size range selections significantly influencing reported MP abundances. Despite great global efforts, there is still a lack of harmonized analyzing framework and understanding of MP pollution in specific regions and facilities. Future research should prioritize the development of standardized analysis protocols and open-source MP datasets to facilitate data comparison. Additionally, exploring the potential of state-of-the-art artificial intelligence for rapid, accurate, and large-scale modeling and characterization of MPs is crucial to inform effective strategies for managing MP pollution in freshwater ecosystems.

Detection of microplastics in human tissues and organs: A scoping review

Background

Research on microplastics has largely focused on the environment and marine organisms until recently. A growing body of evidence has detected microplastics in human organs and tissues, with their exact entry routes being unclear and their potential health effects remain unknown. This scoping review aimed to characterise microplastics in human tissues and organs, examine their entry routes and addressing gaps in research analytical techniques.

Methods

Eligibility criteria included English language full text articles, in-vivo human studies only, and searching the databases using pre-defined terms. We based our analysis and reporting on the PRISMA guideline and examined the quality of evidence using the risk of bias assessment tool.

Results

Of 3616 articles screened, 223 evaluated and 26 were eventually included in this review. Nine were high risk for bias, three were unclear risk and the rest low risk for bias. Microplastics were detected in 8/12 human organ systems including cardiovascular, digestive, endocrine, integumentary, lymphatic, respiratory, reproductive and urinary. Microplastics were also observed in other human biological samples such as breastmilk, meconium, semen, stool, sputum and urine. Microplastics can be characterised based on shape, colours, and polymer type. Potential entry routes into human included atmospheric inhalation and ingestion through food and water. The extraction techniques for analysis of microplastics in human tissues vary significantly, each offering distinct advantages and limitations.

Conclusions

Microplastics are commonly detected in human tissues and organs, with distinct characteristics and entry routes, and variable analytical techniques exist.

Artificial intelligence in microplastic detection and pollution control

The rising prevalence of microplastics (MPs) in various ecosystems has increased the demand for advanced detection and mitigation strategies. This review examines the integration of artificial intelligence (AI) with environmental science to improve microplastic detection. Focusing on image processing, Fourier transform infrared spectroscopy (FTIR), Raman spectroscopy, and hyperspectral imaging (HSI), the review highlights how AI enhances the efficiency and accuracy of these techniques. AI-driven image processing automates the identification and quantification of MPs, significantly reducing the need for manual analysis. FTIR and Raman spectroscopy accurately distinguish MP types by analyzing their unique spectral features, while HSI captures extensive spatial and spectral data, facilitating detection in complex environmental matrices. Furthermore, AI algorithms integrate data from these methods, enabling real-time monitoring, traceability prediction, and pollution hotspot identification. The synergy between AI and spectral imaging technologies represents a transformative approach to environmental monitoring and emphasizes the need to adopt innovative tools for protecting ecosystem health.

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

With the massive release of microplastics (MPs) into the environment, research related to MPs is advancing rapidly. Effective research methods are necessary to identify the chemical composition, shape, distribution, and environmental impacts of MPs. In recent years, artificial intelligence (AI)-driven machine learning methods have demonstrated excellent performance in analyzing MPs in soil and water. This review provides a comprehensive overview of machine learning methods for the prediction of MPs for various tasks, and discusses in detail the data source, data preprocessing, algorithm principle, and algorithm limitation of applied machine learning. In addition, this review discusses the limitation of current machine learning methods for various task analysis in MPs along with future prospect. Finally, this review finds research potential in future work in building large generalized MPs datasets, designing high-performance but low-computational-complexity algorithms, and evaluating model interpretability.

Micro(nano)plastics from synthetic oligomers persisting in Mediterranean seawater: Comprehensive NMR analysis, concerns and origins

The presence in seawater of low-molecular-weight polyethylene (PE) and polydimethylsiloxane (PDMS), synthetic polymers with high chemical resistance, has been demonstrated in this study for the first time by developing a novel methodology for their recovery and quantification from surface seawater. These synthetic polymer debris (SPD) with very low molecular weights and sizes in the nano- and micro-metre range have escaped conventional analytical methods. SPD have been easily recovered from water samples (2 L) through filtration with a nitrocellulose membrane filter with a pore size of 0.45 μm. Dissolving the filter in acetone allowed the isolation of the particulates by centrifugation followed by drying. The isolated SPD were analysed by 1H nuclear magnetic resonance spectroscopy (1H NMR), identifying PE and PDMS. These polymers are thus persisting on seawater because of their low density and the ponderal concentrations were quantified in mg/m3. This method was used in an actual case study in which 120 surface seawater samples were collected during two sampling campaigns in the Mediterranean Sea (from the Gulf of Salerno to the Gulf of Policastro in South Italy). The developed analytical protocol allowed achieving unprecedented simplicity, rapidity and sensitivity. The 1H and 13C NMR structural analysis of the PE debris indicates the presence of oxidised polymer chains with very low molecular weights. Additionally, the origin of those low molecular weight polymers was investigated by analysing influents and effluents from a wastewater treatment plant (WWTP) in Salerno as a hot spot for the release of SPD: the analysis indicates the presence of low molecular weight polymers compatible with wax-PE, widely used for coating applications, food industry, cosmetics and detergents. Moreover, the origin of PDMS debris found in surface seawater can be ascribed to silicone-based antifoamers and emulsifiers.

Research on the Migration and Adsorption Mechanism Applied to Microplastics in Porous Media: A Review

In recent years, microplastics (MPs) have emerged as a significant environmental pollutant, garnering substantial attention for their migration and transformation behaviors in natural environments. MPs frequently infiltrate natural porous media such as soil, sediment, and rock through various pathways, posing potential threats to ecological systems and human health. Consequently, the migration and adsorption mechanisms applied to MPs in porous media have been extensively studied. This paper aims to elucidate the migration mechanisms of MPs in porous media and their influencing factors through a systematic review. The review encompasses the characteristics of MPs, the physical properties of porous media, and hydrodynamic factors. Additionally, the paper further clarifies the adsorption mechanisms of MPs in porous media to provide theoretical support for understanding their environmental behavior and fate. Furthermore, the current mainstream detection techniques for MPs are reviewed, with an analysis of the advantages, disadvantages, and applications of each technique. Finally, the paper identifies the limitations and shortcomings of current research and envisions future research directions.

Artificial intelligence-empowered collection and characterization of microplastics: A review

Microplastics have been detected from water and soil systems extensively, with increasing evidence indicating their detrimental impacts on human and animal health. Concerns surrounding microplastic pollution have spurred the development of advanced collection and characterization methods for studying the size, abundance, distribution, chemical composition, and environmental impacts. This paper offers a comprehensive review of artificial intelligence (AI)-empowered technologies for the collection and characterization of microplastics. A framework is presented to streamline efforts in utilizing emerging robotics and machine learning technologies for collecting, processing, and characterizing microplastics. The review encompasses a range of AI technologies, delineating their principles, strengths, limitations, representative applications, and technology readiness levels, facilitating the selection of suitable AI technologies for mitigating microplastic pollution. New opportunities for future research and development on integrating robots and machine learning technologies are discussed to facilitate future efforts for mitigating microplastic pollution and advancing AI technologies.

Comparative study of the removal of sulfate by UASB in light and dark environment

At present, the application of sewage treatment technologies is restricted by high sulfate concentrations. In the present work, the sulfate removal was biologically treated using an upflow anaerobic sludge blanket (UASB) in the absence/presence of light. First, the start-up of UASB for the sulfate removal was studied in terms of COD degradation, sulfate removal, and effluent pH. Second, the impacts of different operation parameters (i.e., COD/SO42- ratio, temperature and illumination time) on the UASB performance were explored. Third, the properties of sludge derived from the UASB at different time were analyzed. Results show that after 28 days of start-up, the COD removal efficiencies in both the photoreactor and non-photoreactor could reach a range of 85-90% while such reactors could achieve > 90% of sulfate being removed. Besides, higher illumination time could facilitate the removal of pollutants in the photoreactor. To sum up, the present study can provide technical support for the clean removal of sulfate from wastewater using photoreactors.

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

Microplastics pollution is killing human life, contaminating our oceans, and lasting for longer in the environment than it is used. Microplastics have contaminated the geochemistry and turned the water system into trash barrel. Its detection in water is easy in comparison to soil and air so the attention of researchers is focused on it for now. Being very small in size, microplastics can easily cross the water filtration system and end up in the ocean or lakes and become the prospective challenge to aquatic life. This review piece provides the hot research theme and current advances in the field of microplastics and their eradication through the virtual world of artificial intelligence (AI) because Microplastics have confrontation with clean water tactics.

Microplastics in water: Occurrence, fate and removal

A global study on tap water samples has found that up to 83% of these contained microplastic fibres. These findings raise concerns about their potential health risks. Ingested microplastic particles have already been associated with harmful effects in animals, which raise concerns about similar outcomes in humans. Microplastics are ubiquitous in the environment, commonly found disposed in landfills and waste sites. Within indoor environments, the common sources are synthetic textiles, plastic bottles, and packaging. From the various point sources, they are globally distributed through air and water and can enter humans through various pathways. The finding of microplastics in fresh snow in the Antarctic highlights just how widely they are dispersed. The behaviour and health risks from microplastic particles are strongly influenced by their physicochemical properties, which is why their surfaces are important. Surface interactions are also important in pollutant transport via adsorption onto the microplastic particles. Our review covers the latest findings in microplastics research including the latest statistics in their abundance, their occurrence and fate in the environment, the methods of reducing microplastics exposure and their removal. We conclude by proposing future research directions into more effective remediation methods including new technologies and sustainable green remediation methods that need to be explored to achieve success in microplastics removal from waters at large scale.

Innovative methods for microplastic characterization and detection: Deep learning supported by photoacoustic imaging and automated pre-processing data

Plastic products' widespread applications and their non-biodegradable nature have resulted in the continuous accumulation of microplastic waste, emerging as a significant component of ecological environmental issues. In the field of microplastic detection, the intricate morphology poses challenges in achieving rapid visual characterization of microplastics. In this study, photoacoustic imaging technology is initially employed to capture high-resolution images of diverse microplastic samples. To address the limited dataset issue, an automated data processing pipeline is designed to obtain sample masks while effectively expanding the dataset size. Additionally, we propose Vqdp2, a generative deep learning model with multiple proxy tasks, for predicting six forms of microplastics data. By simultaneously constraining model parameters through two training modes, outstanding morphological category representations are achieved. The results demonstrate Vqdp2's excellent performance in classification accuracy and feature extraction by leveraging the advantages of multi-task training. This research is expected to be attractive for the detection classification and visual characterization of microplastics.

Intelligent classification and pollution characteristics analysis of microplastics in urban surface waters using YNet

Microplastics (MPs, ≤ 5 mm in size) are hazardous contaminants that pose threats to ecosystems and human health. YNet was developed to analyze MPs abundance and shape to gain insights into MPs pollution characteristics in urban surface waters. The study found that YNet achieved an accurate identification and intelligent classification performance, with a dice similarity coefficient (DSC) of 90.78%, precision of 94.17%, and recall of 89.14%. Analysis of initial MPs levels in wetlands and reservoirs revealed 127.3 items/L and 56.0 items/L. Additionally, the MPs in effluents were 27.0 items/L and 26.3 items/L, indicating the ability of wetlands and reservoirs to retain MPs. The concentration of MPs in the lower reaches of the river was higher (45.6 items/L) compared to the upper reaches (22.0 items/L). The majority of MPs detected in this study were fragments, accounting for 51.63%, 54.94%, and 74.74% in the river, wetland, and reservoir. Conversely, granules accounted for the smallest proportion of MPs in the river, wetland, and reservoir, representing only 11.43%, 10.38%, and 6.5%. The study proves that the trained YNet accurately identify and intelligently classify MPs. This tool is essential in comprehending the distribution of MPs in urban surface waters and researching their sources and fate.

A review of microplastic transport in coastal zones

Transport of microplastics (MPs) in coastal zones is influenced not only by their own characteristics, but also by the hydrodynamic conditions and coastal environment. In this article, we first summarized the source, distribution and abundance of MPs in coastal zones around the world through the induction of in-situ observation literature, and then comprehensively reviewed the different transports of MPs in coastal zones, including sedimentation, vertical mixing, resuspension, drift and biofouling. Afterwards, we conducted a comparative analysis of relevant experimental literature, and found that the current experimental research on microplastic transport mainly focused on the settling velocity under static water and the transport distribution under dynamic water. Based on the relevant literature on numerical simulation of microplastic transport in coastal zones, it was also found that the Euler-Lagrange method is the most widely used. The main influencing factor in the Euler method is hydrodynamic, while the Lagrange method and Euler-Lagrange method is hydrodynamic and microplastic particle characteristics. Tides in hydrodynamics are mentioned the most frequently, and the role of turbulence in almost all the literature. The density of MPs is the most influencing factor on transport results, followed by size, while shape is only studied in small-scale models. Some literature has also found that the influence of biofilms is mainly reflected in the changes in the density and size of MPs.

Efficient and accurate microplastics identification and segmentation in urban waters using convolutional neural networks

Microplastics (MPs), measuring less than 5 mm, pose threats to ecological security and human health in urban waters. Additionally, they act as carriers, transporting pollutants from terrestrial systems into oceanic circulation, contributing to global pollution. Recognizing the significance of identifying MPs in urban waters, one potential solution to the time-consuming and labor-intensive manual identification process is the application of a convolutional neural network (CNN). Therefore, having a reliable CNN model that efficiently and accurately identifies MPs is essential for extensive research on MPs pollution in urban waters. In this work, an MPs dataset with complex background was acquired from urban waters in southern China. The dataset was used to train and validate CNN models, including UNet, UNet2plus, and UNet3plus. Subsequently, the computational and inference performance of the three models was evaluated using a newly collected MPs dataset. The results showed that UNet, UNet2plus, UNet3plus, after being trained for 120 epochs, provided efficient inferences within less than 1 s, 2 s, and 3 s for 100 MPs images, respectively. Accurate segmentation with mIoU of 91.45 ± 5.93 % and 91.08 ± 6.18 % was achieved using UNet and UNet2plus, respectively, while UNet3plus exhibited a lower performance with only 82.21 ± 10.33 % mIoU. This work demonstrated that UNet and UNet2plus deliver efficient and accurate identification of MPs in urban waters. Developing CNN models that efficiently and accurately identify MPs is crucial for reducing manual time, especially in large-scale investigations of MPs pollution in urban waters.

Microplastics sequestered in the soil affect the turnover and stability of soil aggregates: A review

Plastic products have become ubiquitous in society, and entered various ecosystems due to the massive scale of production. The United Nations Environment Program (UNEP) has listed microplastics (MPs), which form when plastic remnants degrade, as a global emerging pollutant, and the association between soil pollution and MPs has become a popular research topic. This paper systematically reviews research focusing on MP-related soil pollution from the past 10 years (2012-2022), with the identified papers demonstrating that interactions between MPs and soil aggregates has become a research frontier in the field. The presented research provides evidence that soil aggregates are important storage sites for MPs, and that storage patterns of MPs within soil aggregates are influenced by MP characteristics. In addition, MPs affect the formation, turnover, and stability of soil aggregates through the introduction of fracture points along with diverse physicochemical characteristics such as composition and specific surface area. The current knowledge base includes certain issues and challenges that could be addressed in future research by extending the spatial and temporal scales over which microplastic-soil aggregate interactions are studied, unifying quantitative and qualitative methods, and tracing the fates of MPs in the soil matrix. This review contributes to enriching our understanding of how terrestrial MPs interact with soil aggregates, and whether they pose a risk to soil health.

Airborne microplastics: A narrative review of potential effects on the human respiratory system

There has been growing evidence showing the widespread of airborne microplastics (AMPs) in many regions of the world, raising concerns about their impact on human health. This review aimed to consolidate recent literature on AMPs regarding their physical and chemical characteristics, deposition in the human respiratory tract, translocation, occurrence from human studies, and toxic effects determined in vitro and in vivo. The physical characteristics influence interactions with cell membranes, cellular internalization, accumulation, and cytotoxicity resulting from cell membrane damage and oxidative stress. In addition, prolonged exposure to AMP-associated toxic chemicals might lead to significant health effects. Most toxicological assessments of AMPs in vitro and in vivo have demonstrated that oxidative stress and inflammation are major mechanisms of action for their toxic effects. Elevated reactive oxygen species production could lead to mitochondrial dysfunction, inflammatory responses, and subsequent apoptosis in experimental models. To date, there has been some evidence suggesting exposure in humans. However, the data are still insufficient, and adverse human health effects need to be investigated. Future research on the existence, exposure, and health effects of AMPs is required for developing preventive and mitigation measures to protect human health.

Automatic classification of microplastics and natural organic matter mixtures using a deep learning model

Several preprocessing procedures are required for the classification of microplastics (MPs) in aquatic systems using spectroscopic analysis. Procedures such as oxidation, which are employed to remove natural organic matter (NOM) from MPs, can be time- and cost-intensive. Furthermore, the identification process is prone to errors due to the subjective judgment of the operators. Therefore, in this study, deep learning (DL) was applied to improve the classification accuracies for mixtures of microplastic and natural organic matter (MP-NOM). A convolutional neural network (CNN)-based DL model with a spatial attention mechanism was adopted to classify substances from their Raman spectra. Subsequently, the classification results were compared with those obtained using conventional Raman spectral library software to evaluate the applicability of the model. Additionally, the crucial spectral band for training the DL model was investigated by applying gradient-weighted class activation mapping (Grad-CAM) as a post-processing technique. The model achieved an accuracy of 99.54%, which is much higher than the 31.44% achieved by the Raman spectral library. The Grad-CAM approach confirmed that the DL model can effectively identify MPs based on their visually prominent peaks in the Raman spectra. Furthermore, by tracking distinctive spectra without relying solely on visually prominent peaks, we can accurately classify MPs with less prominent peaks, which are characterized by a high standard deviation of intensity. These findings demonstrate the potential for automated and objective classification of MPs without the need for NOM preprocessing, indicating a promising direction for future research in microplastic classification.

Recent Study of Separation and Identification of Micro- and Nanoplastics for Aquatic Products

Micro- and nanoplastics (MNPs) are polymeric compounds widely used in industry and daily life. Although contamination of aquatic products with MNPs exists, most current research on MNPs focuses on environmental, ecological, and toxicological studies, with less on food safety. Currently, the extent to which aquatic products are affected depends primarily on the physical and chemical properties of the consumed MNPs and the content of MNPs. This review presents new findings on the occurrence of MNPs in aquatic products in light of their properties, carrier effects, chemical effects, seasonality, spatiality, and differences in their location within organisms. The latest studies have been summarized for separation and identification of MNPs for aquatic products as well as their physical and chemical properties in aquatic products using fish, bivalves, and crustaceans as models from a food safety perspective. Also, the shortcomings of safety studies are reviewed, and guidance is provided for future research directions. Finally, gaps in current knowledge on MNPs are also emphasized.

A review on constructive classification framework of research trends in analytical instrumentation for secondary micro(nano)plastics: What is new and what needs next?

Secondary micro(nano)plastics generated from the degradation of plastics pose a major threat to environmental and human health. Amid the growing research on microplastics to date, the detection of secondary micro(nano)plastics is hampered by inadequate analytical instrumentation in terms of accuracy, validation, and repeatability. Given that, the current review provides a critical evaluation of the research trends in instrumental methods developed so far for the qualitative and quantitative determination of micro(nano)plastics with an emphasis on the evolution, new trends, missing links, and future directions. We conducted a meta-analysis of the growing literature surveying over 800 journal articles published from 2004 to 2022 based on the Web of Science database. The significance of this review is associated with the proposed novel classification framework to identify three main research trends, viz. (i) preliminary investigations, (ii) current progression, and (iii) novel advances in sampling, characterization, and quantification targeting both micro- and nano-sized plastics. Field Flow Fractionation (FFF) and Hydrodynamic Chromatography (HDC) were found to be the latest techniques for sampling and extraction of microplastics. Fluorescent Molecular Rotor (FMR) and Thermal Desorption-Proton Transfer Reaction-Mass Spectrometry (TD-PTR-MS) were recognized as the modern developments in the identification and quantification of polymer units in micro(nano)plastics. Powerful imaging techniques, viz. Digital Holographic Imaging (DHI) and Fluorescence Lifetime Imaging Microscopy (FLIM) offered nanoscale analysis of the surface topography of nanoplastics. Machine learning provided fast and less labor-intensive analytical protocols for accurate classification of plastic types in environmental samples. Although the existing analytical methods are justifiable merely for microplastics, they are not fully standardized for nanoplastics. Future research needs to be more inclined towards secondary nanoplastics for their effective and selective analysis targeting a broad range of environmental and biological matrices.

Machine learning: Next promising trend for microplastics study

Microplastics (MPs), as an emerging pollutant, pose a significant threat to humans and ecosystems. However, traditional MPs characterization methods are limited by sample requirements and characterization time. Machine Learning (ML) has emerged as a vital technology for analyzing MPs pollution due to its accuracy, broad application, and powerful feature extraction. Nevertheless, environmental scientists require threshold knowledge before using ML, restricting the ML application in MPs research. Furthermore, imbalanced development of ML in MPs research is a pressing concern. In order to achieve a wide ML application in MPs research, in this review, we comprehensively discussed the size and sources of MPs datasets in relevant literature to help environmental scientists deepen their understanding of the construction of MPs datasets. Commonly used ML algorithms are analyzed from the perspective of interpretability and the need for computer facilities. Additionally, methods for improving and evaluating ML model performance, such as dataset pre-processing, model optimization, and model assessment metrics, are discussed. According to datasets and characterization techniques, MPs identification using ML was divided into three categories in this work: spectral identification, image identification, and spectral imaging identification. Finally, other applications of ML in MPs studies, including toxicity analysis, pollutants adsorption, and microbial colonization, are comprehensively discussed, which reveals the great application potential of ML. Based on the discussion above, this review suggests an algorithm selection strategy to assist researchers in selecting the most suitable ML algorithm in different situations, improving efficiency and decreasing the costs of trial and error. We believe that this work sheds light on the application of ML in MPs study.

Improvement of a Rapid Method of Detecting Gasoline Detergency Based on the Image Recognition

The detergency of motor gasoline is closely related to vehicle exhaust emissions and fuel economy. This paper proposed an improved method for the rapid detection of gasoline detergency based on the deposit images of test gasoline on aluminum plates produced by a multichannel gasoline detergency simulation test (MGST). The detection algorithm system was structured to recognize the deposit plate images by computer vision based on the convolutional neural networks (CNNs). Compared with the traditional simulation test, the improved MGST method resulted in significant reductions in fuel consumption, cost, and test time. The performance of three transfer learning models (Inception-ResNet-V2, Inception-V3, and ResNet50-V2) and a customized CNN was evaluated in the detection algorithm system, and their detection accuracies reached 94, 94, 88, and 82%. Inception-RsNet-V2 was selected due to its higher accuracy and better robustness. Based on the model interpretation, it is evident that the model undergoes feature extraction from the sediment deposits on the deposit plate. Subsequently, it employed the acquired deposit features to accurately detect gasoline samples that failed to meet detergency standards. This approach was proved to be effective in enhancing the detection process and ensuring reliable results for gasoline detergency evaluation. It is beneficial to environmental protection regulators for managing market gasoline detergency and urban mobile source pollution. In addition, a deposit plate image database should be established to further improve the detection model performance during the environmental regulation.

Application of Pattern Recognition and Computer Vision Tools to Improve the Morphological Analysis of Microplastic Items in Biological Samples

Since, in many routine analytical laboratories, a stereomicroscope coupled with a digital camera is not equipped with advanced software enabling automatic detection of features of observed objects, in the present study, a procedure of feature detection using open-source software was proposed and validated. Within the framework of applying microscopic expertise coupled with image analysis, a set of digital images of microplastic (MP) items identified in organs of fish was used to determine shape descriptors (such as length, width, item area, etc.). The edge points required to compute shape characteristics were set manually in digital images acquired by the camera coupled with a binocular, and respective values were computed via the use of built-in MotiConnect software. As an alternative, a new approach consisting of digital image thresholding, binarization, the use of connected-component labeling, and the computation of shape descriptors on a pixel level via using the functions available in an OpenCV library or self-written in C++ was proposed. Overall, 74.4% of the images were suitable for thresholding without any additional pretreatment. A significant correlation was obtained between the shape descriptors computed by the software and computed using the proposed approach. The range of correlation coefficients at a very high level of significance, according to the pair of correlated measures, was higher than 0.69. The length of fibers can be satisfactorily approximated using a value of half the length of the outer perimeter (r higher than 0.75). Compactness and circularity significantly differ for particles and fibers.

Shapes of Hyperspectral Imaged Microplastics

Shape matters for microplastics, but its definition, particularly for hyperspectral imaged microplastics, remains ambiguous and inexplicit, leading to incomparability across data. Hyperspectral imaging is a common approach for quantification, yet no unambiguous microplastic shape classification exists. We conducted an expert-based survey and proposed a set of clear and concise shapes (fiber, rod, ellipse, oval, sphere, quadrilateral, triangle, free-form, and unidentifiable). The categories were validated on images of 11,042 microplastics from four environmental compartments (seven matrices: indoor air; wastewater influent, effluent, and sludge; marine water; stormwater; and stormwater pond sediments), by inviting five experts to score each shape. We found that the proposed shapes were well defined, representative, and distinguishable to the human eye, especially for fiber and sphere. Ellipse, oval, and rod were though less distinguishable but dominated in all water and solid matrices. Indoor air held more unidentifiable, an abstract shape that appeared mostly for particles below 30 μm. This study highlights the need for assessing the recognizability of chosen shape categories prior to reporting data. Shapes with a clear and stringent definition would increase comparability and reproducibility across data and promote harmonization in microplastic research.

Microplastics in water: types, detection, and removal strategies

Microplastics are one of the most concerning groups of contaminants that pollute most of the surroundings of the Earth. The abundance of plastic materials available in the environment moved the scientific community in defining a new historical era known as Plasticene. Regardless of their minuscule size, microplastics have posed severe threats to the life forms like animals, plants, and other species present in the ecosystem. Ingestion of microplastics could lead to harmful health effects like teratogenic and mutagenic abnormalities. The source of microplastics could be either primary or secondary in which the components of microplastics are directly released into the atmosphere and the breakdown of larger units to generate the smaller molecules. Though numerous physical and chemical techniques are reported for the removal of microplastics, their increased cost prevents the large-scale applicability of the process. Coagulation, flocculation, sedimentation, and ultrafiltration are some of the methods used for the removal of microplastics. Certain species of microalgae are known to remove microplastics by their inherent nature. One of the biological treatment strategies for microplastic removal is the activated sludge strategy that is used for the separation of microplastic. The overall microplastic removal efficiency is significantly high compared to conventional techniques. Thus, the reported biological avenues like the bio-flocculant for microplastic removal are discussed in this review article.

Abundance and composition of microplastics in Tampico beach sediments, Tamaulipas State, southern Gulf of Mexico

The abundance and characteristics of microplastics (MPs) in coastal sediments from the Tampico beach, Gulf of Mexico was investigated. The MPs were extracted by a density separation method with saturated solutions of NaCl and ZnCl₂, the sediment-solution relationship was 1:3. MPs were classified according to its shape, color, and size under a stereoscopic microscope. Identification of MPs surface was carried out by a Scanning Electron Microscope (SEM). The polymer types were detected by a Fourier-transformed infrared (FTIR) Spectroscopy. Number of MPs in 20 g of sediments varies from 256 to 283 particles. The average abundance of MPs per kg was inferred as ∼13,392 microplastic particles. Fiber was the only MP particle identified in the Tampico beach, its size varied from 1.76 mm to 3.92 mm. Fibers identified were mostly transparent, blue, white, black, multicolor, yellow, pink, and red. Six different polymers were identified, i.e., polyester (PES), polyethylacrylate (PEA), cellophane, polyacrylonitrile (PAN), polystyrene acrylonitrile (SAN), and polyvinyl acetate ethylene (PVAE). PES is the most prevalent polymer in all samples.

AI explainability framework for environmental management research

Deep learning networks powered by AI are essential predictive tools relying on image data availability and processing hardware advancements. However, little attention has been paid to explainable AI (XAI) in application fields, including environmental management. This study develops an explainability framework with a triadic structure to focus on input, AI model and output. The framework provides three main contributions. (1) A context-based augmentation of input data to maximize generalizability and minimize overfitting. (2) A direct monitoring of AI model layers and parameters to use leaner (lighter) networks suitable for edge device deployment, (3) An output explanation procedure focusing on interpretability and robustness of predictive decisions by AI networks. These contributions significantly advance state of the art in XAI for environmental management research, offering implications for improved understanding and utilization of AI networks in this field.

Spectral Classification of Large-Scale Blended (Micro)Plastics Using FT-IR Raw Spectra and Image-Based Machine Learning

Microplastics (MPs) are currently recognized as emerging pollutants; their identification and classification are therefore essential during their monitoring and management. In contrast to most studies based on small datasets and library searches, this study developed and compared four machine learning-based classifiers and two large-scale blended plastic datasets, where a 1D convolutional neural network (CNN), decision tree, and random forest (RF) were fed with raw spectral data from Fourier transform infrared spectroscopy, while a 2D CNN used the corresponding spectral images as the input. With an overall accuracy of 96.43% on a small dataset and 97.44% on a large dataset, the 1D CNN outperformed other models. The 1D CNN was the best at predicting environment samples, while the RF was the most robust with less spectral data. Overall, RF and 2D CNNs might be evaluated for plastic identification with fewer spectral data; however, 1D CNNs were thought to be the most effective with sufficient spectral data. Accordingly, an open-source MP spectroscopic analysis tool was developed to facilitate a quick and accurate analysis of existing MP samples.

Digital holographic approaches to the detection and characterization of microplastics in water environments

Microplastic (MP) pollution is seriously threatening the environmental health of the world, which has accelerated the development of new identification and characterization methods. Digital holography (DH) is one of the emerging tools to detect MPs in a high-throughput flow. Here, we review advances in MP screening by DH. We examine the problem from both the hardware and software viewpoints. Automatic analysis based on smart DH processing is reported by highlighting the role played by artificial intelligence for classification and regression tasks. In this framework, the continuous development and availability in recent years of field-portable holographic flow cytometers for water monitoring also is discussed.

A spectroscopic study on orthodontic aligners: First evidence of secondary microplastic detachment after seven days of artificial saliva exposure

Clear orthodontic aligners have recently seen increasing popularity. The thermoplastic materials present several advantages, even if it is known that all plastic products can be subjected to environmental and mechanical degradation, leading to the release of microplastics (MPs). Their ingestion could cause oxidative stress and inflammatory lesions. This study aims to evaluate the potential detachment of MPs by clear aligners due to mechanical friction simulated with a 7-day protocol in artificial saliva. The study was performed on orthodontic clear aligners from different manufacturers: Alleo (AL); FlexiLigner (FL); F22 Aligner (F22); Invisalign® (INV); Lineo (LIN); Arc Angel (ARC), and Ortobel Aligner (OR). For each group, two aligners were immersed in artificial saliva for 7 days and stirred for 5 h/day, simulating the physiological teeth mechanical friction. After 7 days, the artificial saliva was filtered; then, filters were analyzed by Raman Microspectroscopy (RMS) and Scanning Electron Microscopy (SEM), respectively to chemically identify the polymeric matrix and to measure the number and size of the detected MPs. RMS spectra revealed that AL, FL, LIN, ARC, and OR aligners were composed by polyethylene terephthalate, while F22 and INV ones by polyurethane. SEM analysis showed that the highest number of MPs was found in ARC and the lowest in INV (p < 0.05). As regards MPs' size, no statistically significant difference was found among groups, with most MPs ranging from 5 to 20 μm. Noteworthy, a highly significant correlation (p < 0.0001) was highlighted between the distribution of MPs size and the different typologies of aligners. This in vitro study highlighted for the first time the detachment of MPs from clear aligners due to mechanical friction. This evidence may represent a great concern in the clinical practice since it could impact human general health.

Understanding the underestimated: Occurrence, distribution, and interactions of microplastics in the sediment and soil of China, India, and Japan

Microplastics (MPs) are non-biodegradable substances that can sustain our environment for up to a century. What is more worrying is the incapability of modern technologies to annihilate MPs from om environment. One ramification of MPs is their impact on every kind of life form on this planet, which has been discussed ahead; that is why these substances are surfacing in everyday discussions of scholars and researchers. This paper discusses the overview of the global occurrence, abundance, analysis, and remediation techniques of MPs in the environment. This paper primarily reviews the event and abundance of MPs in coastal sediments and agricultural soil of three major Asian countries, India, China, and Japan. A significant concentration of MPs has been recorded from these countries, which affirms its strong presence and subsequent environmental impacts. Concentrations such as 73,100 MPs/kg in Indian coastal sediments and 42,960 particles/kg in the agricultural soil of China is a solid testimony to prove their massive outbreak in our environment and require urgent attention towards this issue. Conclusions show that human activities, rivers, and plastic mulching on agricultural fields have majorly acted as carriers of MPs towards coastal and terrestrial soil and sediments. Later, based on recorded concentrations and gaps, future research studies are recommended in the concerned domain; a dearth of studies on MPs influencing Indian agricultural soil make a whole sector and its consumer vulnerable to the adverse effects of this emerging contaminant.

A Critical Review on Artificial Intelligence-Based Microplastics Imaging Technology: Recent Advances, Hot-Spots and Challenges

Due to the rapid artificial intelligence technology progress and innovation in various fields, this research aims to use science mapping tools to comprehensively and objectively analyze recent advances, hot-spots, and challenges in artificial intelligence-based microplastic-imaging field from the Web of Science (2019-2022). By text mining and visualization in the scientific literature we emphasized some opportunities to bring forward further explication and analysis by (i) exploring efficient and low-cost automatic quantification methods in the appearance properties of microplastics, such as shape, size, volume, and topology, (ii) investigating microplastics water-soluble synthetic polymers and interaction with other soil and water ecology environments via artificial intelligence technologies, (iii) advancing efficient artificial intelligence algorithms and models, even including intelligent robot technology, (iv) seeking to create and share robust data sets, such as spectral libraries and toxicity database and co-operation mechanism, (v) optimizing the existing deep learning models based on the readily available data set to balance the related algorithm performance and interpretability, (vi) facilitating Unmanned Aerial Vehicle technology coupled with artificial intelligence technologies and data sets in the mass quantities of microplastics. Our major findings were that the research of artificial intelligence methods to revolutionize environmental science was progressing toward multiple cross-cutting areas, dramatically increasing aspects of the ecology of plastisphere, microplastics toxicity, rapid identification, and volume assessment of microplastics. The above findings can not only determine the characteristics and track of scientific development, but also help to find suitable research opportunities to carry out more in-depth research with many problems remaining.