Machine Learning to Predict the Adsorption Capacity of Microplastics

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.

Adsorption behavior and mechanism of heavy metals onto microplastics: A meta-analysis assisted by machine learning

Microplastics (MPs) have the potential to adsorb heavy metals (HMs), resulting in a combined pollution threat in aquatic and terrestrial environments. However, due to the complexity of MP/HM properties and experimental conditions, research on the adsorption of HMs onto MPs often yields inconsistent findings. To address this issue, we conducted a comprehensive meta-analysis assisted with machine learning by analyzing a dataset comprising 3340 records from 134 references. The results indicated that polyamide (PA) (ES = -1.26) exhibited the highest adsorption capacity for commonly studied HMs (such as Pb, Cd, Cu, and Cr), which can be primarily attributed to the presence of C=O and N-H groups. In contrast, polyvinyl chloride (PVC) demonstrated a lower adsorption capacity, but the strongest adsorption strength resulting from the halogen atom on its surface. In terms of HMs, metal cations were more readily adsorbed by MPs compared with metalloids and metal oxyanions, with Pb (ES = -0.78) exhibiting the most significant adsorption. As the pH and temperature increased, the adsorption of HMs initially increased and subsequently decreased. Using a random forest model, we accurately predicted the adsorption capacity of MPs based on MP/HM properties and experimental conditions. The main factors affecting HM adsorption onto MPs were HM and MP concentrations, specific surface area of MP, and pH. Additionally, surface complexation and electrostatic interaction were the predominant mechanisms in the adsorption of Pb and Cd, with surface functional groups being the primary factors affecting the mechanism of MPs. These findings provide a quantitative summary of the interactions between MPs and HMs, contributing to our understanding of the environmental behavior and ecological risks associated with their correlation.

How many microplastics do you need to (sub)sample?

Analysis of microplastics in the environment requires polymer characterization as a confirmation step for suspected microplastic particles found in a sample. Material characterization is costly and can take a long time per particle. When microplastic particle counts are high, many researchers cannot characterize every particle in their sample due to time or monetary constraints. Moreover, characterizing every particle in samples with high plastic particle counts is unnecessary for describing the sample properties. We propose an a priori approach to determine the number of suspected microplastic particles in a sample that should be randomly subsampled for characterization to accurately assess the polymer distribution in the environmental sample. The proposed equation is well-founded in statistics literature and was validated using published microplastic data and simulations for typical microplastic subsampling routines. We report values from the whole equation but also derive a simple way to calculate the necessary particle count for samples or subsamples by taking the error to the power of negative two. Assuming an error of 0.05 (5 %) with a confidence interval of 95 %, an unknown expected proportion, and a sample with many particles (> 100k), the minimum number of particles in a subsample should be 386 particles to accurately characterize the polymer distribution of the sample, given the particles are randomly characterized from the full population of suspected particles. Extending this equation to simultaneously estimate polymer, color, size, and morphology distributions reveals more particles (620) would be needed in the subsample to achieve the same high absolute error threshold for all properties. The above proposal for minimum subsample size also applies to the minimum count that should be present in samples to accurately characterize particle type presence and diversity in a given environmental compartment.

The adsorption and release mechanism of different aged microplastics toward Hg(II) via batch experiment and the deep learning method

Aged microplastics are ubiquitous in the aquatic environment, which inevitably accumulate metals, and then alter their migration. Whereas, the synergistic behavior and effect of microplastics and Hg(II) were rarely reported. In this context, the adsorptive behavior of Hg(II) by pristine/aged microplastics involving polystyrene, polyethylene, polylactic acid, and tire microplastics were investigated via kinetic (pseudo-first and second-order dynamics, the internal diffusion model), Langmuir, and Freundlich isothermal models; the adsorption and desorption behavior was also explored under different conditions. Microplastics aged by ozone exhibited a rougher surface attached with abundant oxygen-containing groups to enhance hydrophilicity and negative surface charge, those promoted adsorption capacity of 4-20 times increment compared with the pristine microplastics. The process (except for aged tire microplastics) was dominated by a monolayer chemical reaction, which was significantly impacted by pH, salinity, fulvic acid, and co-existing ions. Furthermore, the adsorbed Hg(II) could be effectively eluted in 0.04% HCl, simulated gastric liquids, and seawater with a maximum desorption amount of 23.26 mg/g. An artificial neural network model was used to predict the performance of microplastics in complex media and accurately capture the main influencing factors and their contributions. This finding revealed that aged microplastics had the affinity to trap Hg(II) from freshwater, whereafter it released the Hg(II) once transported into the acidic medium, the organism's gastrointestinal system, or the estuary area. These indicated that aged microplastics could be the sink or the source of Hg(II) depending on the surrounding environment, meaning that aged microplastics could be the vital carrier to Hg(II).

Photo-oxidation of Micro- and Nanoplastics: Physical, Chemical, and Biological Effects in Environments

Micro- and nanoplastics (MNPs) are attracting increasing attention due to their persistence and potential ecological risks. This review critically summarizes the effects of photo-oxidation on the physical, chemical, and biological behaviors of MNPs in aquatic and terrestrial environments. The core of this paper explores how photo-oxidation-induced surface property changes in MNPs affect their adsorption toward contaminants, the stability and mobility of MNPs in water and porous media, as well as the transport of pollutants such as organic pollutants (OPs) and heavy metals (HMs). It then reviews the photochemical processes of MNPs with coexisting constituents, highlighting critical factors affecting the photo-oxidation of MNPs, and the contribution of MNPs to the phototransformation of other contaminants. The distinct biological effects and mechanism of aged MNPs are pointed out, in terms of the toxicity to aquatic organisms, biofilm formation, planktonic microbial growth, and soil and sediment microbial community and function. Furthermore, the research gaps and perspectives are put forward, regarding the underlying interaction mechanisms of MNPs with coexisting natural constituents and pollutants under photo-oxidation conditions, the combined effects of photo-oxidation and natural constituents on the fate of MNPs, and the microbiological effect of photoaged MNPs, especially the biotransformation of pollutants.

Polystyrene microplastics induce size-dependent multi-organ damage in mice: Insights into gut microbiota and fecal metabolites

Particle size is one of the most important factors in determining the biological toxicity of microplastics (MPs). In this study, we attempted to examine the systemic toxicity of polystyrene MPs of different sizes (0.5 µm MP1 and 5 µm MP2) in C57BL/6 J mice. After the mice were given oral gavage of MPs for 8 consecutive weeks, histopathology and molecular biology assays, 16 S rRNA sequencing of the gut microbiota, and untargeted metabolomics were performed. The results showed that MPs were distributed in the organs in a size-dependent manner, with smaller particles demonstrating greater biodistribution. Further analysis indicated that exposure to MPs caused multi-organ damage through distinct toxicity pathways. Specifically, exposure to 0.5 µm MP1 led to excessive accumulation and induced more serious inflammation and mechanical damage in the spleen, kidney, heart, lung, and liver. However, 5 µm MP2 led to more severe intestinal barrier dysfunction, as well as gut dysbiosis and metabolic disorder in association with neuroinflammation. These results are helpful in expanding our knowledge of the toxicity of MPs of different sizes in mammalian models.

The use of artificial neural networks in modelling migration pollutants from the degradation of microplastics

The objective of this article was to assess the effectiveness of simulation models in predicting the emission of additives from microplastics. The variety of plastics, their chemical structure, physicochemical properties, as well as the influence of environmental factors on their decomposition generate countless cases for analysis in the laboratory. The search for methods to reduce unnecessary laboratory analyses is a necessary action to protect the environment and ensure economic efficiency. In this study, machine learning techniques, specifically the methodology of artificial neural networks (ANNs), were employed to predict the leaching of contaminants from microplastics. The network's development was based on laboratory test results obtained using gas chromatography coupled to a mass spectrometer (GC-MS). The conducted research revealed the significant utility of the multilayer perceptron (MLP) - type networks, which exhibited correlation levels exceeding 95 % for various predicted values. One comprehensive ANN was developed, encompassing all the parameters analyzed, alongside individual networks for each parameter. A common network for all factors enabled for satisfactory results. Temperature and holding time had the greatest influence on the values of parameters such as the electrolytic conductivity of water (EC), dissolved organic carbon (DOC), and di(2-ethylhexyl) phthalate (DEHP). Correlation results ranged from 0.94 to 0.99 for EC, DEHP and DOC between the model data and laboratory data in each set of training, test, and validation data. The conducted research demonstrated that ANNs are a valuable machine learning method for analyzing and predicting pollutant emissions during the decomposition of microplastics.

Unveiling the impact of short-term polyethylene microplastics exposure on metabolomics and gut microbiota in earthworms (Eudrilus euganiae)

Microplastics (MPs) pose a significant environmental concern, particularly for terrestrial fauna. In this study, earthworms were used as a model organism to investigate the ecotoxicological effects of short-term exposure to virgin MPs on changes in metabolome and gut microbiota. High-throughput untargeted metabolomics showed significant internal reactions in the earthworms' metabolic processes due to MPs exposure, even when no visible stress signs, such as changes in growth or mortality rates, were present. Earthworms exposed to different concentrations of polyethylene (PE) MP exhibited significant disruption in 39 and 199 molecular features related to energy and lipid metabolism, anti-inflammatory, cell signaling, and membrane integrity. The activities of enzymes and transport proteins in earthworms were dysregulated when exposed to PE. Changes in the gut microbiota's community structure and complexity were observed in response to PE MPs exposure. Despite the relative stability in alpha-diversity and relative abundance, shifts in beta-diversity and network analysis in the PE-exposed group were indicative of an adaptive response to MPs. Earthworms exhibited resilience or adaptation in response to MPs exposure, potentially maintaining their functionality. This study provides preliminary insights into the impact of MPs on soil invertebrates like earthworms and highlights the need for further exploration of long-term effects and underlying molecular mechanisms.

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.