Assessment of machine learning-based methods predictive suitability for migration pollutants from microplastics degradation

Predicting microplastic quantities in Indonesian provincial rivers using machine learning models

Microplastic pollution has surfaced as a critical environmental concern, affecting ecosystems and human health globally. This study explored the application of several machine learning models, including the Tree algorithm, k-Nearest Neighbors (kNN), Random Forest (RF), Linear Regression (LR), Support Vector Machine (SVM), and Neural Networks (NN), to predict microplastic concentrations in the rivers of Indonesia's 24 provinces. By utilizing both environmental and anthropogenic data, the Tree algorithm exhibited the best performance, achieving a coefficient of determination (R2) of 0.838 and a mean absolute percentage error (MAPE) of 0.242 on unseen testing data, thereby highlighting strong predictive capability. Key variables influencing microplastic abundance included annual average temperature, gross domestic product (GDP) per capita and population density. The results underscored the necessity of utilizing comprehensive datasets for effective modeling and highlighted the potential of machine learning to enhance environmental monitoring efforts. This research provides critical insights for policymakers and stakeholders aiming to address the growing issue of microplastic pollution in freshwater systems, providing a foundation for the development of more effective environmental management strategies.

Aging of plastics and microplastics in the environment: a review on influencing factors, quantification methods, challenges, and future perspectives

The ubiquitous presence of fragmented plastic particles needs comprehensive understanding of its fate in the environment. The long-term persistence of microplastics (MPs) in the environment is a significant threat to the ecosystem. Even though various degradation mechanisms (physical, chemical, and biological) of commonly used plastics have been demonstrated, quantifying the degradation of MPs over time to predict the consequence of plastic littering and its persistence in the environment remains a challenge. Different advanced analytical techniques have been used to quantify the degradation of MPs by introducing various parameters such as bond indices, crystallinity, and carbon-oxygen ratio. However, a simple and widely accepted reliable methodology for comparing the environmental factors and their influence on the MP degradation has yet to be developed and validated. This paper reviews a section of relevant literature (n = 38) to synthesize an overview of methods implemented for the quantification of fragmentation and aging of MPs in natural and artificial environment. In addition, the inherent weakness and extrinsic factors affecting the degradation of MPs in the environment is discussed. Finally, it proposes challenges and future scope as guideline for research on MP degradation in the environment.

Plastic additives as a new threat to the global environment: Research status, remediation strategies and perspectives

Discharge or leaching of plastic additives, which are an essential part of the plastic production process, can lead to environmental pollution with serious impacts on human and ecosystem health. Recently, the emission of plastic additives is increasing dramatically, but its pollution condition has not received enough attention. Meanwhile, the effective treatment strategy of plastic additive pollution is lack of systematic introduction. Therefore, it is crucial to analyze the harm and pollution status of plastic additives and explore effective pollution control strategies. This paper reviews the latest research progress on additives in plastics, describes the effects of their migration into packaged products and leaching into the environment, presents the hazards of four major classes of plastic additives (i.e., plasticizers, flame retardants, stabilizers, and antimicrobials), summarizes the existing abiotic/biotic strategies for accelerated the remediation of additives, and finally provides perspectives on future research on the removal of plastic additives. To the best of our knowledge, this is the first review that systematically analyzes strategies for the treatment of plastic additives. The study of these strategies could (i) provide feasible, cost-effective abiotic method for the removal of plastic additives, (ii) further enrich the current knowledge on plastic additive bioremediation, and (iii) present application and future development of plants, invertebrates and machine learning in plastic additive remediation.

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.

Environmental occurrence and ecotoxicological risks of plastic leachates in aquatic and terrestrial environments

Plastic pollution poses a significant threat to environmental and human health, with microplastics widely distributed across various ecosystems. Although current ecotoxicological studies have primarily focused on the inherent toxicity of plastics in natural environments, the role of chemical additives leaching from plastics into the environment remains underexplored despite their significant contribution to the overall toxic potential of plastics. Existing systematic studies on plastic leachates have often examined isolated additive compounds, neglecting the ecotoxicological effects of multiple compounds present in plastic leachates. Additionally, most previous research has focused on aquatic environments, overlooking the leaching mechanisms and ecological risks to diverse species with various ecological roles in aquatic and terrestrial ecosystems. This oversight hinders comprehensive ecological risk assessments. This study addresses these research gaps by reviewing the environmental occurrence of plastic leachates and their ecotoxicological impacts on aquatic and terrestrial ecosystems. Key findings reveal the pervasive presence of plastic leachates in various environments, identifying common additives such as phthalates, polybrominated diphenyl ethers (PBDEs), bisphenol A (BPA), and nonylphenols (NPs). Ecotoxicologically, chemical additives leaching from plastics under specific environmental conditions can influence their bioavailability and subsequent uptake by organisms. This review proposes a novel ecotoxicity risk assessment framework that integrates chemical analysis, ecotoxicological testing, and exposure assessment, offering a comprehensive approach to evaluating the risks of plastic leachates. This underscores the importance of interdisciplinary research that combines advanced analytical techniques with ecotoxicological studies across diverse species and environmental conditions to enhance the understanding of the complex impacts of plastic leachates and inform future research and regulatory policies.

A review on advancements in atmospheric microplastics research: The pivotal role of machine learning

Microplastics (MPs), recognized as emerging pollutants, pose significant potential impacts on the environment and human health. The investigation into atmospheric MPs is nascent due to the absence of effective characterization methods, leaving their concentration, distribution, sources, and impacts on human health largely undefined with evidence still emerging. This review compiles the latest literature on the sources, distribution, environmental behaviors, and toxicological effects of atmospheric MPs. It delves into the methodologies for source identification, distribution patterns, and the contemporary approaches to assess the toxicological effects of atmospheric MPs. Significantly, this review emphasizes the role of Machine Learning (ML) and Artificial Intelligence (AI) technologies as novel and promising tools in enhancing the precision and depth of research into atmospheric MPs, including but not limited to the spatiotemporal dynamics, source apportionment, and potential health impacts of atmospheric MPs. The integration of these advanced technologies facilitates a more nuanced understanding of MPs' behavior and effects, marking a pivotal advancement in the field. This review aims to deliver an in-depth view of atmospheric MPs, enhancing knowledge and awareness of their environmental and human health impacts. It calls upon scholars to focus on the research of atmospheric MPs based on new technologies of ML and AI, improving the database as well as offering fresh perspectives on this critical issue.

Migration and Accumulation Simulation Prediction of PPCPs in Urban Green Space Soil Irrigated with Recycled Water: A Review

The presence of pharmaceuticals and personal care products (PPCPs) in reclaimed water introduces an ongoing challenge as they infiltrate green space soils during irrigation, leading to a gradual buildup that poses considerable ecological risks. The simulation and forecasting of PPCPs accumulation in soil are pivotal for proactive ecological risk management. However, the majority of research efforts have predominantly concentrated on the vertical transport mechanisms of PPCPs in the soil, neglecting a holistic perspective that integrates both vertical and lateral transport phenomena, alongside accumulation dynamics. To address this gap, this study introduces a comprehensive conceptual model that encapsulates the dual processes of vertical and lateral transport, coupled with accumulation of PPCPs in the soil environment. Grounded in the distinctive properties of green space soils, we delve into the determinants governing the vertical and lateral migration of PPCPs. Furthermore, we consolidate existing simulation methodologies for contaminant transport, aiming to establish a comprehensive model that accurately predicts PPCPs accumulation in green space soils. This insight is critical for deducing the emission threshold of reclaimed water necessary for the protection of green space soils, informing the formulation of rational irrigation strategies, and anticipating future environmental risks. It provides a critical theoretical basis for more informed decision-making in the realm of urban water reuse and pollution control.

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.

Modeling of microplastics degradation in aquatic environments using an experimental plan

The aim of this article is to apply advanced predictive modeling techniques to understand the degradation process of microplastics in aquatic environments. Utilizing a Fractional Factorial Central Composite Experimental Plan, this study seeks to develop precise predictive statistical models that enable forecasting the quantity of pollutants generated during the degradation of microplastics under various environmental conditions. This tool was applied to model changes in DOC (dissolved organic carbon) and DEHP (bis(2-ethylhexyl) phthalate) values during the degradation of microplastics in aquatic ecosystems. The methods were developed using data derived from laboratory tests conducted using the GC-MS technique. The obtained approximating functions, considering factors such as degradation time, water temperature, and particle size, significantly reduced the analysis time. A two-stage verification of the approximating functions was conducted, considering the accuracy of the function form, its adequacy, the statistical significance of input variables, and their correlation with DOC and DEHP. The employed a Fractional Factorial Central Composite Experimental Plan allowed for the simultaneous reduction in the number of experiments and prediction of the influence of variables on the output values. Precise predictive models support understanding of the microplastic degradation process, facilitating the development of effective strategies for managing this pollution.

Exploring pollutant joint effects in disease through interpretable machine learning

Identifying the impact of pollutants on diseases is crucial. However, assessing the health risks posed by the interplay of multiple pollutants is challenging. This study introduces the concept of Pollutants Outcome Disease, integrating multidisciplinary knowledge and employing explainable artificial intelligence (AI) to explore the joint effects of industrial pollutants on diseases. Using lung cancer as a representative case study, an extreme gradient boosting predictive model that integrates meteorological, socio-economic, pollutants, and lung cancer statistical data is developed. The joint effects of industrial pollutants on lung cancer are identified and analyzed by employing the SHAP (Shapley Additive exPlanations) interpretable machine learning technique. Results reveal substantial spatial heterogeneity in emissions from CPG and ILC, highlighting pronounced nonlinear relationships among variables. The model yielded strong predictions (an R of 0.954, an RMSE of 4283, and an R2 of 0.911) and emphasized the impact of pollutant emission amounts on lung cancer responses. Diverse joint effects patterns were observed, varying in terms of patterns, regions (frequency), and the extent of antagonistic and synergistic effects among pollutants. The study provides a new perspective for exploring the joint effects of pollutants on diseases and demonstrates the potential of AI technology to assist scientific discovery.

Insight into microplastics in the aquatic ecosystem: Properties, sources, threats and mitigation strategies

Globally recognized as emergent contaminants, microplastics (MPs) are prevalent in aquaculture habitats and subject to intense management. Aquaculture systems are at risk of microplastic contamination due to various channels, which worsens the worldwide microplastic pollution problem. Organic contaminants in the environment can be absorbed by and interact with microplastic, increasing their toxicity and making treatment more challenging. There are two primary sources of microplastics: (1) the direct release of primary microplastics and (2) the fragmentation of plastic materials resulting in secondary microplastics. Freshwater, atmospheric and marine environments are also responsible for the successful migration of microplastics. Until now, microplastic pollution and its effects on aquaculture habitats remain insufficient. This article aims to provide a comprehensive review of the impact of microplastics on aquatic ecosystems. It highlights the sources and distribution of microplastics, their physical and chemical properties, and the potential ecological consequences they pose to marine and freshwater environments. The paper also examines the current scientific knowledge on the mechanisms by which microplastics affect aquatic organisms and ecosystems. By synthesizing existing research, this review underscores the urgent need for effective mitigation strategies and further investigation to safeguard the health and sustainability of aquatic ecosystems.

Deep convolutional neural networks for aged microplastics identification by Fourier transform infrared spectra classification

Infrared (IR) spectroscopy is a powerful technique for detecting and identifying Microplastics (MPs) in the environment. However, the aging of MPs presents a challenge in accurately identification and classification. To address this challenge, a classification model based on deep convolutional neural networks (CNNs) was developed using infrared spectra results. Particularly, original infrared (IR) spectra were used as the sample dataset, therefore, relevant spectral details were preserved and additional noise or distortions were not introduced. The Adam (Adaptive moment estimation) algorithm was employed to accelerate gradient descent and weight update, the Dropout function was implemented to prevent overfitting and enhance the generalization performance of the network. An activation function ReLu (Rectified Linear Unit) was also utilized to simplify the co-adaptation relationship among neurons and prevent gradient disappearance. The performance of the CNN model in MPs classification was evaluated based on accuracy and robustness, and compared with other machine learning techniques. CNN model demonstrated superior capabilities in feature extraction and recognition, and greatly simplified the pre-processing procedure. The identification results of aged commercial microplastic samples showed accuracies of 40 % for Artificial Neural Network, 60 % for Random Forest, 80 % for Deep Neural Network, and 100 % for CNN, respectively. The CNN architecture developed in this work also demonstrates versatility by being suitable for both limited data cases and potential expansion to include more discrete data in the future.