Machine learning prediction and interpretation of the impact of microplastics on soil properties

Automatic pre-screening of outdoor airborne microplastics in micrographs using deep learning

Airborne microplastics (AMPs) are prevalent in both indoor and outdoor environments, posing potential health risks to humans. Automating the process of identifying potential particles in micrographs can significantly enhance the research and monitoring of AMPs. Although deep learning has shown substantial promise in microplastics analysis, existing studies have primarily focused on high-resolution images of samples collected from marine and freshwater environments. In contrast, this work introduces a novel approach by employing enhanced U-Net models (Attention U-Net and Dynamic RU-NEXT) along with the Mask Region Convolutional Neural Network (Mask R-CNN) to identify and classify outdoor AMPs in low-resolution micrographs (256 × 256 pixels). A key innovation involves integrating classification directly within the U-Net-based segmentation frameworks, thereby streamlining the workflow and improving computational efficiency. This marks an advancement over previous work where segmentation and classification were performed separately. The enhanced U-Net models attained average classification F1-scores exceeding 85% and segmentation accuracy above 77% on test images. Additionally, the Mask R-CNN model achieved an average bounding box precision of 73.32%, a classification F1-score of 84.29%, and a mask precision of 71.31%. The proposed method provides a faster and more accurate means of identifying AMPs compared to thresholding techniques. It also functions effectively as a pre-screening tool, substantially reducing the number of particles requiring labour-intensive chemical analysis. By integrating advanced deep learning strategies into AMPs research, this study paves the way for more efficient monitoring and characterisation of microplastics.

Exploring the response of bacterial community functions to microplastic features in lake ecosystems through interpretable machine learning

Microplastics (MPs) are ubiquitous and have various characteristics. However, their impacts on bacterial community functions in lakes remain elusive. In this study, we identified 33 different MPs features including their abundance, shape, color, size, and polymer type, from Taihu Lake, China. These features were used to construct 48 machine learning models, utilizing four types of machine learning regression algorithms, to investigate how different MP features influence human health, carbon/nitrogen cycling, and energy source-related functions of bacterial communities. The XGBoost models provided the best performance with an average R2 of 0.85 in explaining the abundance of functions. Yellow-, fragment-, and polyethylene terephthalate (PET) MPs were the most important features by Shapley values. Yellow- and PET-MPs mainly had primarily negative impacts on human pathogens pneumonia and chemoheterotrophy, respectively. Fragment-MPs had a primarily positive impact, which shifted from positive to negative at a proportion of 0.5 for methanol oxidation. Moreover, MPs may affect community structure by filtering for functional traits. These findings are important for understanding the effects of MP pollution on bacterial community function and its role in the global carbon and nitrogen cycling and human health and help us to determine the potential impacts of MP pollution on ecosystems.

Are we underestimating the driving factors and potential risks of freshwater microplastics from in situ and in silico perspective?

The high loads of heterogeneous microplastics (MPs) in water system sparked the exploration of MPs source and impact in the environment. However, the contributions of driving factors to MPs contamination and the potential risks posed by multidimensional characteristics are still poorly understood. By incorporating in situ investigation with machine learning predictions, this study reported widespread MPs contamination in both textile upstream and receiving watershed in the Yangtze River Delta. The dominant MPs categories were fibers (0.1-0.5 mm in size), transparent in color, and composed of polyethylene terephthalate. These morphological characteristics indicated a conditional fragmentation process, suggesting that larger MPs are more prone to fragmentation. Multivariable analysis revealed significant correlations between MPs occurrence and factors of metal concentrations, geographic locations, and water qualities, highlighting the roles of textile production and automotive tire wear in determining MPs abundance. Among five machine learning models, Random Forest outperformed others in predicting MPs abundance. The interpretable analysis indicated that longitude (35.3 %), TN (13.8 %) and Sb (13.4 %) were pivotal nodes in shaping the MPs abundance. Emission point sources from express, autotire and textile yield feature importance from 6.60 % to 7.88 %. A total 12.39 % of the predicted variability can be further explained by interaction effects. Besides, MPERI and MultiMP indices based on abundance, size, color, shape, and polymer distributions suggested that most sampling sites fell within moderate to high-risk categories. Artificial neural network-based assessment results are suitable for explaining the MPs induced risks and polymer type was the most influential variable in determining the risk values. These quantitative insights into the driving factors and potential risks behind MPs occurrence improve our knowledge to manage MPs pollution in large-scale watersheds, providing crucial information for the development of effective mitigation strategies.

Microplastics in agricultural soils: sources, impacts on soil organisms, plants, and humans

Agricultural land has long been regarded as a resource for food production, but over time, the effects of climate change have reduced the ability of soil to produce food efficiently. Nowadays, farmers have moved from traditional to modern techniques of farming. Across the globe, plastic mulching has become widely used on farmlands. According to a few studies, the breakdown of plastic mulches releases microplastics (MPs) into the soil. Despite studies reporting the presence of MPs in soils, there are limited studies on the sources and impacts on soil organisms, plant growth, fruits, and human health. This study evaluated research articles collected from the Web of Science to assess the origin of MP in soil and crops and its effects on soil organisms, plants, and humans. It was observed that MPs come from different sources such as waste water, organic fertilizer, irrigation water, sewage, and sludge. Plastic mulching, which can spread across agricultural fields at varying depths, is the dominant source. Furthermore, it was observed that MPs alter crop quality, reduce the leaf count of wheat, and decrease the root length of crops such as maize, water spinach, black gram, and garden cress. MP can decrease the abundance of soil microarthropods and nematodes, damage the intestinal walls of earthworms, and reduce the feeding and excretion of snails. MP causes liver damage, inflammation, respiratory irritation, and immunological issues. Ultimately, these contaminants (MPs) can transfer and have been detected in fruits and vegetables, which pose adverse effects on human health.

Microplastics influencing aquatic environment and human health: A review of source, determination, distribution, removal, degradation, management strategy and future perspective

Microplastics (MPs) are produced from various primary and secondary sources and pose multifaceted environmental problems. They are of non-biodegradable nature and may stay in aquatic environments for a long time period. The present review has covered novel aspects pertaining to MPs that were not covered in earlier studies. It has been observed that several methods are being employed for samples collection, extraction and identification of MPs and polymer types using various equipment, chemicals and instrumental techniques. Aquatic species mistakenly ingest MPs, considering them prey and through food-chain, and then suffer from various metabolic disorders. The consumption of seafood and fish may consequently cause health implications in humans. Certain plasticizers are added during manufacturing to provide colour, durability, flexibility, and strength to plastics, but they leach out during usage, storage, and transport, as well as after entering the bodies of aquatic species and human beings. The leached chemicals (bisphenol-A, triclosan, phthalates, etc.) act as endocrine disrupting chemicals (EDCs), which effect on homeostasis; thereby causing neurotoxicity, cytotoxicity, reproductive problems, adverse behaviour and autism. Negative influence of MPs on carbon sequestration potential of water bodies is also observed, however more studies are required to understand it with a detail mechanism under natural conditions. The wastewater treatment plants are found to remove a large amount of MPs, but in turn, also act as significant sources of their release in sludge and effluents. Further, it is covered that how advanced oxidation processes, thermal- and photo-oxidation, fungi, algae and microbes degrade the plastics and increase their numbers in the surrounding environment. The management strategy comprising recovery of energy and other valuable by-products from plastic wastes, recycling and regulatory framework; are also described in detail. The future perspectives can be of paramount importance to control MPs generation and their abundance in the aquatic and other types of environments. The studies in future need to focus on advanced filtration techniques, advanced oxidation processes, energy recovery from plastic wastes and influences of MPs on carbon sequestration in aquatic environment and human health.

Unveiling the mechanism of micro-and-nano plastic phytotoxicity on terrestrial plants: A comprehensive review of omics approaches

Micro-and-nano plastics (MNPs) are pervasive in terrestrial ecosystems and represent an increasing threat to plant health; however, the mechanisms underlying their phytotoxicity remain inadequately understood. MNPs can infiltrate plants through roots or leaves, causing a range of toxic effects, including inhibiting water and nutrient uptake, reducing seed germination rates, and impeding photosynthesis, resulting in oxidative damage within the plant system. The effects of MNPs are complex and influenced by various factors including size, shape, functional groups, and concentration. Recent advancements in omics technologies such as proteomics, metabolomics, transcriptomics, and microbiomics, coupled with emerging technologies like 4D omics, phenomics, spatial transcriptomics, and single-cell omics, offer unprecedented insight into the physiological, molecular, and cellular responses of terrestrial plants to MNPs exposure. This literature review synthesizes current findings regarding MNPs-induced phytotoxicity, emphasizing alterations in gene expression, protein synthesis, metabolic pathways, and physiological disruptions as revealed through omics analyses. We summarize how MNPs interact with plant cellular structures, disrupt metabolic processes, and induce oxidative stress, ultimately affecting plant growth and productivity. Furthermore, we have identified critical knowledge gaps and proposed future research directions, highlighting the necessity for integrative omics studies to elucidate the complex pathways of MNPs toxicity in terrestrial plants. In conclusion, this review underscores the potential of omics approaches to elucidate the mechanisms of MNPs-phytotoxicity and to develop strategies for mitigating the environmental impact of MNPs on plant health.

Polyethylene microplastics distinctly affect soil microbial community and carbon and nitrogen cycling during plant litter decomposition

Plant litter is an important input source of carbon and nitrogen in soil. While microplastics (MPs) and plant litter are ubiquitously present in soil, their combined impact on soil biogeochemical processes remains poorly understood. To address this gap, we examined the soil changes resulting from the coexistence of plant litter (Alfalfa) and polyethylene microplastics (PE). The soil changes included physicochemical properties, composition of soil dissolved organic matter, and structure of the soil microbial community. The results showed that the addition of polyethylene (PE) inhibited the degradation of humus-like substances and decreased the quantity of humic acid-like compounds in soil dissolved organic matter (DOM). PE negatively impacted plant litter decomposition, disrupted soil organic carbon (SOC) breakdown, interfered with the nitrogen cycle, and significantly altered microbial community structures during the process. By day 35, SOC and total nitrogen (TN) levels were reduced by 39.8% and 10.1%, respectively, in the presence of PE. Furthermore, PE significantly decreased the abundance of nitrogen-fixing microbes, including Streptomyces (43.1%) and Bacillus (45.9%), which play key roles in nitrate reduction to ammonium. This study highlights the environmental effects of MPs on plant litter decomposition and their potential implications for soil biogeochemical processes.

Machine learning-based prediction and model interpretability analysis for algal growth affected by microplastics

Microplastics (MPs), the plastic debris smaller than 5 mm, are ubiquitous in waterbodies and have been shown to be toxic to aquatic organisms, especially to microalgae. The aim of this study is to use machine learning models to predict the effects of MPs on algal growth and to evaluate the relative importance of different features (MP properties, algal characteristics, and experimental conditions) through model interpretability analysis. Based on literature search, 408 samples were collected as inputs for the models. Three integrated machine learning algorithms, Random Forest (RF), Categorical Boosting (CatBoost), and Light Gradient Boosting Machine (LightGBM), were used to construct classification prediction models for algal growth. Our results show that the LightGBM model yields the best performance, with a total accuracy rate of 0.8305 and a Kappa value of 0.7165. The model interpretability analysis indicates that "Exposure time", "MP concentrations", and "MP size" are the most influential features affecting algal growth. For "Exposure time", which belongs to experimental conditions, 72-216 h of MP exposure was found to exert the greatest effects on algal growth. The impact of MPs on algal growth increases with increasing MP concentrations over the range of 0 to 300 mg/L. Smaller MPs exert more effects on algal growth, and MPs are more likely to inhibit algal growth when the ratio of algal cell size to MP size is higher. Our study successfully established prediction models for evaluating the effects of various MP properties on algal growth. This study also provides insights into the prediction of MP toxicity in organisms.

Impact of microplastics on plant physiology: A meta-analysis of dose, particle size, and crop type interactions in agricultural ecosystems

The increasing prevalence of plastic pollution has led to widespread environmental concerns, particularly with microplastics (MPs) that persist in various ecosystems. As MPs accumulate in terrestrial environments, their potential impact on plant health and agricultural productivity has become a growing area of focus. This study presents a comprehensive meta-analysis evaluating the effects of MPs on plant physiological and biochemical parameters, synthesizing data from 37 studies comprising 2886 observations. Our findings indicate that MPs significantly decrease plant biomass by 13 % (95 % CI: 7-19 %) and chlorophyll content by 28 % (95 % CI: 23-34 %), impairing crop growth and quality. Notably, higher doses and smaller MP particle sizes exert more pronounced inhibitory effects, particularly on root activity and biomass, while larger MPs predominantly damage plant roots. Furthermore, MPs were found to significantly increase oxidative stress in plants, evidenced by a 20 % rise in oxidative damage (95 % CI: 15-25 %) and a 14 % increase in antioxidant capacity (95 % CI: 8-19 %). This study highlights intricate interactions between MP type, particle size, dose, and plant species, with particle size having a greater impact than dose. This study emphasizes the importance of accounting for crop diversity and environmental factors to fully elucidate the potential risks posed by MP pollution to agricultural ecosystems.

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.

Do Added Microplastics, Native Soil Properties, and Prevailing Climatic Conditions Have Consequences for Carbon and Nitrogen Contents in Soil? A Global Data Synthesis of Pot and Greenhouse Studies

Microplastics threaten soil ecosystems, strongly influencing carbon (C) and nitrogen (N) contents. Interactions between microplastic properties and climatic and edaphic factors are poorly understood. We conducted a meta-analysis to assess the interactive effects of microplastic properties (type, shape, size, and content), native soil properties (texture, pH, and dissolved organic carbon (DOC)) and climatic factors (precipitation and temperature) on C and N contents in soil. We found that low-density polyethylene reduced total nitrogen (TN) content, whereas biodegradable polylactic acid led to a decrease in soil organic carbon (SOC). Microplastic fragments especially depleted TN, reducing aggregate stability, increasing N-mineralization and leaching, and consequently increasing the soil C/N ratio. Microplastic size affected outcomes; those <200 μm reduced both TN and SOC contents. Mineralization-induced nutrient losses were greatest at microplastic contents between 1 and 2.5% of soil weight. Sandy soils suffered the highest microplastic contamination-induced nutrient depletion. Alkaline soils showed the greatest SOC depletion, suggesting high SOC degradability. In low-DOC soils, microplastic contamination caused 2-fold greater TN depletion than in soils with high DOC. Sites with high precipitation and temperature had greatest decrease in TN and SOC contents. In conclusion, there are complex interactions determining microplastic impacts on soil health. Microplastic contamination always risks soil C and N depletion, but the severity depends on microplastic characteristics, native soil properties, and climatic conditions, with potential exacerbation by greenhouse emission-induced climate change.

Earth at risk: An urgent call to end the age of destruction and forge a just and sustainable future

Human development has ushered in an era of converging crises: climate change, ecological destruction, disease, pollution, and socioeconomic inequality. This review synthesizes the breadth of these interwoven emergencies and underscores the urgent need for comprehensive, integrated action. Propelled by imperialism, extractive capitalism, and a surging population, we are speeding past Earth's material limits, destroying critical ecosystems, and triggering irreversible changes in biophysical systems that underpin the Holocene climatic stability which fostered human civilization. The consequences of these actions are disproportionately borne by vulnerable populations, further entrenching global inequities. Marine and terrestrial biomes face critical tipping points, while escalating challenges to food and water access foreshadow a bleak outlook for global security. Against this backdrop of Earth at risk, we call for a global response centered on urgent decarbonization, fostering reciprocity with nature, and implementing regenerative practices in natural resource management. We call for the elimination of detrimental subsidies, promotion of equitable human development, and transformative financial support for lower income nations. A critical paradigm shift must occur that replaces exploitative, wealth-oriented capitalism with an economic model that prioritizes sustainability, resilience, and justice. We advocate a global cultural shift that elevates kinship with nature and communal well-being, underpinned by the recognition of Earth's finite resources and the interconnectedness of its inhabitants. The imperative is clear: to navigate away from this precipice, we must collectively harness political will, economic resources, and societal values to steer toward a future where human progress does not come at the cost of ecological integrity and social equity.

Elucidating the impacts of microplastics on soil greenhouse gas emissions through automatic machine learning frameworks

With the rise in global plastic production and agricultural demand, the released microplastics (MPs) have increasingly influenced the elemental cycles of soils, leading to notable effects on greenhouse gas emissions. Despite initial research, there remains a gap in establishing a detailed modeling approach that comprehensively explores the impacts of MPs on GHG emissions. Herein, we utilized literature mining to assemble a comprehensive dataset examining the interplays between MPs and emissions of CO2, CH4, and N2O. Five automated machine learning frameworks were employed for predictive modeling. The GAMA framework was particularly effective in predicting CO2 (Q2 = 0.946) and CH4 (Q2 = 0.991) emissions. The Autogluon framework provided the most accurate prediction for N2O emission, though it exhibited signs of overfitting. Interpretability analysis indicated that the type of MPs significantly influenced CO2 emission. Degradable MPs (i.e., polyamide) inherently led to elevated CO2 emission, and the environmental aging further exacerbated this effect. Although both linear and nonlinear correlations between MPs and CH₄ emission were not identified, the incorporation of specific MPs that elevate soil pH, augment soil water retention, and cultivate anaerobic conditions may potentially elevate soil CH₄ emission. This research underscores the profound influence of MPs on soil GHG emissions, providing vital insights for shaping agricultural policies and soil management practices in the context of escalating plastic use.