Advancing environmental sustainability through emerging AI-based monitoring and mitigation strategies for microplastic pollution in aquatic ecosystems

 Corresponding author: Ifeanyi Kingsley Egbuna, Email: Copyright © 2025 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution License 4.0. Advancing environmental sustainability through emerging AI-based monitoring and mitigation strategies for microplastic pollution in aquatic ecosystems Ifeanyi Kingsley Egbuna 1, *, Mustapha Saidu 2, Khalid Hussain Ahmad 3, Paullett Ugochi Ogeah 4, Taiwo Bakare-Abidola 5, Aanuoluwa Temitayo Iyiola 6 and Abiola Bidemi Obafemi 7 1 Department of Supply Chain Management, Marketing, and Management, Raj Soin College of Business, Wright State University, United States. 2 Department of Biology, Sustainable Aquaculture, University of St Andrews, United Kingdom. 3 Department of Computer Science, Federal University Lokoja, Nigeria. 4 Department of Human Kinentics and Health Education, Ahmadu Bello University Zaria, Nigeria. 5 Department of Environmental Science, Georgia Southern University, Georgia, USA. 6 Department of Biochemistry, Federal University of Technology, Minna, Nigeria. 7 Department of Coastal Sciences, University of Southern Mississippi, USA. World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 Publication history: Received on 18 March 2025; revised on 29 April 2025; accepted on 01 May 2025 Article DOI: https://doi.org/10.30574/wjbphs.2025.22.2.0438 Abstract Microplastics have become a significant pollutant in aquatic ecosystems, with serious implications for biodiversity, food safety, and environmental sustainability. This paper reviews the nature and sources of microplastic pollution, alongside its ecological and human health impacts. Recognizing the limitations of traditional monitoring and removal methods, the study explores emerging artificial intelligence (AI)-based strategies as innovative tools for improving environmental monitoring and pollution mitigation. The manuscript discusses how AI techniques such as machine learning, computer vision, and remote sensing can enhance the detection, classification, and prediction of microplastic distribution in water bodies. It also highlights the potential of AI-driven robotic systems in supporting targeted mitigation efforts. While these technologies show promise, further interdisciplinary research and development are necessary to fully realize their application in real-world environmental management. The integration of AI offers a proactive path toward achieving cleaner aquatic ecosystems and supporting global sustainability goals. Keywords: Microplastic Pollution; Aquatic Ecosystems; Artificial Intelligence; Environmental Monitoring; Machine Learning; Computer Vision; Sustainability 1. Introduction Microplastic pollution in aquatic ecosystems is a critical environmental issue that has gained increasing attention over the past few decades. Defined as synthetic solid particles or polymeric materials measuring less than 5 millimeters in diameter, microplastics can be categorized into primary and secondary types [1]. Primary microplastics are intentionally manufactured for use in products such as cosmetics, cleaning products, and industrial abrasives. In contrast, secondary microplastics result from the breakdown of larger plastic debris through processes like photodegradation, mechanical wear, and chemical degradation. These particles are often too small to be efficiently filtered by water treatment plants, leading to their widespread distribution in marine and freshwater environments. The sources of microplastic pollution are extensive, ranging from synthetic fibers shed from clothing and textiles during washing, to plastic waste that degrades into smaller pieces over time. The persistence of these particles in aquatic World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 92 ecosystems, combined with their ability to accumulate and persist in the environment, presents significant challenges for both environmental sustainability and ecosystem health. The global environmental and ecological impact of microplastic pollution is profound and widespread. Aquatic organisms across various trophic levels are vulnerable to the ingestion of microplastics, which can lead to a range of harmful effects. For instance, smaller marine organisms, such as plankton, can mistake microplastic particles for food, which then enter the food chain. Studies have shown that microplastics can cause physical damage to the gastrointestinal systems of marine species, leading to internal abrasions, blockages, and reduced feeding efficiency [2]. Furthermore, the ingestion of microplastics can impair growth and reproduction in various aquatic organisms, threatening biodiversity and ecosystem services. In addition to these direct impacts, microplastics also act as vectors for persistent organic pollutants (POPs), which include chemicals such as pesticides and industrial compounds that adhere to the surface of plastic particles. These chemicals are then transported across the aquatic environment, potentially entering the food web and reaching human populations. The effects of microplastics are not confined to marine ecosystems alone; freshwater systems such as rivers and lakes are also increasingly contaminated, further exacerbating the scope of the problem [3]. This issue of microplastic pollution is intricately linked to the United Nations Sustainable Development Goals (SDGs), particularly Goal 14, which focuses on conserving and sustainably using the oceans, seas, and marine resources for sustainable development. Microplastic pollution directly threatens marine life by disrupting ecosystems, harming aquatic species, and compromising the health of marine environments. According to Jambeck et al. [4], the widespread presence of plastic waste in the oceans, which includes microplastics, has severe consequences for marine biodiversity and the livelihoods of coastal communities dependent on marine resources. Moreover, microplastic pollution also intersects with SDG 12, which calls for responsible consumption and production. The increasing prevalence of plastic products and their subsequent degradation into microplastics highlight the need for sustainable practices in plastic production, consumption, and disposal. Therefore, addressing microplastic pollution is crucial for achieving these SDGs and advancing global environmental sustainability efforts. Efforts to mitigate the impacts of microplastics align with the broader goals of protecting biodiversity, promoting the sustainable use of marine resources, and ensuring environmental health [2,3]. The role of Artificial Intelligence (AI) in addressing environmental challenges has been growing rapidly in recent years, offering new avenues for monitoring, analyzing, and mitigating pollution. AI technologies, such as machine learning, image recognition, and data analytics, are being increasingly applied in environmental science to enhance the efficiency and accuracy of pollution detection and management [5,6]. In the context of microplastic pollution, AI has demonstrated significant potential in revolutionizing environmental monitoring techniques. For instance, AI-powered image recognition systems can analyze large datasets of images from remote sensors and underwater cameras to identify microplastic particles, reducing the need for manual inspection and increasing the speed of data processing [7]. Machine learning algorithms can also be used to predict the movement and distribution of microplastics in aquatic ecosystems, helping to identify hotspots for targeted interventions. Furthermore, AI has the capacity to optimize waste management processes, by predicting and detecting microplastic sources and facilitating the development of mitigation strategies tailored to specific environments. The integration of AI in environmental science thus represents a transformative approach that can improve the effectiveness of monitoring systems and inform data-driven decision-making processes aimed at reducing microplastic pollution [6,7]. The purpose of this review is to explore the emerging role of AI-based monitoring and mitigation strategies in the fight against microplastic pollution in aquatic ecosystems, with a focus on advancing environmental sustainability. By synthesizing recent research, this review aims to provide a comprehensive overview of how AI technologies are being applied to monitor and manage microplastic pollution. This review will address the various sources of microplastics, their environmental impacts, and the innovative AI tools and techniques being utilized to address these challenges. Through this analysis, the review seeks to underscore the importance of interdisciplinary approaches, combining environmental science and AI, to effectively tackle the microplastic crisis and promote a more sustainable future. The scope of this review is to highlight the potential of AI in enhancing environmental sustainability through improved pollution monitoring, predictive modeling, and targeted mitigation efforts. 2. Microplastic Pollution in Aquatic Ecosystems: Current Landscape 2.1. Types and Classifications of Microplastics Microplastics, defined as plastic particles smaller than 5 mm in size, are classified into two major categories: primary and secondary microplastics. Primary microplastics are deliberately manufactured at microscopic sizes for specific World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 93 industrial applications [8]. These include microbeads, which are commonly used in cosmetics, personal care products, and cleaning agents, as well as microfibers shed from synthetic textiles such as polyester and nylon. They also encompass plastic pellets or "nurdles" used as raw material in the production of larger plastic items. The manufacturing process of these materials results in microplastics directly entering aquatic systems, contributing to their pervasive spread in the environment [8]. On the other hand, secondary microplastics result from the physical degradation and fragmentation of larger plastic debris over time. This fragmentation occurs through mechanical processes, photodegradation, and chemical weathering, which break down plastics into smaller and smaller particles [9]. Items such as plastic bottles, packaging, and fishing nets are common sources of secondary microplastics. These microplastics are more ubiquitous in the environment due to the sheer volume of plastic waste present in aquatic ecosystems. They can persist for decades or even centuries, causing long-term contamination of water bodies [10]. Both primary and secondary microplastics can have significant impacts on aquatic ecosystems due to their small size and diverse physical and chemical properties. The classification of microplastics based on their origin helps to understand their pathways and fate in the environment and aids in identifying effective mitigation strategies [9-11]. To further illustrate the distinctions between primary and secondary microplastics, their sources, and environmental behavior, Table 1 presents a detailed classification and characterization matrix that highlights key attributes relevant to their environmental fate. Table 1 Classification and Characteristics of Microplastics Type (Primary / Secondary) Example Source Size Range Shape / Morphology Common Polymer Composition Typical Environmental Behavior Primary Cosmetics (microbeads), industrial abrasives, plastic pellets (nurdles) <5 mm Spherical, granular, fibrous Polyethylene (PE), Polypropylene (PP), Polystyrene (PS) Often suspended in water, widely dispersed Primary Synthetic fibers from textiles (e.g., polyester) <5 mm Fibrous Polyester, Nylon Remain suspended or settle depending on density Secondary Plastic bottles, fishing nets, packaging Variable, <5 mm after degradation Irregular, fragmented Varies—PE, PP, PET, etc. Accumulates in sediments, bioavailable to fauna 2.2. Behavior, Transport, and Fate in Marine and Freshwater Systems Microplastics exhibit complex behavior in aquatic environments, and their movement and persistence are influenced by factors such as size, density, and surface characteristics. The behavior of microplastics varies greatly depending on their physical properties [12]. For instance, smaller microplastics tend to remain suspended in the water column, while larger particles may sink to the sediments. The buoyancy of microplastics is also influenced by the chemical composition of the polymer, with some types being more likely to float on the surface or aggregate with other particles [12-15]. Understanding the movement of microplastics through various environmental compartments is crucial for assessing their ecological impact. After their release into the environment through domestic, industrial, and agricultural activities, microplastics are subject to complex transport dynamics involving wind dispersal, runoff, river transport, and tidal deposition. These pathways determine their distribution across soils, freshwater, and marine environments, influencing their persistence and interactions with biota. The schematic below provides a comprehensive overview of the major pathways and processes involved in the environmental transport and fate of microplastics across terrestrial and aquatic systems (Figure 1). World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 94 Figure 1 Pathways and Fate of Microplastics in Terrestrial and Aquatic Ecosystems. Reproduced with permission from ref. [13] Once introduced into the aquatic environment, microplastics can be transported over long distances by ocean currents, rivers, and wind [16]. Studies have shown that microplastics are found in remote regions of the ocean, far from their source of origin. They can be carried from urban areas to the open sea, highlighting the widespread nature of the contamination. In freshwater systems, microplastics are similarly transported by rivers and streams, accumulating in areas such as riverbeds, wetlands, and lakes [16-18]. The fate of microplastics in marine and freshwater systems depends on their interaction with environmental processes and biota. Over time, microplastics may accumulate in the sediments or be ingested by marine organisms. In some cases, these particles can enter the food chain, leading to bioaccumulation and biomagnification. The persistence of microplastics in the environment is concerning, as they resist natural degradation processes, and their presence in ecosystems can last for hundreds of years [19-20]. Recent studies have provided important insights into the behavior and transport of microplastics in aquatic systems. For instance, according to research by Coyle et al. [21], microplastics have been found to accumulate in marine sediments and riverbeds, where they pose a threat to benthic organisms. In addition, microplastics' ability to adsorb toxic substances, such as persistent organic pollutants (POPs), increases their ecological risk, as these chemicals may be released into organisms when ingested, leading to toxic effects [21]. 2.3. Ecological and Health Risks to Organisms and Humans Microplastic pollution in aquatic ecosystems presents significant ecological and health risks to both organisms and humans. For aquatic organisms, the ingestion of microplastics is a major concern. Many marine and freshwater species, including fish, shellfish, and invertebrates, mistake microplastics for food, leading to internal injuries, digestive blockages, and impaired feeding [22]. The ingestion of microplastics can also affect growth, reproduction, and survival, as evidenced by studies on fish populations that have shown reduced growth rates and reproductive success following microplastic exposure [22,23]. The ingestion of microplastics can also result in the bioaccumulation of toxic chemicals present on the plastic's surface. These chemicals, which may include heavy metals, pesticides, and other pollutants, can leach into the organisms' tissues, leading to adverse health effects [24]. This is of particular concern in marine ecosystems, where microplastics can enter the food chain and accumulate in higher trophic levels. In the case of apex predators, such as marine mammals, the effects of microplastic ingestion may have severe consequences for species health and population sustainability [25]. World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 95 For humans, the primary route of exposure to microplastics is through the consumption of contaminated seafood, particularly fish and shellfish [26]. In recent years, studies have shown that microplastics are present in commercially important seafood species, raising concerns about human health risks [26-28]. In addition to ingestion, humans can be exposed to microplastics through drinking water, where microplastic particles have been detected in both bottled and tap water globally. Some researchers have even suggested that inhalation of airborne microplastic fibers could pose a health risk, especially in areas with high levels of industrial plastic processing or waste incineration [29-31]. The potential health risks to humans from microplastic exposure are still under investigation, but early studies suggest that microplastics may cause inflammation, oxidative stress, and immune system dysfunction. According to a study by Akbari & Jaafari [20], the ingestion of microplastics has been linked to inflammation in laboratory animals, suggesting that chronic exposure may lead to more serious health conditions. Moreover, the presence of toxic chemicals adsorbed onto microplastics could contribute to long-term health risks, including endocrine disruption, reproductive toxicity, and cancer. 2.4. Gaps in Traditional Monitoring and Control Strategies Monitoring and controlling microplastic pollution in aquatic ecosystems has proven to be a challenging task due to several limitations in traditional methods [32]. One major challenge is the lack of standardized monitoring protocols for microplastics, which makes it difficult to compare results across studies. The diversity in size, shape, and polymer type of microplastics requires the use of specialized detection methods, many of which are still in the developmental stage. Traditional sampling methods, such as trawling nets and surface water collection, are often insufficient for capturing smaller microplastics or those that are buried in sediments [33-35]. Furthermore, the global scale of microplastic pollution presents significant logistical challenges for monitoring efforts. Microplastics are widely distributed across marine and freshwater systems, often in remote or difficult-to-reach areas. Effective monitoring requires a large-scale and coordinated approach, with regular sampling in both high-traffic and remote regions. However, the cost and complexity of such monitoring programs are substantial, limiting their feasibility [34,36]. In terms of control strategies, traditional efforts have largely focused on reducing plastic waste inputs into the environment, such as banning single-use plastics and improving waste management systems. While these efforts are important, they have been insufficient to address the already existing pollution in aquatic ecosystems. The lack of effective removal technologies, particularly for microplastics in wastewater, remains a significant obstacle [37,38]. Advances in filtration and treatment technologies, such as the development of microplastic capture systems in wastewater treatment plants, are needed to reduce microplastic contamination at its source [38]. A study by Choudhury et al. [18] emphasized the need for more comprehensive and effective mitigation measures, suggesting that both prevention and active removal strategies are necessary to address microplastic pollution. The development of novel techniques, including the use of artificial intelligence (AI) for monitoring and predicting microplastic distribution, represents a promising area of research. These technologies could provide more efficient, cost-effective, and widespread solutions to microplastic pollution control [18]. 3. Role of Artificial Intelligence in Environmental Monitoring Artificial intelligence (AI) has brought transformative changes to environmental monitoring, particularly in the detection and analysis of microplastic pollution in aquatic ecosystems. AI technologies, including machine learning (ML), deep learning (DL), and computer vision, are revolutionizing the way researchers and environmental scientists study and address microplastic pollution [39,40]. These technologies enhance data processing, enable real-time monitoring, and allow for the efficient classification and tracking of microplastic contamination across large geographical areas. Additionally, AI-driven systems are able to process vast amounts of data from various sources, including remote sensing, drones, underwater imaging, and sensor networks, providing researchers with valuable insights that would be difficult or impossible to obtain using traditional methods [41,42]. 3.1. AI Subfields Relevant to Microplastics AI subfields, such as machine learning (ML), deep learning (DL), and computer vision, have been crucial in the development of more effective systems for monitoring and detecting microplastics in aquatic environments [43]. Machine learning encompasses a wide range of algorithms that can be trained to detect patterns and make predictions from data. This capability is particularly useful for classifying microplastics from other environmental debris. ML algorithms, such as decision trees, random forests, and support vector machines, have been applied to environmental World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 96 data to differentiate microplastics based on specific features such as size, shape, and texture [31]. These machine learning algorithms are especially beneficial in automating the analysis of large datasets, reducing human error and the time required for data processing. Deep learning, a subset of machine learning, utilizes neural networks with multiple layers to learn complex patterns in data. Convolutional neural networks (CNNs) are especially prominent in deep learning applications for microplastic detection. These networks are trained on large datasets of images to detect microplastics in various environmental contexts, such as satellite imagery, underwater photos, and drone footage. DL models, particularly CNNs, have demonstrated high accuracy in identifying microplastic particles, even in challenging environments where microplastics are visually similar to other materials like organic debris [39]. The use of deep learning in microplastic detection has the potential to revolutionize how large-scale environmental monitoring efforts are carried out, by providing high-speed, automated solutions for continuous data analysis. Computer vision, another critical AI subfield, is designed to enable machines to interpret and understand visual information from the world around them. In the context of microplastic pollution, computer vision algorithms are applied to interpret visual data obtained from underwater cameras, drones, or satellites. These systems analyze images to detect microplastic debris, classifying them according to various characteristics such as shape, size, and texture. By automating the image analysis process, computer vision significantly reduces the need for manual intervention, enabling continuous, real-time monitoring of aquatic ecosystems [40]. This application of computer vision plays a crucial role in detecting microplastics that may not be easily identified through traditional monitoring methods. Table 2 summarizes the major artificial intelligence techniques applied in microplastic monitoring, mapping each to their specific applications, data requirements, strengths, and case study examples drawn from recent literature. Table 2 AI Techniques and Their Application to Microplastic Monitoring AI Technique Application Data Type Used Strengths Limitations Case Study Reference Machine Learning (SVM, Random Forest) Classification of microplastics vs non-plastics Imaging, spectral data High accuracy, interpretable models Requires feature engineering, sensitive to noisy data [48] Deep Learning (CNN) Image-based detection of microplastics Drone/underwater/satellite imagery Automated feature learning, high accuracy Data-intensive, opaque decisionmaking [39] Computer Vision Visual identification and classification Camera/drone footage Real-time processing, scalable Limited by image quality, lighting [47] Predictive Modeling (ML/DL) Forecasting microplastic movement and distribution Historical pollution data, environmental variables Supports preventive action Requires continuous data input [49] 3.2. Data Sources: Remote Sensing, Drones, Underwater Imaging, Sensor Networks AI applications for microplastic detection depend heavily on the integration of diverse data sources. Remote sensing, a key technology in environmental monitoring, allows for the collection of large-scale data from satellite and aerial imagery. Satellite-based remote sensing provides high-resolution images that are essential for identifying microplastic particles on the ocean surface or in large freshwater bodies. AI-powered image classification models are used to analyze these images, providing insights into the concentration and distribution of microplastics across vast regions [44]. Remote sensing enables the monitoring of large aquatic ecosystems that may otherwise be inaccessible, offering an efficient and cost-effective solution for global-scale microplastic surveillance. Drones have become increasingly popular for collecting environmental data in both marine and freshwater ecosystems. Equipped with high-resolution cameras and sensors, drones capture detailed images and videos of water bodies, which are then analyzed using machine learning and computer vision algorithms. Drones are particularly valuable in hard-toreach areas where traditional monitoring techniques may be limited. Their mobility and ability to gather real-time data make them an indispensable tool for monitoring microplastic pollution [45,46]. Additionally, drones provide World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 97 researchers with the ability to collect high-quality data across a range of geographic locations, offering a broader scope for monitoring microplastic pollution in diverse ecosystems. Underwater imaging technologies, such as sonar systems and underwater robots, are crucial for detecting microplastics that are not visible from the surface. These technologies allow for the collection of detailed data on submerged microplastics that may be suspended in the water column or embedded in the sediments. AI algorithms can process this data to identify microplastic particles based on their size, shape, and other physical characteristics [47,48]. Furthermore, sensor networks deployed in aquatic environments provide real-time data on environmental conditions, such as temperature, water quality, and particle concentrations. When combined with AI-based systems, these sensor networks improve the accuracy and efficiency of microplastic detection by providing continuous, high-frequency data [49]. A concise overview of the various AI-integrated data sources used in microplastic detection is provided in Table 3, detailing the tools, application environments, and technological limitations associated with each method. Table 3 Summary of AI-Integrated Data Sources for Microplastic Detection Data Source Example Device/Tool Resolution / Sensitivity Application Environment Role in AI-Based Analysis Limitations Remote Sensing PRISMA Satellite, Sentinel-2 Up to 30m (optical), spectral bands Marine Broad spatial monitoring, used in CNNs for classification Limited to surface plastics, cloud interference Drones DJI Phantom with multispectral sensors Highresolution images (cm level) Freshwater & Coastal Used for real-time microplastic spotting via image processing Battery limits, small area coverage Underwater Imaging ROVs with optical cameras High resolution (mm scale) Deep sea & lake beds Detailed close-up classification with AI Limited by visibility, costly Sensor Networks In-situ turbidity/fluorescence sensors Real-time particulate matter Rivers, treatment plants Feeds ML models for trend analysis Non-specific signal, maintenance needs 3.3. Application to Microplastic Detection AI technologies have found widespread application in the detection of microplastics, particularly in areas such as image recognition, hyperspectral and multispectral data classification, and predictive modeling. Image recognition, facilitated by deep learning algorithms like CNNs, is one of the most powerful applications of AI in microplastic detection. In recent studies, CNNs have been successfully applied to classify and detect microplastic particles in images obtained from drones, satellites, and underwater cameras. By training CNN models on large datasets of labeled images, these algorithms can identify microplastics with high accuracy, even when they are mixed with other types of marine debris [39]. This application allows for the automation of image processing, reducing the need for manual inspections and speeding up the analysis process. Hyperspectral and multispectral data classification techniques are becoming increasingly important for microplastic detection, particularly in marine environments. These imaging techniques capture data across multiple wavelengths of light, allowing for the identification of materials based on their unique spectral signatures. When combined with AI algorithms, hyperspectral and multispectral data can be analyzed to differentiate microplastics from natural particles or sediments. These AI models are particularly useful in detecting microplastics that are invisible to the naked eye or that may be submerged beneath the surface of the water [44]. The ability to analyze multispectral and hyperspectral data through AI-powered systems enables more accurate and comprehensive monitoring of microplastic pollution. Predictive modeling and pattern recognition, powered by machine learning and deep learning, have also become essential tools in the study of microplastics. AI models can be trained to recognize patterns in historical environmental data, allowing for predictions about the movement and accumulation of microplastics in aquatic ecosystems. By combining predictive models with real-time sensor data, researchers can better understand microplastic distribution World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 98 dynamics and predict where future contamination may occur [49]. These models are particularly useful for long-term monitoring efforts, providing valuable insights into the effectiveness of mitigation strategies and helping policymakers make informed decisions about managing microplastic pollution. 3.4. Case Studies/Examples from Recent Literature Recent case studies illustrate the significant impact AI has had in advancing microplastic detection. Studies by Hamzah et al. [45] and Maharjan et al. [50] demonstrated the use of drones equipped with machine learning models to detect microplastics in freshwater environments. By analyzing images captured by the drones, the machine learning algorithms were able to detect microplastic particles with high precision. This study highlights the potential of dronebased AI systems in detecting microplastics in hard-to-reach areas and offers a practical solution for real-time environmental monitoring. Another notable example comes from Hu et al. [39], who utilized deep learning algorithms to analyze satellite imagery for large-scale monitoring of oceanic microplastics. Their study showed how AI-powered image recognition could be applied to satellite data to track microplastic pollution across the world's oceans. This approach allowed for the identification of areas with high concentrations of microplastics, providing critical information for marine conservation efforts and policy-making. In a study conducted by Taggio et al. [47], hyperspectral imaging and machine learning algorithms were used to detect microplastics in marine environments. By analyzing hyperspectral images, the researchers were able to identify microplastic particles that were not visible using traditional methods. This study demonstrated the power of AI and hyperspectral technology in overcoming the limitations of visual detection and improving the accuracy of microplastic monitoring. 4. AI-Driven Mitigation Strategies and Sustainable Interventions Artificial intelligence offers transformative potential in developing mitigation strategies for microplastic pollution, enabling targeted, efficient, and scalable interventions. AI-driven solutions are revolutionizing the monitoring, prediction, and management of microplastics, with applications ranging from optimizing waste management processes to advancing recycling technologies [51,52]. Through predictive modeling, AI enhances the ability to foresee areas with high contamination risks, allowing for preemptive actions that minimize environmental damage. Additionally, AI facilitates the design of sustainable interventions by streamlining waste collection and treatment processes and supporting circular economy initiatives that aim to reduce plastic production and consumption. These AI-based strategies align with broader environmental sustainability goals and demonstrate the promising role of technology in mitigating the pervasive issue of microplastic pollution [4,53]. 4.1. Autonomous Robotics and Underwater Vehicles for Cleanup The integration of autonomous robotics and underwater vehicles in microplastic cleanup efforts presents a groundbreaking approach to combating pollution in aquatic ecosystems. These robotic systems, equipped with AI technologies, enable precise detection, collection, and removal of microplastics from both freshwater and marine environments [54]. The development of these systems has been driven by the need for scalable, efficient, and sustainable solutions capable of operating in challenging aquatic environments where traditional methods are ineffective. Autonomous underwater vehicles (AUVs) equipped with advanced sensors, such as optical and infrared imaging systems, facilitate real-time monitoring of pollution levels, identifying microplastic concentrations with high accuracy [55,56]. These technologies can also be designed to perform cleanup tasks autonomously, reducing the need for human intervention in dangerous or remote locations. AI plays a central role in optimizing the efficiency of these robots, using machine learning algorithms to process data from sensors and adapt to varying environmental conditions. These systems are capable of distinguishing between microplastics and other organic or inorganic materials, ensuring that only harmful pollutants are targeted for removal. Additionally, the deployment of autonomous vehicles reduces operational costs and labor intensity, enabling continuous and large-scale cleaning operations. The combination of AI and robotics in underwater cleanup is also fostering the development of intelligent navigation systems that can autonomously map and chart polluted areas, adjusting their cleaning routes to maximize efficiency [54]. Robotic cleanup technologies are being tested in a variety of aquatic environments, with several pilot projects successfully employing AI-driven solutions for the removal of microplastics from rivers, lakes, and oceans. These AIintegrated robots not only provide a significant reduction in pollution but also promote the sustainability of aquatic World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 99 ecosystems by preventing the accumulation of plastics in sensitive areas. The capability of these robots to collect plastic debris at a high rate and in difficult-to-reach locations offers a novel solution that aligns with long-term environmental conservation efforts [57,58]. 4.2. AI-Optimized Bioremediation and Filtration Systems AI-optimized bioremediation and filtration systems present an innovative approach to tackling microplastic pollution by enhancing natural processes and improving the efficiency of filtration technologies. Machine learning models are increasingly utilized to analyze large datasets, which help identify the most effective microbial strains capable of breaking down microplastics. Through AI, the environmental conditions required for optimal microbial activity can be precisely controlled, resulting in more efficient degradation of microplastics in aquatic ecosystems. These AI-driven systems can also monitor real-time data from sensors embedded in water bodies to assess the degradation process, predict future outcomes, and adjust conditions accordingly, thereby maximizing the effectiveness of bioremediation efforts [59,60]. In parallel, AI plays a crucial role in enhancing filtration systems designed to capture microplastics from water sources. Advanced filtration techniques, such as membrane-based filtration and electrostatic separation, can be optimized through AI algorithms that analyze water flow, pressure, and particle size distribution in real-time. These AI systems can dynamically adjust filter parameters, improving the capture rates of microplastics while minimizing energy consumption and operational costs [59]. By combining AI with filtration technologies, the overall efficiency of microplastic removal is significantly improved, making it possible to scale these systems for widespread use in water treatment facilities. The integration of AI into both bioremediation and filtration not only enhances the effectiveness of these systems but also contributes to the sustainability of aquatic ecosystems. AI algorithms assist in the identification of areas most affected by microplastic pollution, enabling targeted interventions. Furthermore, the combination of bioremediation with filtration systems ensures that microplastics are not only broken down but also physically removed from the environment. This multi-layered approach provides a promising pathway for mitigating microplastic contamination in aquatic environments while contributing to long-term environmental sustainability goals [61]. 4.3. Wastewater Treatment Plant (WWTP) Monitoring and Process Optimization AI plays a significant role in optimizing the operations of wastewater treatment plants (WWTPs), crucial for reducing microplastic contamination in aquatic ecosystems. Machine learning algorithms can be employed to enhance the detection of microplastics in wastewater by integrating sensor data with real-time analysis, improving the efficiency and effectiveness of filtration systems. Advanced AI-driven models analyze large datasets from sensors placed throughout the treatment process, identifying patterns in microplastic presence and behavior. These insights enable the fine-tuning of operational parameters, such as flow rates, chemical dosing, and filtration methods, to ensure higher removal efficiency of microplastics from wastewater before discharge into water bodies [39,62]. The application of AI in process optimization extends beyond monitoring; predictive models can anticipate variations in influent water quality, allowing for adjustments in treatment protocols. For instance, AI can predict fluctuations in the concentrations of microplastics based on historical data and environmental factors, enabling operators to adapt treatment schedules accordingly. This proactive approach not only enhances the removal efficiency but also minimizes energy consumption, thereby contributing to the overall sustainability of the WWTP. Studies have highlighted the integration of AI models in monitoring and controlling biological and chemical processes within WWTPs, leading to significant improvements in both cost-effectiveness and performance [61,63]. AI-powered optimization techniques also foster the development of closed-loop systems in WWTPs, where waste byproducts are reused or repurposed, contributing to circular economy goals. By improving the overall efficiency of these plants, AI reduces the operational costs and environmental footprint of wastewater treatment processes, while simultaneously curbing the release of microplastics into the ecosystem. Furthermore, these AI tools can be integrated with real-time environmental monitoring systems, which, in turn, helps in ensuring compliance with water quality regulations and contributes to overall environmental sustainability [64]. 4.4. Role of AI in Lifecycle Analysis and Circular Economy Strategies Artificial intelligence plays a crucial role in supporting lifecycle analysis (LCA) and advancing circular economy strategies aimed at mitigating microplastic pollution. By employing machine learning algorithms, AI can track the entire lifecycle of plastics from production and usage to disposal and recycling. This data-driven approach enables more World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 106 [22] Sharma, S., & Chatterjee, S. (2017). Microplastic pollution, a threat to marine ecosystem and human health: a short review. Environmental Science and Pollution Research, 24, 21530-21547. [23] Rakib, M. R. J., Sarker, A., Ram, K., Uddin, M. G., Walker, T. R., Chowdhury, T., ... & Idris, A. M. (2023). Microplastic toxicity in aquatic organisms and aquatic ecosystems: a review. Water, Air, & Soil Pollution, 234(1), 52. [24] Koelmans, A. A. (2015). Modeling the role of microplastics in bioaccumulation of organic chemicals to marine aquatic organisms. A critical review. Marine anthropogenic litter, 309-324. [25] Carbery, M., O'Connor, W., & Palanisami, T. (2018). Trophic transfer of microplastics and mixed contaminants in the marine food web and implications for human health. Environment international, 115, 400-409. [26] Smith, M., Love, D. C., Rochman, C. M., & Neff, R. A. (2018). Microplastics in seafood and the implications for human health. Current environmental health reports, 5, 375-386. [27] Santillo, D., Miller, K., & Johnston, P. (2017). Microplastics as contaminants in commercially important seafood species. Integrated environmental assessment and management, 13(3), 516-521. [28] Yuan, Z., Nag, R., & Cummins, E. (2022). Human health concerns regarding microplastics in the aquatic environment-From marine to food systems. Science of the Total Environment, 823, 153730. [29] Sridharan, S., Kumar, M., Singh, L., Bolan, N. S., & Saha, M. (2021). Microplastics as an emerging source of particulate air pollution: A critical review. Journal of Hazardous Materials, 418, 126245. [30] Ziccardi, L. M., Edgington, A., Hentz, K., Kulacki, K. J., & Kane Driscoll, S. (2016). Microplastics as vectors for bioaccumulation of hydrophobic organic chemicals in the marine environment: A state‐of‐the‐science review. Environmental toxicology and chemistry, 35(7), 1667-1676. [31] Phan, S., & Luscombe, C. K. (2023). Recent trends in marine microplastic modeling and machine learning tools: Potential for long-term microplastic monitoring. Journal of Applied Physics, 133(2). [32] Zhang, K., Shi, H., Peng, J., Wang, Y., Xiong, X., Wu, C., & Lam, P. K. (2018). Microplastic pollution in China's inland water systems: a review of findings, methods, characteristics, effects, and management. Science of the Total Environment, 630, 1641-1653. [33] Miller, E., Sedlak, M., Lin, D., Box, C., Holleman, C., Rochman, C. M., & Sutton, R. (2021). Recommended best practices for collecting, analyzing, and reporting microplastics in environmental media: Lessons learned from comprehensive monitoring of San Francisco Bay. Journal of hazardous materials, 409, 124770. [34] Zarfl, C. (2019). Promising techniques and open challenges for microplastic identification and quantification in environmental matrices. Analytical and Bioanalytical Chemistry, 411, 3743-3756. [35] Ivleva, N. P. (2021). Chemical analysis of microplastics and nanoplastics: challenges, advanced methods, and perspectives. Chemical reviews, 121(19), 11886-11936. [36] Covernton, G. A., Pearce, C. M., Gurney-Smith, H. J., Chastain, S. G., Ross, P. S., Dower, J. F., & Dudas, S. E. (2019). Size and shape matter: A preliminary analysis of microplastic sampling technique in seawater studies with implications for ecological risk assessment. Science of the Total Environment, 667, 124-132. [37] Cornago, E., Börkey, P., & Brown, A. (2021). Preventing single-use plastic waste: Implications of different policy approaches. OECD Environment Working Papers, (182), 0_1-68. [38] Krishnan, R. Y., Manikandan, S., Subbaiya, R., Karmegam, N., Kim, W., & Govarthanan, M. (2023). Recent approaches and advanced wastewater treatment technologies for mitigating emerging microplastics contamination–A critical review. Science of the Total Environment, 858, 159681. [39] Hu, B., Dai, Y., Zhou, H., Sun, Y., Yu, H., Dai, Y., ... & Zhou, P. (2024). Using artificial intelligence to rapidly identify microplastics pollution and predict microplastics environmental behaviors. Journal of Hazardous Materials, 134865. [40] Jin, H., Kong, F., Li, X., & Shen, J. (2024). Artificial intelligence in microplastic detection and pollution control. Environmental Research, 119812. [41] Abdulmuttalib, H., Al Doori, M., Barsi, Á., Blaschke, T., Gao, Y., Kugler, Z., ... & Tiede, D. (2024). Remote Sensing Data Quality in the Era of AI. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 10, 1-11. [42] Mandal, A., & Ghosh, A. R. (2024). AI-driven surveillance of the health and disease status of ocean organisms: a review. Aquaculture International, 32(1), 887-898. World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 107 [43] Zhang, Y., Zhang, D., & Zhang, Z. (2023). A critical review on artificial intelligence—based microplastics imaging technology: recent advances, hot-spots and challenges. International Journal of Environmental Research and Public Health, 20(2), 1150. [44] Castagna, A., Dierssen, H. M., Devriese, L. I., Everaert, G., Knaeps, E., & Sterckx, S. (2023). Evaluation of historic and new detection algorithms for different types of plastics over land and water from hyperspectral data and imagery. Remote Sensing of Environment, 298, 113834. [45] Hamzah, A., Aqlan, F., & Baidya, S. (2024). Drone‐based digital twins for water quality monitoring: A systematic review. Digital Twins and Applications, 1(2), 131-160. [46] Francia, D., Galiè, G., & Pagliari, C. (2025). Design and Validation of an Eco-Compatible Autonomous Drone for Microplastic Monitoring in Port Environments. Sustainability, 17(6), 2696. [47] Taggio, N., Aiello, A., Ceriola, G., Kremezi, M., Kristollari, V., Kolokoussis, P., ... & Barbone, E. (2022). A combination of machine learning algorithms for marine plastic litter detection exploiting hyperspectral PRISMA data. Remote Sensing, 14(15), 3606. [48] Li, F., Liu, D., Guo, X., Zhang, Z., Martin, F. L., Lu, A., & Xu, L. (2024). Identification and visualization of environmental microplastics by Raman imaging based on hyperspectral unmixing coupled machine learning. Journal of Hazardous Materials, 465, 133336. [49] Godasiaei, S. H. (2025). Predictive modeling of microplastic adsorption in aquatic environments using advanced machine learning models. Science of The Total Environment, 958, 178015. [50] Maharjan, N., Miyazaki, H., Pati, B. M., Dailey, M. N., Shrestha, S., & Nakamura, T. (2022). Detection of river plastic using UAV sensor data and deep learning. Remote Sensing, 14(13), 3049. [51] Bhattacharjee, J., & Roy, S. (2024). Green remediation of microplastics using bionanomaterials. In Remediation of plastic and microplastic waste (pp. 240-260). CRC Press. [52] Farghali, M., & Osman, A. I. (2024). Revolutionizing waste management: unleashing the power of artificial intelligence and machine learning. In Advances in Energy from Waste (pp. 225-279). Woodhead Publishing. [53] Geyer, R., Jambeck, J. R., & Law, K. L. (2017). Production, use, and fate of all plastics ever made. Science advances, 3(7), e1700782. [54] Agarwala, N. (2020). Monitoring the ocean environment using robotic systems: Advancements, trends, and challenges. Marine Technology Society Journal, 54(5), 42-60. [55] Fulton, M., Hong, J., Islam, M. J., & Sattar, J. (2019, May). Robotic detection of marine litter using deep visual detection models. In 2019 international conference on robotics and automation (ICRA) (pp. 5752-5758). IEEE. [56] Nazerdeylami, A., Majidi, B., & Movaghar, A. (2021). Autonomous litter surveying and human activity monitoring for governance intelligence in coastal eco-cyber-physical systems. Ocean & Coastal Management, 200, 105478. [57] Dadheech, D., Paul, A. S., Vyas, S., & Malakar, A. (2024). Revolutionizing Ocean Cleanup: AI and Robotics Tackle Pollution Challenges. In Artificial Intelligence and Edge Computing for Sustainable Ocean Health (pp. 343-358). Cham: Springer Nature Switzerland. [58] Zhao, B., Richardson, R. E., & You, F. (2024). Advancing microplastic analysis in the era of artificial intelligence: From current applications to the promise of generative AI. Nexus, 1(4). [59] Gupta, P., Bhardwaj, G., Dubey, S., Tayal, T., Sengupta, A., & Narad, P. (2024). AI-Enabled Process Optimization for Sustainable Wastewater Treatment Solutions. In The AI Cleanse: Transforming Wastewater Treatment Through Artificial Intelligence: Harnessing Data-Driven Solutions (pp. 141-164). Cham: Springer Nature Switzerland. [60] Bhattacharjee, J., & Roy, S. (2024). Green remediation of microplastics using bionanomaterials. In Remediation of plastic and microplastic waste (pp. 240-260). CRC Press. [61] Zhao Braun, U., Altmann, K., Herper, D., Knefel, M., Bednarz, M., & Bannick, C. G. (2021). Smart filters for the analysis of microplastic in beverages filled in plastic bottles. Food Additives & Contaminants: Part A, 38(4), 691700. [62] Sahu, S., Kaur, A., Singh, G., & Arya, S. K. (2023). Harnessing the potential of microalgae-bacteria interaction for eco-friendly wastewater treatment: a review on new strategies involving machine learning and artificial intelligence. Journal of environmental management, 346, 119004. World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 108 [63] Di Fiore, C., Carriera, F., Iannone, A., Paris, E., Gallucci, F., & Avino, P. (2024). First Approach for Defining an Analytical Protocol for the Determination of Microplastics in Cheese Using Pyrolysis–Gas Chromatography–Mass Spectrometry. Applied Sciences, 14(13), 5621. [64] Lowe, M., Qin, R., & Mao, X. (2022). A review on machine learning, artificial intelligence, and smart technology in water treatment and monitoring. Water, 14(9), 1384. [65] Guo, P., Wang, Y., Moghaddamfard, P., Meng, W., Wu, S., & Bao, Y. (2024). Artificial intelligence-empowered collection and characterization of microplastics: A review. Journal of Hazardous Materials, 134405. [66] Guarda, C., Caseiro, J., & Pires, A. (2024). Machine learning to enhance sustainable plastics: A review. Journal of Cleaner Production, 143602. [67] Sundui, B., Ramirez Calderon, O. A., Abdeldayem, O. M., Lázaro-Gil, J., Rene, E. R., & Sambuu, U. (2021). Applications of machine learning algorithms for biological wastewater treatment: updates and perspectives. Clean Technologies and Environmental Policy, 23, 127-143. [68] Solaja, O. M. (2024). Unleashing the Power of AI: Revolutionizing Plastic Waste Management for Sustainable Development in Developing Nations. Waste Technology, 12(1), 28-38. [69] Ramos, E., Lopes, A. G., & Mendonça, F. (2024). Application of Machine Learning in Plastic Waste Detection and Classification: A Systematic Review. Processes, 12(8), 1632. [70] Zhang, Y., Zhang, D., & Zhang, Z. (2023). A critical review on artificial intelligence—based microplastics imaging technology: recent advances, hot-spots and challenges. International Journal of Environmental Research and Public Health, 20(2), 1150. [71] Zarfl, C. (2019). Promising techniques and open challenges for microplastic identification and quantification in environmental matrices. Analytical and Bioanalytical Chemistry, 411, 3743-3756. [72] Chen, J., Chen, S., Fu, R., Li, D., Jiang, H., Wang, C., ... & Hicks, B. J. (2022). Remote sensing big data for water environment monitoring: Current status, challenges, and future prospects. Earth's Future, 10(2), e2021EF002289. [73] Li, C., & Huang, M. (2023). Environmental sustainability in the age of big data: opportunities and challenges for business and industry. Environmental Science and Pollution Research, 30(56), 119001-119015. [74] Soundariya, A., Behera, N. K., Selvakumar, P., Chandel, P. S., Gupta, S., & Manjunath, T. C. (2025). AI and Environmental Ethics: The Role of AI in Addressing Climate Change Ethical Considerations in AI-Driven Environmental Solutions. In Human Values, Ethics, and Dignity in the Age of Artificial Intelligence (pp. 321-346). IGI Global Scientific Publishing. [75] Samarawickrama, M. (2022). AI governance and ethics framework for sustainable AI and sustainability. arXiv preprint arXiv:2210.08984. [76] Chisom, O. N., Biu, P. W., Umoh, A. A., Obaedo, B. O., Adegbite, A. O., & Abatan, A. (2024). Reviewing the role of AI in environmental monitoring and conservation: A data-driven revolution for our planet. World Journal of Advanced Research and Reviews, 21(1), 161-171. [77] Ohalete, N. C., Aderibigbe, A. O., Ani, E. C., Ohenhen, P. E., Daraojimba, D. O., & Odulaja, B. A. (2023). AI-driven solutions in renewable energy: A review of data science applications in solar and wind energy optimization. World Journal of Advanced Research and Reviews, 20(3), 401-417. [78] Taggio, N., Aiello, A., Ceriola, G., Kremezi, M., Kristollari, V., Kolokoussis, P., ... & Barbone, E. (2022). A combination of machine learning algorithms for marine plastic litter detection exploiting hyperspectral PRISMA data. Remote Sensing, 14(15), 3606. [79] Liang, W., Tadesse, G. A., Ho, D., Fei-Fei, L., Zaharia, M., Zhang, C., & Zou, J. (2022). Advances, challenges and opportunities in creating data for trustworthy AI. Nature Machine Intelligence, 4(8), 669-677. [80] Miller, T., Durlik, I., Kostecka, E., Kozlovska, P., Łobodzińska, A., Sokołowska, S., & Nowy, A. (2025). Integrating Artificial Intelligence Agents with the Internet of Things for Enhanced Environmental Monitoring: Applications in Water Quality and Climate Data. Electronics, 14(4), 696. [81] Raji, I. D., & Buolamwini, J. (2019, January). Actionable auditing: Investigating the impact of publicly naming biased performance results of commercial ai products. In Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society (pp. 429-435). World Journal of Biology Pharmacy and Health Sciences, 2025, 22(02), 091-109 109 [82] Mitu, N. E., & Mitu, G. T. (2024). The Hidden Cost of AI: Carbon Footprint and Mitigation Strategies. Available at SSRN 5036344. [83] Tseng, C. J., & Lin, S. Y. (2024). Role of artificial intelligence in carbon cost reduction of firms. Journal of Cleaner Production, 447, 141413. [84] Twagirayezu, G., Irumva, O., Huang, K., Xia, H., Uwimana, A., Nizeyimana, J. C., ... & Itangishaka, A. C. (2022). Environmental effects of electrical and electronic waste on water and soil: a review. Pol. J. Environ. Stud, 31, 2507-2525. [85] Andrade, A. C. C., & Vasquez, M. C. S. (2024). The Compatibility Between SDGs and the EU Regulatory Framework of AI. Journal of Ethics and Legal Technologies, 6(JELT-Volume 6 Issue 1), 11-144. [86] Hasan, M. A., Balasubadra, K., Vadivel, G., Arunfred, N., Ishwarya, M. V., & Murugan, S. (2024, February). IoTDriven Image Recognition for Microplastic Analysis in Water Systems using Convolutional Neural Networks. In 2024 2nd International Conference on Computer, Communication and Control (IC4) (pp. 1-6). IEEE. [87] Reza, S. A., Chowdhury, M. S. R., Hossain, S., Hasanuzzaman, M., Shawon, R. E. R., Chowdhury, B. R., & Rana, M. S. (2024). Global Plastic Waste Management: Analyzing Trends, Economic and Social Implications, and Predictive Modeling Using Artificial Intelligence. Journal of Environmental and Agricultural Studies, 5(3), 42-58. [88] Conrad, C. C., & Hilchey, K. G. (2011). A review of citizen science and community-based environmental monitoring: issues and opportunities. Environmental monitoring and assessment, 176, 273-291. [89] Emam, W. W., & Soliman, K. M. (2024). Integrating geospatial approach with citizen science to combat marine plastic pollution. Developments in Environmental Science, 16, 309-332. [90] Huang, M., Han, K., Liu, W., Wang, Z., Liu, X., & Guo, Q. (2024). Advancing microplastic surveillance through photoacoustic imaging and deep learning techniques. Journal of Hazardous Materials, 470, 134188. [91] Zhao, B., Richardson, R. E., & You, F. (2024). Advancing microplastic analysis in the era of artificial intelligence: From current applications to the promise of generative AI. Nexus, 1(4). [92] Hu, B., Dai, Y., Zhou, H., Sun, Y., Yu, H., Dai, Y., ... & Zhou, P. (2024). Using artificial intelligence to rapidly identify microplastics pollution and predict microplastics environmental behaviors. Journal of Hazardous Materials, 134865. [93] Mitrano, D. M., Bigalke, M., Booth, A. M., Carteny, C. C., Coffin, S., Egger, M., ... & Wagner, S. (2023). Training the next generation of plastics pollution researchers: tools, skills and career perspectives in an interdisciplinary and transdisciplinary field. Microplastics and Nanoplastics, 3(1), 24. [94] Zhu, Y., Li, Y., Huang, J., Zhang, Y., Ho, Y. W., Fang, J. K. H., & Lam, E. Y. (2024). Advanced optical imaging technologies for microplastics identification: progress and challenges. Advanced Photonics Research, 5(11), 2400038. [95] Mazhandu, Z. S., & Muzenda, E. (2019, November). Global plastic waste pollution challenges and management. In 2019 7th International Renewable and Sustainable Energy Conference (IRSEC) (pp. 1-8). IEEE.