Next Article in Journal
Spatial Assessment of Ecosystem Services in Zhoushan Archipelago Based on InVEST Model
Previous Article in Journal
Towards Sustainable and Resilient Infrastructure: Hurricane-Induced Roadway Closure and Accessibility Assessment in Florida Using Machine Learning
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sustainability
Volume 17
Issue 9
10.3390/su17093912
sustainability-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Review

The Role of Artificial Intelligence in Sustainable Ocean Waste Tracking and Management: A Bibliometric Analysis

by
Mariam I. Adeoba
1,*,
Thanyani Pandelani
1,
Harry Ngwangwa
1 and
Tracy Masebe
1,2
1
UNISA Biomechanics Research Group, Department of Mechanical, Bioresources and Biomedical Engineering, College of Science, Engineering and Technology (CSET), University of South Africa, Florida (UNISA), Florida 1710, South Africa
2
Department of Life and Consumer Sciences, College of Agriculture and Environmental Sciences, University of South Africa, Florida (UNISA), Florida 1710, South Africa
*
Author to whom correspondence should be addressed.
Sustainability 2025, 17(9), 3912; https://doi.org/10.3390/su17093912 (registering DOI)
Submission received: 7 March 2025 / Revised: 21 April 2025 / Accepted: 22 April 2025 / Published: 26 April 2025
(This article belongs to the Section Environmental Sustainability and Applications)
Browse Figures
Versions Notes

Abstract

:
The application of artificial intelligence (AI) in monitoring and managing ocean waste reveals considerable promise for improving sustainable strategies to combat marine pollution. This study performs a bibliometric analysis to examine research trends, knowledge frameworks, and future directions in AI-driven sustainable ocean waste management. This study delineates key research themes, prominent journals, influential authors, and leading nations contributing to the field by analysing scientific publications from major databases. Research from citation networks, keyword analysis, and co-authorship patterns highlights significant topics such as AI algorithms for waste detection, machine learning models for predictive mapping of pollution hotspots, and the application of autonomous drones and underwater robots in real-time waste management. The findings indicate a growing global focus on utilising AI to enhance environmental monitoring, optimise waste reduction methods, and support policy development for sustainable marine ecosystems. This bibliometric study provides a comprehensive analysis of the current knowledge landscape, identifies research gaps, and underscores the importance of AI as a crucial enabler for sustainable ocean waste management, offering vital insights for researchers, industry leaders, and environmental policymakers dedicated to preserving ocean health.

1. Introduction

Ocean pollution worldwide has skyrocketed, endangering human health, coastal economies, and marine ecosystems [1]. Over 8 million metric tons of plastic waste alone wind up in the oceans yearly, adding to the buildup of debris that threatens aquatic life, disturbs marine environments, and costs the fishing and tourism industries money. The complexity of managing marine waste is made worse by the size of the seas, the variety of toxins they contain, and the challenge of monitoring waste movement across international waters. The necessity for creative and sustainable approaches to ocean waste management has been brought to light by the limited efficacy of conventional techniques such as localised monitoring and manual beach clean-ups [2,3].
In response to this global challenge, a shift towards sustainable waste management approaches has become crucial [4]. Sustainable strategies prioritise prevention, reduction, and efficient waste management in ways that minimise environmental impact while promoting long-term ecological balance. Effective management of ocean waste involves removing existing debris and implementing systems to predict and prevent future pollution [5]. The integration of advanced technologies, such as artificial intelligence (AI), into waste management systems has shown potential for improving the monitoring, detection, and removal of marine waste more efficiently and cost-effectively [6,7].
Artificial intelligence is emerging as a transformative tool in environmental monitoring and management, including the critical domain of ocean waste tracking [8]. AI encompasses a range of technologies such as machine learning, deep learning, and computer vision that can analyse vast datasets, detect patterns, and make data-driven decisions. In ocean waste management, AI applications can facilitate the real-time monitoring of marine environments through satellite imagery, drone surveillance, and autonomous underwater vehicles (AUVs) [9,10]. These technologies enable precise identification and tracking of waste hotspots, allowing for targeted clean-up efforts and optimised resource allocation.
The predictive capabilities of AI can further aid in modelling waste dispersion patterns and forecasting the accumulation of debris based on environmental variables such as currents, wind patterns, and human activities [11,12]. By leveraging AI-driven insights, policymakers and environmental organisations can design proactive strategies to address pollution before it escalates. Additionally, AI technologies can support the development of automated waste collection systems, including robotic platforms and smart sensors that autonomously detect and retrieve marine litter. The use of AI in this field is still in its infancy. While there have been notable advancements in AI applications for terrestrial waste management, there are unique challenges associated with marine environments, such as the variability of water conditions, the need for robust hardware capable of withstanding harsh oceanic settings, and the limited availability of high-quality datasets [13,14]. Addressing these challenges requires interdisciplinary research and collaboration between oceanographers, data scientists, and policymakers to optimise AI solutions for sustainable marine waste management [15].
This study aims to conduct a comprehensive bibliometric analysis to explore the role of AI in sustainable ocean waste management. The primary objectives are twofold: The first is to analyse the role of AI in enhancing sustainable waste management practices in marine environments, focussing on current capabilities, technologies, and use cases. This includes assessing the impact of AI on monitoring, tracking, and predicting ocean waste patterns. The second is to perform a bibliometric analysis to systematically and evaluate the academic literature on AI applications in ocean waste management. The analysis will identify key themes, influential research works, leading authors, and collaborative networks, highlighting trends, challenges, and research gaps.
By mapping the existing research body, this study provides a comprehensive overview of how AI contributes to sustainable ocean waste management [16]. The bibliometric analysis will leverage data from reputable databases such as Scopus and Web of Science to assess the scope of scholarly work in this domain. VOSviewer will visualise research networks, co-authorship collaborations, and keyword trends. Through this approach, this study aims to generate insights that can inform future research directions, policy frameworks, and technological innovations in the fight against ocean pollution. Understanding the existing literature and identifying gaps is essential for advancing AI’s role in addressing one of our time’s most pressing environmental challenges [17]. The findings of this analysis will contribute to the academic community and support stakeholders such as environmental organisations, governments, and the private sector in leveraging AI technologies for sustainable ocean conservation efforts [18].
AI in sustainable ocean waste tracking and management presents a promising avenue for addressing the global issue of marine pollution [19]. This study’s bibliometric approach will provide a detailed understanding of current research trends and guide future efforts in optimising AI applications for environmental protection. By aligning technological advancements with sustainable practices, the potential to protect marine ecosystems and promote ocean health can be significantly enhanced [20].

2. Methodology

This study’s research design employs bibliometric analysis to methodically review the scholarly literature on artificial intelligence’s (AI) function in sustainable ocean waste tracking and management. An efficient technique for figuring out research patterns, mapping collaboration networks, and comprehending the evolution of scientific knowledge is bibliometric analysis [21]. A thorough assessment of the scientific contributions of the topic is made possible by this methodology, which analyses data including co-authorship networks, citation trends, and publication counts. Finding trends and insights in the corpus of research on AI applications in ocean waste management is the main goal of this bibliometric analysis. This study focusses on answering specific research questions: What are the main areas of research in AI-driven ocean waste management? Which countries, institutions, and authors are the most active in this field? How has the application of AI in managing ocean waste evolved? This analysis provides an evidence-based overview of how AI contributes to sustainable waste management, highlights influential research, and identifies gaps in the literature that future studies can address [22,23].

2.1. Database Selection

Two databases were selected in this study: the Web of Science and Scopus. The choice of these databases is due to their accessibility and user-friendly interface. They are equipped to provide in-depth research and are widely used across scientific fields. We searched and collected data on the Web of Science on 10 November 2024, and Scopus on 11 November the same year. The choice of keywords for the search in this study is motivated by our research topic: “The role of artificial intelligence in sustainable ocean waste tracking and management”. Different search terms were used. The terms that were eventually considered were as follows: deep learning OR machine learning OR computer vision AND ocean waste OR marine plastic OR waste tracking OR pollution. We collected all the studies published between 2004 and 2024, with 2024 data representing partial-year coverage (January–October), limiting the subject area to environmental science, engineering, computer science, agricultural and biological science, earth and planetary science, physics and astronomy, chemical engineering, decision science, multidisciplinary studies, and energy. All the published papers in English were obtained from different articles, reviews, conference papers, book chapters, and books.

2.2. Data Collection

Data collection is essential in bibliometric analysis, ensuring that relevant and high-quality information is extracted for further study. The key steps in data collection include database selection, keyword search, and defining the inclusion and exclusion criteria [24]. A structured search combining AI-related keywords (e.g., deep learning, machine learning, computer vision) and ocean waste (e.g., marine plastic, waste tracking, pollution) was conducted using the search words deep learning OR machine learning OR computer vision AND ocean waste OR marine plastic OR waste tracking OR pollution in both Web of Science and Scopus. On the Web of Science, the initial search yielded 17,212,791 documents. This was reduced to 397,614 papers when further criteria such as the choice of years of study (2004–2024, with 2024 data representing partial-year coverage (January–October)) and journals (Sustainability, Environmental Science and Pollution Research, Sensors, Applied Sciences, Remote Sensing, Energies, IEEE Access, Water, and others) were applied. Figure 1 shows the summary of the search process and the outcomes. As seen in Figure 1, when the language was set to English and the search filtered open-access publications, the results drastically reduced to 10,174 documents, which were downloaded for further screening. When the exact search terms (“deep learning OR machine learning OR computer vision AND ocean waste OR marine plastic OR waste tracking OR pollution”) were used with Scopus, the initial search revealed 1487 documents. This was limited to all the studies published between 2004 and 2024, limiting the subject area to environmental science, engineering, computer science, agricultural and biological science, earth and planetary science, physics and astronomy, chemical engineering, decision science, multidisciplinary studies, and energy. All the published papers in English, spanning articles, reviews, conference papers, book chapters, and books, were obtained, resulting in a total of 1234 documents ready to be exported for further screening. In each database, the exported data included bibliographic data like titles, authors, publication dates, abstracts, keywords, and citation counts for all relevant articles.
The Web of Science (WOS) and Scopus yielded 11,408 papers, of which 999 were duplicates. As seen in Figure 1, 10,409 records were finally included for this review. After collecting and refining the dataset, several bibliometric analysis tools were utilised to analyse the extracted data and derive insights into the research landscape [25]. This study used three distinct software applications: Microsoft Excel, Python JupyterLab (JupyterLab Desktop 4.0.5-1 accessed between 17–19 December 2024), and VOSviewer 1.6.20. Microsoft Excel was used to organise the data and clean it for the removal of duplicates and irrelevant materials. These materials, tagged as irrelevant, either do not specifically concern the application of artificial intelligence (AI) in ocean waste tracking or do not even mention the subject. The tool VOSviewer was used to visualise co-authorship networks, keyword co-occurrence, and citation maps. VOSviewer enables researchers to create graphical representations of collaborative relationships and identify influential authors and institutions. This tool was employed to analyse citation networks and detect emerging trends in the field. This study used Python JupyterLab for additional quantitative analysis to perform descriptive statistics, such as publication count by year, country, and institution. The analysis examined the growth in the number of publications over time to identify periods of increased research activity [26]. This study analysed citation counts to determine the impact of specific papers, authors, and institutions on the field. This study identified the main research topics and emerging areas of interest by mapping frequently used keywords. This analysis helps recognise shifts in focus, such as the increasing application of deep learning for waste detection. This study included co-authorship and collaboration network analyses to identify influential researchers and assess the level of interdisciplinary collaboration. This metric is essential for understanding how knowledge flows across different domains.
The methodology outlined provides a structured approach to analysing the existing literature on AI applications in sustainable ocean waste management. By leveraging advanced bibliometric tools and comprehensive data collection strategies, this study aims to offer insights into the current state of research, collaboration networks, and emerging trends in this rapidly evolving field [27,28]. The results of this analysis can inform future studies, policymaking, and technological advancements aimed at improving ocean health through the application of AI.

3. Bibliometric Analysis Results

3.1. Publications by Year

Publications around AI and ocean waste have received massive attention from researchers, with tens of thousands of studies focussing on the subject matter over the years. As the years approach the present, the rate of publications related to the application of AI to waste tracking also increases. Figure 2 visually showcases these trends, highlighting periods of exponential growth and recent fluctuations. It shows that publications between 2004 and 2024 totalled 10,408, emphasising the extensive research conducted over two decades and underlining the subject’s importance in academia and industry and the recent influx of many researchers into the subject area.
The data on the count of publications over the years (Figure 2) provide insight into the trend of research related to “the role of artificial intelligence in sustainable ocean waste tracking and management”. The number of publications has steadily increased from 2004 to 2023, indicating the growing interest in this research area and its relevance. A relatively low publication count (10 to 44) between 2004 and 2008 suggests that this period represents the early stages of exploration in this field. Moderate growth occurred between 2009 and 2012, with the publication count increasing from 52 to 69. Between 2013 and 2017, there was an increase from 66 publications in 2013 to 206 in 2017, demonstrating rising awareness and advancements in AI and environmental research. Research from 2018 to 2023 shows exponential growth, peaking in 2023 with 2176 publications. This period reflects the global push toward sustainability and the increasing adoption of AI. The highest number of publications to date occurred in 2023, with 2176 entries, marking the culmination of the rising trend. A slight decline is noted for 2024 (1936 publications), which could indicate a natural fluctuation in research activity or a potential impact of delayed publication or incomplete data for 2024. From the data, early-stage research (2004–2012) laid the foundation for the boom in the subsequent years. The dramatic increase post-2015 aligns with advancements in AI technologies, global environmental policies, and sustainability initiatives like the UN’s Sustainable Development Goals (SDGs). The high volume of recent publications highlights its position as a critical and evolving study area.

3.2. Journals of Publication

As indicated in Figure 2, AI and environmental studies have gained significant research and global attention in recent years. These research efforts have been made across many subject areas in journals like Sensors, Sustainability, IEEE Access, International Journal of Environmental Research and Public Health, and many others. This bibliometric search revealed 1511 sources, including journal articles, reviews, conferences, and book chapters, in which these studies have been published. Table 1 shows 20 such journals with more than 80 publications.
Both Table 1 and Figure 3 provide the top journals contributing to publications on AI and sustainable ocean waste tracking and management. SENSORS leads with 6.16% of the publications, reflecting its focus on sensor technologies critical for AI-based tracking systems in environmental research. SUSTAINABILITY follows with 5.67% of the publications, emphasising sustainable development and environmental management. IEEE ACCESS ranks third with 5.02% of the publications, highlighting the significant role of engineering and technological advances in this field. Journals like SENSORS, IEEE ACCESS, and ELECTRONICS focus on technological and engineering applications that align with AI and system-based innovations. Journals like SUSTAINABILITY, WATER, and FRONTIERS IN ENVIRONMENTAL SCIENCE emphasise sustainability, water management, and environmental impact, directly tying to ocean waste and ecological balance. Multidisciplinary journals such as SCIENCE OF THE TOTAL ENVIRONMENT and INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH bridge the gap between AI technology and its implications for public health and environmental safety.
FRONTIERS IN MARINE SCIENCE (1.15%) targets explicitly the marine ecosystem in relation to ocean waste tracking and management. TOXICS (1.01%) and ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH (1.15%) focus on pollution’s chemical and toxicological aspects. AI-driven approaches require substantial interdisciplinary research. Journals like BRIEFINGS IN BIOINFORMATICS (1.19%) suggest integrating computational techniques with environmental data analysis. The top five journals account for a considerable share (23.49%, 2680 publications), indicating concentrated efforts in leading journals. Others in the list (ranked 6–20) have lower numbers of contributions but still play crucial roles in addressing specific niches of AI applications, environmental safety, and sustainability. The wide range of journals highlights the topic’s interdisciplinary nature, bridging technology, sustainability, marine science, and public health. For foundational studies and trend-setting research, leading journals like SENSORS, SUSTAINABILITY, and IEEE ACCESS can be referred to; specialised journals like FRONTIERS IN MARINE SCIENCE provide niche insights into ocean-specific waste management.

3.3. Main Research Area

3.3.1. What Are the Main Research Areas in AI-Driven Ocean Waste Tracking and Management?

To determine the main research area of focus in AI-driven ocean waste tracking and management, we analysed the main subject areas where related works have been published and the co-occurrence of keywords.

3.3.2. The 20 Most Studied Subject Areas

The chart in Figure 4 displays the number of publications categorised by their respective research fields, focussing on AI-driven ocean waste tracking and management topics. The environmental sciences and ecology category has the most publications, indicating that this field is the most actively researched in AI-driven ocean waste tracking and management. This strongly emphasises sustainability, environmental impact, and ecological applications. Computer science ranks as the second most prolific category, which aligns with the role of AI and computational methods in waste tracking systems. The overlap between environmental sciences, ecology, and computer science points to interdisciplinary research combining technology with ecological studies. Categories such as “science and technology—other topics; environmental sciences and ecology”, “chemistry; engineering; instruments and instrumentation”, and “engineering telecommunications” highlight the diverse technological and scientific approaches employed. These intersections emphasise that advancements in this field rely on tools like remote sensing, data analytics, and instrumentation. Categories like “environmental sciences and ecology”, “public, environmental, and occupational health”, and “toxicology” reflect concerns about ocean waste’s human and environmental health impacts, which suggests a focus on the societal implications of waste management strategies.
The chart includes fields such as marine and freshwater biology, biotechnology, and applied microbiology, which indicate research interest in understanding the biological impacts of ocean waste and exploring biotechnological solutions for waste management. Geology, remote sensing, imaging science, and photographic technology point to satellite imagery and other sensing technologies for monitoring ocean waste distribution. The inclusion of “science and technology—other topics; energy and fuels” may signify research on converting ocean waste into energy, an innovative approach to waste management.
The chart highlights the multidisciplinary nature of AI-driven ocean waste tracking and management research, with contributions from environmental sciences, computer science, engineering, and health sciences. The focus on environmental sciences and ecology reinforces the importance of sustainability and conservation in this domain. The substantial role of computer science reflects the growing reliance on AI and computational tools for innovative solutions. Emerging areas like marine biology, remote sensing, and biotechnology signal potential future directions for research and innovation. This result underscores the need for continued interdisciplinary collaboration to address the complexities of ocean waste management through AI and other advanced technologies.

3.3.3. Co-Occurrence Analysis of Keywords

The charts in Figure 5a,b show the VOSviewer visualisation (a keyword co-occurrence network), which shows clusters of terms related to a search on AI-driven ocean waste tracking. Each node in the map represents a keyword or term found in the search. The size of each node indicates the frequency of the keyword. Larger nodes are more frequently mentioned in the articles. Different colours represent different clusters of related keywords. The red cluster focusses on topics related to microplastics and environmental pollution. The green cluster focusses on air quality, air pollution, and human health. The blue cluster focusses on technological aspects like machine learning and computer vision. The lines between the nodes indicate co-occurrences of terms, showing how often two keywords appear together in the same articles. Thicker lines represent stronger connections, meaning those terms are more frequently associated with each other.
The mapping results indicate that numerous AI-driven technologies have been employed in tracking and cleaning debris and waste from the marine environment. The map shows the application of deep learning, machine learning, computer vision, and other significant AI types to maintain a sustainable ocean environment. The term “machine learning” is prominently displayed, indicating it is a central term within ocean-cleaning-related research. The map highlights that AI (like machine learning and deep learning) is heavily discussed in the context of environmental monitoring, pollution, and sustainability.
The entries in Table 2 reveal that machine learning and deep learning are the most applied artificial intelligence technologies in environmental management, especially marine ecosystem maintenance. The link strength indicates (4346, 2913) that these AI types are widely connected to environmental pollution control and marine ecosystem cleaning factors.
The yellow-coloured nodes in Figure 5a represent phrases that have become increasingly common in recent years (2015–2024), indicating a clear trend. The employment of terms like “optimization”, “data analytics”, “digitalization”, and “renewable energy” demonstrates how environmental and public health issues are becoming increasingly prominent in academic discourse. This trend indicates that researchers are responding to pressing social and ecological problems by using AI (ML or DL) to conduct studies with real-world implications rather than abstract theoretical frameworks; this highlights AI’s flexibility and usefulness in addressing new environmental problems. This inclination is beneficial because it keeps research focussed on the world’s needs, allowing us to tackle difficulties with ecological data processing and monitoring using novel approaches.

3.4. Publications by Institutions

This section features publications by institutions, particularly institutions from which more than two documents have been sampled in this review. The bar chart in Figure 6 illustrates the number of publications per institution related to AI-driven ocean waste tracking and management in a sample of the 10 top institutions. The Universal Village Society in Cambridge, United States, leads in the number of publications, which suggests that the institution is heavily engaged in research addressing sustainable and innovative solutions for ocean waste management using AI. In Figure 6, institutions from various regions are represented:
  • ▪ United States: The Universal Village Society and the University of Minnesota dominate the United States;
  • ▪ China: Multiple institutions, such as South China University of Technology, Shenzhen University, and Hangzhou Dianzi University, actively contribute publications;
  • ▪ Australia: The University of Adelaide;
  • ▪ United Kingdom: Warwick Manufacturing Group, University of Warwick;
  • ▪ Singapore: Singapore Institute of Manufacturing Technology;
  • ▪ Germany: Friedrich–Alexander University Erlangen–Nürnberg.
This global diversity underscores the widespread recognition of ocean waste management as a critical international issue. Chinese institutions feature prominently, reflecting the country’s growing focus on integrating AI into environmental management and sustainability efforts. The College of Computer Science and Software Engineering (Shenzhen University) and the School of Civil Engineering and Transportation (South China University of Technology) indicate an interdisciplinary approach, combining AI technology with engineering solutions. Including the Department of Civil, Environmental, and Ocean Engineering (Stevens Institute of Technology) suggests the presence of research that bridges civil and environmental engineering for ocean waste solutions.
While these institutions are leaders, the absolute number of publications per institution is relatively small, likely due to this research field’s niche and emerging nature. The Universal Village Society is a potential hub for international collaboration on sustainable technologies. Multiple Chinese institutions indicate significant investment in AI and environmental sustainability research. Institutions from diverse regions signal the potential for global partnerships to advance AI-driven ocean waste management technologies. The small publication numbers suggest that this field is still developing, with room for further contributions from established and new research centres. These data highlight the importance of fostering global cooperation and investing in interdisciplinary research to address the pressing challenge of ocean waste management effectively.

3.5. Countries of Top Publications

The publications finally included from the search were obtained from eighty distinct countries. Ten countries with the most publications were selected and sampled, as seen on the map in Figure 7. The chart in Figure 8 presents the top 10 countries by the number of publications related to AI-driven ocean waste tracking and management. China dominates with over 200 publications, far surpassing other countries. This highlights its substantial investment in research and innovation focussed on environmental sustainability and AI applications. The United States follows with approximately 175 publications, showcasing its significant role in advancing AI technologies and environmental management. India ranks third, reflecting its growing focus on sustainability and technological research. The United Kingdom and Australia complete the top five, each contributing a notable volume of publications, emphasising their active research environments. Italy, Germany, and Spain are the only European countries on the list, demonstrating the region’s engagement with AI and environmental issues. The inclusion of countries like Canada, South Korea, and others reflects the worldwide recognition of the need for innovative approaches to ocean waste management.
China’s lead may be attributed to its emphasis on addressing pressing environmental challenges using cutting-edge technologies, which is supported by its significant funding and policy focus. As a leader in AI research and technology, the U.S.’s substantial contribution highlights its commitment to tackling global environmental issues. Countries like India and South Korea are emerging as key players, indicating a shift towards more inclusive global participation in solving environmental challenges. While the top contributors dominate, other countries can potentially increase their involvement, particularly in regions heavily impacted by ocean waste.

3.6. Citation Analysis of Cited Journals

The citation analysis of cited journals in Table 3 and Figure 9 highlights the most influential journals in AI-driven ocean waste tracking and management. Science of the Total Environment has the highest citation count (791) and link strength (91.48), indicating its significant influence and interconnectedness in the research network. It covers interdisciplinary environmental research that is highly relevant to ocean waste tracking. Although Remote Sensing has slightly more documents than Science of the Total Environment, it has fewer citations (436), suggesting that it is widely used but newer or less cited overall. Its focus on spatial data analysis explains its importance in waste tracking.
Sustainability (Switzerland) emphasises sustainability research, making it relevant for discussions on the ecological impact of and solutions for ocean waste management. Dedicated to marine science, Marine Pollution Bulletin provides valuable insights specific to ocean pollution, contributing significantly to the field’s development. Although the Journal of Marine Science and Engineering has fewer citations, its strong link strength suggests it plays a specialised but pivotal role in the research community. Publications from Sensors are crucial for technological developments, particularly in sensor systems used in AI-driven waste tracking.
IEEE Access is known for publishing high-quality engineering and technology-related research; its strong citation count highlights its relevance for AI-related methodologies. Environmental Science and Pollution Research specialises in environmental pollution research, reflecting its role in assessing and addressing ocean waste. Journal of Cleaner Production focusses on sustainable production processes; its high citation count relative to its document count suggests it has influential papers in this domain. This analysis demonstrates the diversity of research approaches and the multidisciplinary nature of AI-driven ocean waste tracking.

3.7. H-Index Analysis of the Cited Journals

To evaluate the prominence and impact of journals contributing to AI in sustainable ocean waste tracking and management, we analysed the H-index of selected journals using the Scimago Journal & Country Rank database. The H-index is a metric that reflects the productivity and citation impact of a journal, researcher, or publication. It measures the number of publications (H) cited at least H times, reflecting the journal’s overall influence in the academic community. As shown in Table 3, useful articles relating to AI in sustainable ocean waste tracking are dominated by journals like Science of the Total Environment (H-index: 353) and Journal of Cleaner Production (H-index: 309). Their high H-index reflects their significant influence on sustainability research, including AI and ocean waste management topics. Generalist journals such as Science of the Total Environment and Journal of Cleaner Production cover various environmental topics, including AI applications. Specialised journals like the Marine Pollution Bulletin (H-index: 229) and Journal of Marine Science and Engineering (H-index: 51) focus more narrowly on marine- and ocean-specific research. This distinction highlights the interdisciplinary nature of research in ocean waste management. Journals such as Remote Sensing (H-index: 193) and Sensors (H-index: 245) emphasise technological advancements, particularly in AI-driven waste detection and monitoring tracking systems.
MDPI journals like Sustainability (Switzerland) and Sensors are significant contributors, often emphasising open-access models that enable wider dissemination of research findings. Elsevier and Springer’s journals have high H-indices, underscoring their established reputation for high-quality publications. The dominance of journals with high H-indices, as summarised in Figure 10, demonstrates the growing interest and importance of AI applications in addressing environmental challenges like ocean waste. Emerging researchers can leverage these journals as reliable platforms to publish and access high-impact studies in this emerging field. The diverse focus of these journals, from technological innovation to sustainability solutions, highlights the multidisciplinary nature of this research area. The H-index analysis underscores the significance of publishing and referencing research in high-impact journals to advance the role of artificial intelligence in sustainable ocean waste tracking and management. This metric is a valuable guide for researchers, policymakers, and practitioners to prioritise influential studies and foster impactful collaborations.

3.8. Co-Citation Analysis of Authors

The analysis was divided into many clusters. The major clusters are the ones with the colours red and green, with massive nodes representing authors with prominent works whose impact on AI and environmental pollution control, especially in the marine ecosystem, have been referenced in much research.
The co-citation analysis identifies influential researchers whose work is frequently referenced together, demonstrating their foundational contributions. From the red clusters in Figure 11, it is observed that authors like those of Ref. [24] of Optoelectronic System Laboratory, Institute of Semiconductors, Chinese Academy of Sciences, Beijing, China, with works like “Mask-guided deep learning fishing net detection and recognition based on underwater range-gated laser imaging and Analysis of recent techniques in marine object detection: a review” Ref. [28] of CCCC First Highway Consultants Co., Ltd., Xi’an, China, and Ref. [29] appear prominently, showing their research forms a theoretical or practical backbone for AI in waste management. This may include pioneering studies integrating AI into remote sensing or waste classification. From the green cluster, it is observed that authors like Thompson R.C. referenced in publications like “Comparison of Learning Models to predict LDPE, PET, and ABS concentrations in beach sediment based on spectral reflectance” by Ref. [25], While [30] developed a laboratory-based rapid mass conversion method for environmental microplastics of diverse shapes without direct focus on the marine environment but is applicable, [31] specifically investigated the distribution and density of seafloor macrolitter in the eastern Red Sea, providing field-based marine pollution insights." and many other works like “Large-scale detection of marine debris in coastal areas with Sentinel-2” by Refs. [32,33], Refs. [34,35,36,37,38], and others, and Goncalves G. in Refs. [37,39,40] likely contribute to waste ecology, suggesting a link between AI modelling and its environmental impacts. The connections among various clusters indicate an evolving body of work where AI technologies are applied across domains, including underwater robotics, waste detection systems, and autonomous vehicles for marine clean-up operations.

3.9. Bibliographic Coupling

Table 4, analysing the most-cited journals, provide a snapshot of how research on AI’s role in ocean waste management is concentrated across interdisciplinary domains. Science of the Total Environment leads with 791 citations, reflecting a significant focus on environmental systems and sustainability. AI-based tracking solutions, such as satellite monitoring and waste flow predictions, are likely central to these publications. Remote Sensing (436 citations) highlights the integration of AI with geospatial technologies like satellite imagery and drone-based monitoring, emphasising its role in identifying and mapping waste in oceans. Sustainability (Switzerland) and Marine Pollution Bulletin emphasise how AI supports sustainability efforts, such as smart waste classification and predicting pollution trajectories. Journals such as Sensors (362 citations) and IEEE Access (633 citations) are more technical, suggesting a focus on sensor-based technologies and machine learning algorithms for real-time data collection and ocean waste tracking. Applied Sciences (Switzerland) and the Journal of Cleaner Production are interested in developing AI models that balance economic and environmental considerations in waste management practices. While journals like Science of the Total Environment lead in citations, there is an opportunity to expand AI’s role in niche areas like predictive modelling of waste flows or autonomous ocean-cleaning systems. Research heavily cited in journals such as Sensors and IEEE Access suggests AI’s potential in real-world systems, such as deploying drones and IoT devices for tracking marine debris and forecasting pollution patterns.
Figure 12 depicts a bibliographic coupling network where journals are connected based on the overlap of their referenced works. This visualisation provides insights into the interconnections and shared intellectual foundations among the prominent journals contributing to this research area. Journals such as Science of the Total Environment, Remote Sensing, and Marine Pollution Bulletin are central in the network. This centrality highlights their significant role in publishing foundational or widely cited research on environmental sustainability, ocean management, and the integration of AI technologies. The connections (lines) between journals indicate shared citations or similar references. For example, Science of the Total Environment connects strongly with Marine Pollution Bulletin and Journal of Cleaner Production, showing shared research interests in environmental monitoring and sustainable practices. Remote Sensing and Sensors are closely linked, emphasising their focus on AI-driven technologies like satellite monitoring, IoT devices, and data processing for ocean waste tracking.
The colour gradient (i.e., moving from blue to yellow) likely represents the time dimension, indicating when specific studies gained prominence. Journals like IEEE Access and Applied Sciences (Switzerland) show recent contributions, reflecting the rising focus on applying AI and advanced technologies in sustainable waste management. Journals such as Sustainability (Switzerland) and Environmental Science and Pollution Research bridge disciplines, integrating AI innovations with sustainability and pollution control, indicating the multidisciplinary nature of this field. This network demonstrates how journals in the environmental and technological domains converge on shared challenges in ocean waste tracking and management. Specifically, IEEE Access highlights recent technological breakthroughs in addressing waste tracking, including machine learning, robotics, and IoT solutions.

4. Emerging Trends

Artificial intelligence (AI) integration in addressing ocean waste management has seen significant advancements in recent years, focussing on waste tracking, real-time monitoring, predictive modelling, and sustainable disposal solutions [41,42]. Research in AI-driven ocean waste tracking revolves around four major themes: waste tracking, real-time monitoring, predictive modelling, and sustainable disposal solutions. One of the core applications of AI in ocean waste management is tracking waste in marine environments [43]. Studies have focussed on using machine learning and deep learning to identify and classify different types of waste, such as plastics, fishing gear, and other debris. These AI systems utilise satellite imagery, drones, and underwater sensors to detect and map the spread of waste in the ocean. Real-time monitoring is essential to assessing the scale and movement of ocean waste. Researchers have explored the use of AI to process data from various sources, including sensors and IoT devices, to provide continuous updates on waste concentration, location, and trends. This enables more effective intervention and management of oceanic waste in real time. Predictive models powered by AI algorithms, such as deep learning and reinforcement learning, are being developed to forecast waste accumulation patterns in specific ocean regions [44,45]. These models analyse historical waste data, ocean currents, and environmental factors to predict where and when waste will accumulate, allowing for targeted waste management interventions. Finally, AI contributes to identifying sustainable waste disposal solutions by simulating different waste management strategies. By evaluating the effectiveness of various approaches, AI systems can optimise collection and recycling processes, contributing to the circular economy and reducing the environmental impact of oceanic waste [46,47].
Despite significant progress, several gaps still need to be addressed in the application of AI for ocean waste tracking and management. One key gap is the limited application of AI in remote and under-explored ocean regions [48]. AI solutions have primarily been implemented in well-monitored coastal areas, leaving vast ocean expanses to be understood. Expanding AI systems to cover less-explored regions could provide a more comprehensive understanding of global ocean pollution patterns. Another gap is the under-explored use of AI techniques for waste management, such as reinforcement learning and unsupervised learning [49]. Most research focusses on supervised machine learning methods, which require labelled data. However, many ocean waste scenarios need more labelled data, making unsupervised and reinforcement learning methods an exciting area for future exploration. Finally, there is a need for better integration of AI with environmental policy frameworks. Although AI has proven effective in waste management, its implementation often needs more collaboration with policymakers and environmental agencies [50].
This study offers bibliometric insights into the utilisation of AI for ocean waste detection; however, it would benefit from explicitly linking these insights to practical challenges in real-world applications. Four primary research clusters identified through bibliometric mapping encompass deep learning for marine litter detection, the integration of remote sensing and satellite data, AI-enhanced marine robotics and autonomous monitoring, and intelligent waste management utilising predictive modelling. These research domains align with innovative trajectories in academia; however, their conversion into practical solutions involve several implementation challenges. These challenges encompass data quality and accessibility, scalability of prototypes, integration into policy and practice, cybersecurity, model resilience, interoperability, and infrastructure.
Adversarial robustness and model reliability are insufficiently addressed, without safeguards, and AI tools may be vulnerable to image perturbation, sensor spoofing, or data poisoning, jeopardising reliability in real-time marine monitoring. Interoperability and infrastructure are fragmented due to disparate research initiatives and the lack of unified testbeds or benchmark standards.
This study highlights a notable translation gap by linking bibliometric themes with practical realities. Despite increasing academic interest in AI applications for ocean waste, implementation is hindered by data deficiencies, infrastructural shortcomings, governance readiness, and algorithmic robustness. Rectifying this disparity requires cooperative efforts among researchers, policymakers, technologists, and environmental stakeholders. Future research should focus on developing frameworks that align AI-based solutions with legal and regulatory structures for more effective and sustainable ocean waste management.

5. In-Depth Analysis of Key Literature

5.1. AI Applications in Ocean Waste Tracking and Management

Researchers, environmental groups, and governments are addressing the pressing issue of marine pollution in a new way thanks to the application of artificial intelligence (AI) in ocean waste tracking and management [51,52]. As shown in Figure 5a,b, artificial intelligence (AI) offers creative ways to improve detection, monitoring, and management techniques in response to the ever-increasing threat that waste, especially plastics, poses to the oceans. This helps to maintain sustainable marine ecosystems. With an emphasis on waste identification, predictive analytics, robots, and data integration, this section examines the numerous uses of AI in ocean waste management.
One of the most significant applications of AI in ocean waste management is its ability to detect and monitor marine debris [53]. AI algorithms, especially machine learning (ML) and deep learning (DL) models, have effectively identified waste in vast oceanic areas. These technologies analyse patterns in large datasets to automatically recognise debris from various sources, such as satellite imagery and aerial photos, reducing the need for manual inspection. Satellite- and drone-based remote sensing combined with AI algorithms allow for high-resolution monitoring of large water bodies [54]. Using convolutional neural networks (CNNs), researchers can process satellite images to detect plastic patches and other pollutants in the ocean. These systems are trained to distinguish between natural ocean elements (like seaweed or foam) and waste materials, achieving high accuracy in real-time detection. Deep learning models excel in processing complex image data, making them ideal for identifying marine waste in challenging environments [55]. For example, DL models can be trained on labelled datasets of marine images, learning to identify different types of debris, even in low-visibility conditions. By deploying AI-driven remote sensing, scientists can gain a more accurate picture of the extent and location of marine pollution, which is crucial for planning effective clean-up operations [56,57].
AI is also crucial in predicting ocean waste accumulation and distribution patterns. Traditional methods of monitoring waste rely on historical data, which may not accurately reflect dynamic changes in the marine environment [58]. In contrast, AI models can analyse large volumes of historical and real-time data to forecast where the waste will likely accumulate. Machine learning algorithms, such as random forests and gradient boosting, are used to predict the movement of marine debris based on ocean currents, wind patterns, and other environmental factors [59,60]. These models enable proactive waste management strategies by identifying areas with a high likelihood of waste buildup. Predictive analytics can inform decision-makers about the best times and locations for deploying waste collection resources, thus optimising the efficiency of clean-up efforts [61,62]. For instance, AI-driven models can help prioritise regions most vulnerable to pollution, allowing for timely intervention before waste disperses further. These predictive capabilities are instrumental in reducing the long-term impact of waste on marine ecosystems by enabling targeted clean-ups and prevention measures.
Integrating AI with robotics and autonomous systems transforms how ocean waste is collected and managed. Autonomous underwater vehicles (AUVs) and drones equipped with AI technology are increasingly used to detect and collect marine debris [63,64]. AUVs and AI-powered drones can operate in challenging marine environments, identifying and collecting waste with minimal human intervention. These systems use computer vision algorithms to detect waste in real time and adapt their operations, enhancing waste collection efficiency. AI enables robots to make autonomous decisions based on real-time data. For example, AUVs can adjust their routes dynamically in response to new waste sightings or changes in ocean conditions, optimising their collection efficiency. Using reinforcement learning, these systems can improve their waste collection strategies over time, learning from previous missions to enhance future performance. Robotic systems integrated with AI reduce the need for human involvement in hazardous clean-up operations and offer scalability, making it possible to address ocean waste at a larger scale [65,66].
In ocean waste management, big AI-powered data analytics is increasingly vital for tracking waste sources, movement, and accumulation over time [67]. AI’s ability to process vast amounts of data from multiple sources allows for a more comprehensive understanding of marine pollution. AI algorithms integrate data from various sources, including satellite imagery, drones, AUV sensors, and oceanographic databases. Combining these datasets allows AI to create a holistic view of ocean waste patterns, providing valuable insights for policymakers and environmental organisations [68]. Machine learning models can analyse temporal and spatial data to identify waste generation and accumulation trends. This helps in understanding the impact of human activities on marine ecosystems and enables the development of more effective waste management policies. Furthermore, natural language processing (NLP) techniques can extract information from the scientific literature and reports, adding another layer of data for comprehensive analysis. By leveraging AI-driven data integration and analytics, stakeholders can develop more effective waste management strategies and policies, aligning them with sustainability goals [69]. For instance, the government of Cambodia, the World Bank, and some researchers started a project to lower plastic pollution in rivers, canals, and beaches and improve waste management in two main cities, Siem Reap and Sihanoukville. The Marine Perception research group at Oldenburg, affiliated with the German Research Center for Artificial Intelligence (DFKI), has created a drone-based system for monitoring environmental pollution. The drones, outfitted with sensor technology, are employed along waterways to detect potential issues and document the entire region. Drones equipped with multispectral cameras identify plastic waste in rivers and on beaches, categorising waste types through a classification catalogue. The gathered data assisted the Cambodian government in formulating and executing a plastic action plan to prevent future plastic pollution (https://en.reset.org/articles/, 21 April 2025).
The application of AI in ocean waste tracking and management offers promising solutions to the global issue of marine pollution. AI algorithms, predictive models, autonomous systems, and big data analytics collectively enhance the capabilities for waste detection, monitoring, and intervention [70]. By leveraging these technologies, researchers and practitioners can optimise waste management efforts, ultimately contributing to the protection and sustainability of marine environments. As AI technology advances, its integration into ocean waste management strategies will likely become even more critical, driving innovations that can help preserve the health of the world’s oceans [71,72]. Those involved in ocean waste management still have much to learn about newly developing artificial intelligence paradigms, including federated learning (FL) and reinforcement learning (RL). Using autonomous decision-making in marine drones to navigate challenging ocean currents to track or gather waste, RL could improve by training models on distributed sensor data without centralised access [73]. FL presents an opportunity for integration across regional marine monitoring systems while preserving privacy. Though not well known in current research, these approaches deserve future study as infrastructure and artificial intelligence readiness in marine monitoring advances.

5.2. Challenges and Limitations of AI in Ocean Waste Tracking and Management

Artificial intelligence (AI) could significantly advance ocean waste tracking and management, but to fully realise its potential, several issues need to be resolved [73]. These difficulties include problems with data quality, resource restrictions, technology constraints, and regulatory matters. Since these present obstacles to the efficient use of AI in sustainable ocean waste management, they must be addressed for AI-driven solutions to reach their full potential.
A key challenge in leveraging AI for ocean waste management is the quality and availability of data. AI systems require large, high-quality datasets to function effectively, yet the complexity and dynamic nature of ocean environments make data collection particularly difficult [74]. Marine environments are often challenging to monitor comprehensively, with sensors and satellite imagery facing limitations due to water turbidity, varying depths, and weather conditions [75]. This can lead to incomplete or inaccurate datasets, affecting the accuracy of AI models that rely on such data. For instance, AI-based image recognition algorithms might misidentify or fail to detect marine debris under poor-visibility conditions, leading to erroneous waste tracking. In many regions, especially in remote or less-studied areas, limited data are available for informing AI algorithms. The lack of consistent, real-time monitoring further exacerbates the issue, limiting the potential for AI to provide predictive analytics or track ocean waste over time [76]. Without standardised methods for data collection, integrating data from diverse sources and ensuring their compatibility becomes a significant challenge.
The application of AI in ocean waste management also faces technological and computational barriers that can hinder the scalability and effectiveness of AI systems [77]. Many AI models, particularly those based on deep learning, require substantial computational power to process large datasets. While these models can work well in controlled environments, their application in vast, unpredictable marine settings presents challenges. The scale of data generated from ocean monitoring, such as satellite imagery and sensor readings, demands robust infrastructure that may only sometimes be available in remote locations or at sea. AI-driven systems such as drones and autonomous underwater vehicles (AUVs) must operate in harsh and unpredictable ocean conditions. These systems must resist saltwater corrosion, extreme pressures, and rapid environmental changes. Developing AI models that can function effectively under these conditions without frequent technical malfunctions remains a significant challenge for large-scale implementation in marine environments [78,79].
The use of AI technologies in ocean waste management raises several regulatory and ethical concerns, particularly about data privacy, security, and governance. AI systems often rely on large-scale data collection, including satellite imagery, sensor data, and environmental monitoring inputs [16]. As these data may sometimes involve sensitive information, there are concerns about the privacy of data collected from marine environments and human activities. Data security is vital to preventing potential misuse of or unauthorised access to the information collected by AI-driven systems. Implementing AI in ocean waste management must comply with existing environmental regulations, which can vary significantly across jurisdictions. For example, countries have varying laws concerning data sharing, environmental protection, and marine pollution. Aligning AI-based solutions with these diverse regulations is a complex task and could slow the adoption of AI technologies in ocean waste tracking and management.
Finally, the costs and resource constraints associated with implementing AI technologies in ocean waste management are significant barriers to widespread adoption. The development and deployment of AI-driven systems, such as drones, AUVs, and satellite imaging technologies, require substantial financial investment [80]. These technologies often involve expensive hardware, software, and data storage infrastructure. The initial costs of implementing AI-based systems can be prohibitively high for many organisations, especially in developing countries or underfunded research institutions. In addition to the upfront costs, maintaining and operating AI systems in the field demands sustained resources. This includes data processing capabilities, technical expertise, and energy consumption. For instance, AUVs and drones used in ocean waste management require regular maintenance and updates to ensure optimal performance, adding to the overall cost of these technologies. AI-driven waste management systems can improve energy efficiency by enhancing algorithms using edge computing for local data processing, implementing adaptive sampling to reduce unnecessary processing, and developing energy-conscious scheduling mechanisms to prioritise tasks based on energy consumption and urgency.
While AI presents significant potential for revolutionising ocean waste management, several challenges must be addressed [81]. Improving data quality, overcoming technological limitations, addressing regulatory concerns, and managing financial constraints are essential to making AI solutions more effective, accessible, and sustainable in marine waste tracking and management.

5.3. Limitations of the Methodologies Applied

Despite the strengths of the bibliometric approach used in this study, several methodological limitations should be acknowledged. First, the reliance on data from specific databases such as Scopus and Web of Science inherently limits the scope of the analysis, as not all the relevant literature may be indexed within these platforms. This can exclude important regional or non-English-language publications, introducing potential bias. Second, this study’s findings are influenced by the quality and consistency of metadata (e.g., author names, affiliations, and keywords), which can sometimes be inconsistent or incomplete, affecting the accuracy of network visualisations and trend analysis. Third, while helpful, bibliometric indicators such as publication counts and citation frequencies do not fully capture research outputs’ quality, novelty, or practical impact. Additionally, the methodology focusses primarily on quantitative aspects and does not incorporate qualitative insights, which could provide deeper context and interpretation. These limitations suggest the need for a more integrated approach in future research, combining bibliometric data with expert evaluation and content analysis.

6. Conclusions

The bibliometric approach used highlights the growing interest in artificial intelligence (AI) for ocean waste management. Recent publications show a surge in publications on AI-driven solutions for identifying, monitoring, and managing marine debris. Key research topics include predictive analytics for waste distribution, robot integration for waste collection, and machine learning and deep learning algorithms for waste detection. Despite geographic and resource inequities, leading institutions and nations contribute significantly to this field.
AI’s contribution to sustainable environmental management is substantial, offering innovative approaches to tackling the persistent challenge of ocean pollution. Using AI for real-time monitoring, predictive waste tracking, and optimising waste management interventions presents a promising avenue for more effective and sustainable ocean management. Moreover, AI’s potential for integrating diverse datasets from satellite imagery to sensor data enables more comprehensive waste tracking and a deeper understanding of oceanic waste patterns.
Looking to the future, AI’s role in ocean sustainability is poised to expand further. AI models will become more sophisticated, scalable, and adaptable to dynamic and harsh marine environments as technology advances. The ongoing development of autonomous systems and the integration of big data analytics are expected to significantly enhance ocean waste management practices. However, challenges such as data quality, technological scalability, regulatory compliance, and cost constraints must be addressed to unlock the full potential of AI. With concerted efforts to overcome these barriers, AI could play a transformative role in achieving cleaner oceans and a more sustainable future.

Funding

This research was funded by the University of South Africa.

Conflicts of Interest

The authors declare no conflict of interest.

References

  1. Fleming, L.E.; Maycock, B.; White, M.P.; Depledge, M.H. Fostering human health through ocean sustainability in the 21st century. People Nat. 2019, 1, 276–283. [Google Scholar] [CrossRef]
  2. Battisti, C.; Poeta, G.; Romiti, F.; Picciolo, L. Small environmental actions need a problem-solving approach: Applying project management tools to beach litter clean-ups. Environments 2020, 7, 87. [Google Scholar] [CrossRef]
  3. Schmaltz, E.; Melvin, E.C.; Diana, Z.; Gunady, E.F.; Rittschof, D.; Somarelli, J.A.; Virdin, J.; Dunphy-Daly, M.M. Plastic pollution solutions: Emerging technologies to prevent and collect marine plastic pollution. Environ. Int. 2020, 144, 106067. [Google Scholar] [CrossRef] [PubMed]
  4. Sharma, H.B.; Vanapalli, K.R.; Samal, B.; Cheela, V.S.; Dubey, B.K.; Bhattacharya, J. Circular economy approach in solid waste management system to achieve UN-SDGs: Solutions for post-COVID recovery. Sci. Total Environ. 2021, 800, 149605. [Google Scholar] [CrossRef]
  5. Winterstetter, A.; Grodent, M.; Kini, V.; Ragaert, K.; Vrancken, K.C. A review of technological solutions to prevent or reduce marine plastic litter in developing countries. Sustainability 2021, 13, 4894. [Google Scholar] [CrossRef]
  6. Ditria, E.M.; Buelow, C.A.; Gonzalez-Rivero, M.; Connolly, R.M. Artificial intelligence and automated monitoring for assisting conservation of marine ecosystems: A perspective. Front. Mar. Sci. 2022, 9, 918104. [Google Scholar] [CrossRef]
  7. Altowayti, W.A.H.; Shahir, S.; Othman, N.; Eisa, T.A.E.; Yafooz, W.M.S.; Al-Dhaqm, A.; Soon, C.Y.; Yahya, I.B.; Rahim, N.A.N.B.C.; Abaker, M.; et al. The role of conventional methods and artificial intelligence in the wastewater treatment: A comprehensive review. Processes 2022, 10, 1832. [Google Scholar] [CrossRef]
  8. Gambin, A.F.; Angelats, E.; Gonzalez, J.S.; Miozzo, M.; Dini, P. Sustainable marine ecosystems: Deep learning for water quality assessment and forecasting. IEEE Access 2021, 9, 121344–121365. [Google Scholar] [CrossRef]
  9. El Mahrad, B.; Newton, A.; Icely, J.D.; Kacimi, I.; Abalansa, S.; Snoussi, M. Contribution of remote sensing technologies to a holistic coastal and marine environmental management framework: A review. Remote Sens. 2020, 12, 2313. [Google Scholar] [CrossRef]
  10. Glaviano, F.; Esposito, R.; Di Cosmo, A.; Esposito, F.; Gerevini, L.; Ria, A.; Molinara, M.; Bruschi, P.; Costantini, M.; Zupo, V. Management and sustainable exploitation of marine environments through smart monitoring and automation. J. Mar. Sci. Eng. 2022, 10, 297. [Google Scholar] [CrossRef]
  11. Bhatia, S.; Bansal, D.; Patil, S.; Pandya, S.; Ilyas, Q.M.; Imran, S. A retrospective study of climate change affecting dengue: Evidences, challenges and future directions. Front. Public Health 2022, 10, 884645. [Google Scholar] [CrossRef]
  12. Kaandorp, M.L.A.; Ypma, S.L.; Boonstra, M.; Dijkstra, H.A.; van Sebille, E. Using machine learning and beach cleanup data to explain litter quantities along the Dutch North Sea coast. Ocean Sci. 2022, 18, 269–293. [Google Scholar] [CrossRef]
  13. Kostas, E.T.; Adams, J.M.; Ruiz, H.A.; Durán-Jiménez, G.; Lye, G.J. Macroalgal biorefinery concepts for the circular bioeconomy: A review on biotechnological developments and future perspectives. Renew. Sustain. Energy Rev. 2021, 151, 111553. [Google Scholar] [CrossRef]
  14. Ganesapillai, M.; Mondal, B.; Sarkar, I.; Sinha, A.; Ray, S.S.; Kwon, Y.-N.; Nakamura, K.; Govardhan, K. The face behind the COVID-19 mask—A comprehensive review. Environ. Technol. Innov. 2022, 28, 102837. [Google Scholar] [CrossRef]
  15. Trice, A.T.; Robbins, C.R.; Philip, N.P.; Rumsey, M.R. Challenges and Opportunities for Ocean Data to Advance Conservation and Management; Ocean Conservancy: Washington, DC, USA, 2021. [Google Scholar] [CrossRef]
  16. Himeur, Y.; Rimal, B.; Tiwary, A.; Amira, A. Using artificial intelligence and data fusion for environmental monitoring: A review and future perspectives. Inf. Fusion 2022, 86–87, 44–75. [Google Scholar] [CrossRef]
  17. Nishant, R.; Kennedy, M.; Corbett, J. Artificial intelligence for sustainability: Challenges, opportunities, and a research agenda. Int. J. Inf. Manag. 2020, 53, 102104. [Google Scholar] [CrossRef]
  18. D’amico, G.; Szopik-Depczyńska, K.; Dembińska, I.; Ioppolo, G. Smart and sustainable logistics of Port cities: A framework for comprehending enabling factors, domains and goals. Sustain. Cities Soc. 2021, 69, 102801. [Google Scholar] [CrossRef]
  19. Isabelle, D.A.; Westerlund, M. A review and categorization of artificial intelligence-based opportunities in wildlife, ocean and land conservation. Sustainability 2022, 14, 1979. [Google Scholar] [CrossRef]
  20. Mustafa, S.; Estim, A.; Tuzan, A.D.; Ann, C.C.; Seng, L.L.; Shaleh, S.R.M. Nature-based and technology-based solutions for sustainable blue growth and climate change mitigation in marine biodiversity hotspots. Environ. Biotechnol. 2019, 15, 1–7. [Google Scholar] [CrossRef]
  21. Pessin, V.Z.; Yamane, L.H.; Siman, R.R. Smart bibliometrics: An integrated method of science mapping and bibliometric analysis. Scientometrics 2022, 127, 3695–3718. [Google Scholar] [CrossRef]
  22. Bibri, S.E. Data-driven smart sustainable cities of the future: An evidence synthesis approach to a comprehensive state-of-the-art literature review. Sustain. Futur. 2021, 3, 100047. [Google Scholar] [CrossRef]
  23. Secundo, G.; Ndou, V.; Del Vecchio, P.; De Pascale, G. Sustainable development, intellectual capital and technology policies: A structured literature review and future research agenda. Technol. Forecast. Soc. Chang. 2020, 153, 119917. [Google Scholar] [CrossRef]
  24. Wohlin, C.; Kalinowski, M.; Felizardo, K.R.; Mendes, E. Successful combination of database search and snowballing for identification of primary studies in systematic literature studies. Inf. Softw. Technol. 2022, 147, 106908. [Google Scholar] [CrossRef]
  25. Zhang, Y.; Wang, X.; Sun, L.; Lei, P.; Chen, J.; He, J.; Zhou, Y.; Liu, Y. Mask-guided deep learning fishing net detection and recognition based on underwater range gated laser imaging. Opt. Laser Technol. 2024, 171, 110402. [Google Scholar] [CrossRef]
  26. Wang, B.; Yao, X.; Yang, M.; Zhang, R.; Huang, J.; Wang, X.; Dong, Z.; Zhao, H. Mechanical performance of 3D printed concrete in steam curing conditions. Materials 2022, 15, 2864. [Google Scholar] [CrossRef]
  27. Huda, F.R.; Richard, F.S.; Rahman, I.; Moradi, S.; Hua, C.T.Y.; Wanwen, C.A.S.; Fong, T.L.; Mujahid, A.; Müller, M. Comparison of learning models to predict LDPE, PET, and ABS concentrations in beach sediment based on spectral reflectance. Sci. Rep. 2023, 13, 6258. [Google Scholar] [CrossRef] [PubMed]
  28. Rußwurm, M.; Venkatesa, S.J.; Tuia, D. Large-scale detection of marine debris in coastal areas with Sentinel-2. iScience 2023, 26, 108402. [Google Scholar] [CrossRef]
  29. Yang, B.-C.; Zhao, Y.; Yao, T.-Y.; Zhou, Y.-J.; Jia, M.-Y.; Hu, H.-Y.; Xiao, C.-C. Summary of research on highway bridge vehicle force identification. Sustainability 2024, 16, 4469. [Google Scholar] [CrossRef]
  30. Chen, Q.; Yang, Y.; Qi, H.; Su, L.; Zuo, C.; Shen, X.; Chu, W.; Li, F.; Shi, H. Rapid Mass Conversion for Environmental Microplastics of Diverse Shapes. Environ. Sci. Technol. 2024, 58, 10776–10785. [Google Scholar] [CrossRef]
  31. Martynova, A.; Rodrigue, M.; Pieribone, V.; Qurban, M.; Duarte, C.M. Density and distribution patterns of seafloor macrolitter in the eastern Red Sea. Sci. Total Environ. 2024, 953, 176042. [Google Scholar] [CrossRef]
  32. Pellegrini, C.; Saliu, F.; Bosman, A.; Sammartino, I.; Raguso, C.; Mercorella, A.; Galvez, D.; Petrizzo, A.; Madricardo, F.; Lasagni, M.; et al. Hotspots of microplastic accumulation at the land-sea transition and their spatial heterogeneity: The Po River prodelta (Adriatic Sea). Sci. Total Environ. 2023, 895, 164908. [Google Scholar] [CrossRef] [PubMed]
  33. Sozio, A.; Scarrica, V.M.; Rizzo, A.; Aucelli, P.P.C.; Barracane, G.; Dimuccio, L.A.; Ferreira, R.; La Salandra, M.; Staiano, A.; Tarantino, M.P.; et al. Application of Direct and Indirect Methodologies for Beach Litter Detection in Coastal Environments. Remote Sens. 2024, 16, 3617. [Google Scholar] [CrossRef]
  34. Wang, R.; Record, N.R.; King, D.W.; Chowdhury, T. Designing A Sustainable Marine Debris Clean-up Framework without Human Labels. In Proceedings of the 7th ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies, New Delhi, India, 8–11 July 2024. [Google Scholar] [CrossRef]
  35. Castano-Londono, L.; Llorente, S.d.P.M.; Paipa-Sanabria, E.; Orozco-Lopez, M.B.; Montaña, D.I.F.; Montoya, D.G. Evolution of Algorithms and Applications for Unmanned Surface Vehicles in the Context of Small Craft: A Systematic Review. Appl. Sci. 2024, 14, 9693. [Google Scholar] [CrossRef]
  36. Su, L.; Dong, X.; Peng, J.; Cheng, H.; Craig, N.J.; Hu, B.; Li, J.-Y. Segmentation of beach plastic fragments’ contours based on self-organizing map and multi-shape descriptors: A rapid indication of fragmentation and wearing types. J. Hazard. Mater. 2024, 478, 135564. [Google Scholar] [CrossRef]
  37. Xie, H.; Zhang, Y.; Wu, Z.; Lv, T. A bibliometric analysis on land degradation: Current status, development, and future directions. Land 2020, 9, 28. [Google Scholar] [CrossRef]
  38. Baker, H.K.; Pandey, N.; Kumar, S.; Haldar, A. A bibliometric analysis of board diversity: Current status, development, and future research directions. J. Bus. Res. 2020, 108, 232–246. [Google Scholar] [CrossRef]
  39. Park, Y.E. A data-driven approach for discovery of the latest research trends in higher education for business by leveraging advanced technology and big data. J. Educ. Bus. 2021, 96, 291–298. [Google Scholar] [CrossRef]
  40. Agostini, L.; Nosella, A.; Sarala, R.; Spender, J.C.; Wegner, D. Tracing the evolution of the literature on knowledge management in inter-organizational contexts: A bibliometric analysis. J. Knowl. Manag. 2020, 24, 463–490. [Google Scholar] [CrossRef]
  41. Hoang, T.D.; Ky, N.M.; Thuong, N.T.N.; Nhan, H.Q.; Ngan, N.V.C. Artificial intelligence in pollution control and management: Status and future prospects. In Artificial Intelligence and Environmental Sustainability: Challenges and Solutions in the Era of Industry 4.0; Springer: Singapore, 2022; pp. 23–43. [Google Scholar]
  42. Mustapha, U.F.; Alhassan, A.; Jiang, D.; Li, G. Sustainable aquaculture development: A review on the roles of cloud computing, internet of things and artificial intelligence (CIA). Rev. Aquac. 2021, 13, 2076–2091. [Google Scholar] [CrossRef]
  43. Mumtaz, N.; Izhar, T.; Pandey, G.; Labhasetwar, P.K. Utilizing artificial intelligence for environmental sustainability. In Artificial Intelligence for Renewable Energy Systems; Woodhead Publishing: Sawston, UK, 2022; pp. 259–279. [Google Scholar] [CrossRef]
  44. Shahab, S.; Anjum, M. Solid waste management scenario in india and illegal dump detection using deep learning: An AI approach towards the sustainable waste management. Sustainability 2022, 14, 15896. [Google Scholar] [CrossRef]
  45. Tahmasebi, P.; Kamrava, S.; Bai, T.; Sahimi, M. Machine learning in geo-and environmental sciences: From small to large scale. Adv. Water Resour. 2020, 142, 103619. [Google Scholar] [CrossRef]
  46. Mahmoud, A.E.D.; Desokey, O. Artificial intelligence-based smart waste management for the circular economy. In Environmental Management Technologies; CRC Press: Boca Raton, FL, USA, 2022; pp. 341–358. [Google Scholar] [CrossRef]
  47. Kumar, R.; Verma, A.; Shome, A.; Sinha, R.; Sinha, S.; Jha, P.K.; Kumar, R.; Kumar, P.; Shubham; Das, S.; et al. Impacts of plastic pollution on ecosystem services, sustainable development goals, and need to focus on circular economy and policy interventions. Sustainability 2021, 13, 9963. [Google Scholar] [CrossRef]
  48. Fahlevi, M. A Systematic Literature Review on Marine Tourism in Business Management: State of the Art and Future Research Agenda. J. Tour. Serv. 2023, 14, 299–321. [Google Scholar] [CrossRef]
  49. Filom, S.; Amiri, A.M.; Razavi, S. Applications of machine learning methods in port operations—A systematic literature review. Transp. Res. Part E Logist. Transp. Rev. 2022, 161, 102722. [Google Scholar] [CrossRef]
  50. Zhang, A.; Venkatesh, V.; Liu, Y.; Wan, M.; Qu, T.; Huisingh, D. Barriers to smart waste management for a circular economy in China. J. Clean. Prod. 2019, 240, 118198. [Google Scholar] [CrossRef]
  51. Gupta, P.K.; Saxena, A.; Dattaprakash, B.; Sheriff, R.S.; Chaudhari, S.H.; Ullanat, V.; Chayapathy, V. Applications of Artificial Intelligence in Environmental Science. In Artificial Intelligence (AI); CRC Press: Boca Raton, FL, USA, 2021; pp. 225–240. [Google Scholar]
  52. Dwivedi, Y.K.; Hughes, L.; Kar, A.K.; Baabdullah, A.M.; Grover, P.; Abbas, R.; Andreini, D.; Abumoghli, I.; Barlette, Y.; Bunker, D.; et al. Climate change and COP26: Are digital technologies and information management part of the problem or the solution? An editorial reflection and call to action. Int. J. Inf. Manag. 2022, 63, 102456. [Google Scholar] [CrossRef]
  53. Maximenko, N.; Corradi, P.; Law, K.L.; Van Sebille, E.; Garaba, S.P.; Lampitt, R.S.; Galgani, F.; Martinez-Vicente, V.; Goddijn-Murphy, L.; Veiga, J.M.; et al. Toward the integrated marine debris observing system. Front. Mar. Sci. 2019, 6, 447. [Google Scholar] [CrossRef]
  54. Kieu, H.T.; Law, A.W.-K. Remote sensing of coastal hydro-environment with portable unmanned aerial vehicles (pUAVs) a state-of-the-art review. J. Hydro-Environ. Res. 2021, 37, 32–45. [Google Scholar] [CrossRef]
  55. Gladju, J.; Kamalam, B.S.; Kanagaraj, A. Applications of data mining and machine learning framework in aquaculture and fisheries: A review. Smart Agric. Technol. 2022, 2, 100061. [Google Scholar] [CrossRef]
  56. Saad, A.; Stahl, A.; Våge, A.; Davies, E.; Nordam, T.; Aberle, N.; Ludvigsen, M.; Johnsen, G.; Sousa, J.; et al.; Norwegian University of Science and Technology Advancing ocean observation with an ai-driven mobile robotic explorer. Oceanography 2020, 33, 50–59. [Google Scholar] [CrossRef]
  57. Bakker, K. Smart Oceans: Artificial intelligence and marine protected area governance. Earth Syst. Gov. 2022, 13, 100141. [Google Scholar] [CrossRef]
  58. Melet, A.; Teatini, P.; Le Cozannet, G.; Jamet, C.; Conversi, A.; Benveniste, J.; Almar, R. Earth observations for monitoring marine coastal hazards and their drivers. Surv. Geophys. 2020, 41, 1489–1534. [Google Scholar] [CrossRef]
  59. Fallati, L.; Polidori, A.; Salvatore, C.; Saponari, L.; Savini, A.; Galli, P. Anthropogenic Marine Debris assessment with Unmanned Aerial Vehicle imagery and deep learning: A case study along the beaches of the Republic of Maldives. Sci. Total Environ. 2019, 693, 133581. [Google Scholar] [CrossRef]
  60. Kim, T.; Lee, W.-D. Review on applications of machine learning in coastal and ocean engineering. J. Ocean Eng. Technol. 2022, 36, 194–210. [Google Scholar] [CrossRef]
  61. Kuznetsova, E.; Cardin, M.A.; Diao, M.; Zhang, S. Integrated decision-support methodology for combined centralized-decentralized waste-to-energy management systems design. Renew. Sustain. Energy Rev. 2019, 103, 477–500. [Google Scholar] [CrossRef]
  62. Benitez-Bravo, R.; Gomez-González, R.; Rivas-García, P.; Botello-Álvarez, J.E.; Huerta-Guevara, O.F.; García-León, A.M.; Rueda-Avellaneda, J.F. Optimization of municipal solid waste collection routes in a Latin-American context. J. Air Waste Manag. Assoc. 2021, 71, 1415–1427. [Google Scholar] [CrossRef]
  63. Whitt, C.; Pearlman, J.; Polagye, B.; Caimi, F.; Muller-Karger, F.; Copping, A.; Spence, H.; Madhusudhana, S.; Kirkwood, W.; Grosjean, L.; et al. Future vision for autonomous ocean observations. Front. Mar. Sci. 2020, 7, 697. [Google Scholar] [CrossRef]
  64. Zuzanna, K.; Tomasz, U.; Michal, G.; Robert, P. How high-tech solutions support the fight against IUU and ghost fishing: A review of innovative approaches, methods, and trends. IEEE Access 2022, 10, 112539–112554. [Google Scholar] [CrossRef]
  65. Das, S.; Lee, S.-H.; Kumar, P.; Kim, K.-H.; Lee, S.S.; Bhattacharya, S.S. Solid waste management: Scope and the challenge of sustainability. J. Clean. Prod. 2019, 228, 658–678. [Google Scholar] [CrossRef]
  66. Wei, Y.; Wei, Q.; An, D. Intelligent monitoring and control technologies of open sea cage culture: A review. Comput. Electron. Agric. 2020, 169, 105119. [Google Scholar] [CrossRef]
  67. Ali, H.; Khattak, W.A. Big Data for Sustainability: A Holistic Approach to Environmental Conservation and Resource Management. J. Big-Data Anal. Cloud Comput. 2022, 7, 18–30. [Google Scholar]
  68. Sequeira, A.M.M.; Hays, G.C.; Sims, D.W.; Eguíluz, V.M.; Rodríguez, J.P.; Heupel, M.R.; Harcourt, R.; Calich, H.; Queiroz, N.; Costa, D.P.; et al. Overhauling ocean spatial planning to improve marine megafauna conservation. Front. Mar. Sci. 2019, 6, 639. [Google Scholar] [CrossRef]
  69. Deekshith, A. Cross-Disciplinary Approaches: The Role of Data Science in Developing AI-Driven Solutions for Business Intelligence. arXiv 2022, arXiv:2012.07906. [Google Scholar]
  70. Soomro, K.; Bhutta, M.N.M.; Khan, Z.; Tahir, M.A. Smart city big data analytics: An advanced review. Wiley Interdiscip. Rev. Data Min. Knowl. Discov. 2019, 9, e1319. [Google Scholar] [CrossRef]
  71. Cheah, C.G.; Chia, W.Y.; Lai, S.F.; Chew, K.W.; Chia, S.R.; Show, P.L. Innovation designs of industry 4.0 based solid waste management: Machinery and digital circular economy. Environ. Res. 2022, 213, 113619. [Google Scholar] [CrossRef]
  72. Maiurova, A.; Kurniawan, T.A.; Kustikova, M.; Bykovskaia, E.; Othman, M.H.D.; Singh, D.; Goh, H.H. Promoting digital transformation in waste collection service and waste recycling in Moscow (Russia): Applying a circular economy paradigm to mitigate climate change impacts on the environment. J. Clean. Prod. 2022, 354, 131604. [Google Scholar] [CrossRef]
  73. Richards, C.E.; Tzachor, A.; Avin, S.; Fenner, R. Rewards, risks and responsible deployment of artificial intelligence in water systems. Nat. Water 2023, 1, 422–432. [Google Scholar] [CrossRef]
  74. Sun, A.Y.; Scanlon, B.R. How can Big Data and machine learning benefit environment and water management: A survey of methods, applications, and future directions. Environ. Res. Lett. 2019, 14, 073001. [Google Scholar] [CrossRef]
  75. Amani, M.; Mehravar, S.; Asiyabi, R.M.; Moghimi, A.; Ghorbanian, A.; Ahmadi, S.A.; Ebrahimy, H.; Moghaddam, S.H.A.; Naboureh, A.; Ranjgar, B.; et al. Ocean remote sensing techniques and applications: A review (part ii). Water 2022, 14, 3401. [Google Scholar] [CrossRef]
  76. Galaz, V.; Centeno, M.A.; Callahan, P.W.; Causevic, A.; Patterson, T.; Brass, I.; Baum, S.; Farber, D.; Fischer, J.; Garcia, D.; et al. Artificial intelligence, systemic risks, and sustainability. Technol. Soc. 2021, 67, 101741. [Google Scholar] [CrossRef]
  77. Ahmad, T.; Zhang, D.; Huang, C.; Zhang, H.; Dai, N.; Song, Y.; Chen, H. Artificial intelligence in sustainable energy industry: Status Quo, challenges and opportunities. J. Clean. Prod. 2021, 289, 125834. [Google Scholar] [CrossRef]
  78. Molina-Molina, J.C.; Salhaoui, M.; Guerrero-González, A.; Arioua, M. Autonomous marine robot based on AI recognition for permanent surveillance in marine protected areas. Sensors 2021, 21, 2664. [Google Scholar] [CrossRef] [PubMed]
  79. Malde, K.; Handegard, N.O.; Eikvil, L.; Salberg, A.-B. Machine intelligence and the data-driven future of marine science. ICES J. Mar. Sci. 2020, 77, 1274–1285. [Google Scholar] [CrossRef]
  80. Jain, S.; Ahuja, N.J.; Srikanth, P.; Bhadane, K.V.; Nagaiah, B.; Kumar, A.; Konstantinou, C. Blockchain and autonomous vehicles: Recent advances and future directions. IEEE Access 2021, 9, 130264–130328. [Google Scholar] [CrossRef]
  81. Adusei-Gyamfi, J.; Boateng, K.S.; Sulemana, A.; Hogarh, J.N. Post COVID-19 recovery: Challenges and opportunities for solid waste management in Africa. Environ. Chall. 2022, 6, 100442. [Google Scholar] [CrossRef]
Sustainability 17 03912 g001
Figure 1. Flowchart showing the bibliographic search process.
Figure 1. Flowchart showing the bibliographic search process.
Sustainability 17 03912 g001
Sustainability 17 03912 g002
Figure 2. Total publications year-wise.
Figure 2. Total publications year-wise.
Sustainability 17 03912 g002
Sustainability 17 03912 g003
Figure 3. Publications per journal.
Figure 3. Publications per journal.
Sustainability 17 03912 g003
Sustainability 17 03912 g004
Figure 4. Subject areas.
Figure 4. Subject areas.
Sustainability 17 03912 g004
Sustainability 17 03912 g005
Figure 5. (a) Co-occurrence analysis of keywords extending to environmental impacts. (b) Co-occurrence analysis of keywords with a focus on AI technology.
Figure 5. (a) Co-occurrence analysis of keywords extending to environmental impacts. (b) Co-occurrence analysis of keywords with a focus on AI technology.
Sustainability 17 03912 g005
Sustainability 17 03912 g006
Figure 6. Publications per institution.
Figure 6. Publications per institution.
Sustainability 17 03912 g006
Sustainability 17 03912 g007
Figure 7. Map showing the top 10 countries by number of publications.
Figure 7. Map showing the top 10 countries by number of publications.
Sustainability 17 03912 g007
Sustainability 17 03912 g008
Figure 8. Top 10 countries by number of publications.
Figure 8. Top 10 countries by number of publications.
Sustainability 17 03912 g008
Sustainability 17 03912 g009
Figure 9. Citation analysis of journals.
Figure 9. Citation analysis of journals.
Sustainability 17 03912 g009
Sustainability 17 03912 g010
Figure 10. H-index analysis of the cited journals.
Figure 10. H-index analysis of the cited journals.
Sustainability 17 03912 g010
Sustainability 17 03912 g011
Figure 11. Co-citation analysis.
Figure 11. Co-citation analysis.
Sustainability 17 03912 g011
Sustainability 17 03912 g012
Figure 12. Bibliographic coupling of journals.
Figure 12. Bibliographic coupling of journals.
Sustainability 17 03912 g012
Table 1. Journals with more than 80 publications.
Table 1. Journals with more than 80 publications.
S/NJournalsTotal
1SENSORS703
2SUSTAINABILITY647
3IEEE ACCESS573
4INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH447
5SCIENCE OF THE TOTAL ENVIRONMENT310
6WATER279
7ELECTRONICS262
8REMOTE SENSING239
9ENVIRONMENT INTERNATIONAL171
10BRIEFINGS IN BIOINFORMATICS136
11ATMOSPHERE135
12FRONTIERS IN MARINE SCIENCE131
13ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH131
14TOXICS115
15FRONTIERS IN ENVIRONMENTAL SCIENCE113
16RENEWABLE & SUSTAINABLE ENERGY REVIEWS103
17ENVIRONMENTAL RESEARCH99
18ENVIRONMENTAL POLLUTION91
19ENVIRONMENTAL HEALTH PERSPECTIVES90
20ECOTOXICOLOGY AND ENVIRONMENTAL SAFETY84
Table 2. Co-occurrence analysis of keywords.
Table 2. Co-occurrence analysis of keywords.
S/NKeywordsOccurrencesTotal Link Strength
1Machine learning16734346
2Deep learning10992913
3Artificial intelligence6912153
4Air pollution404951
5Feature extraction151743
6Pollution255648
7Microplastics281635
8Review177614
9COVID-19205611
10Internet of Things151565
11Climate change234547
12Systematics75529
13Computer vision171520
14Sustainability207487
15Systematic review201480
16Remote sensing187477
17Neural networks114437
18Classification131432
19Sensors103394
20Task analysis59393
Table 3. Citation analysis of cited journals.
Table 3. Citation analysis of cited journals.
SourceDocumentsCitationsTotal Link StrengthH-IndexPublisher
Science of the Total Environment2679191.48353Elsevier
Remote Sensing2743689.65193MDPI
Sustainability (Switzerland)1740565.00169MDPI
Marine Pollution Bulletin1739664.96229Elsevier
Journal of Marine Science and Engineering157553.5051MDPI
Sensors1836243.50245MDPI
Applied Sciences (Switzerland)1213038.00130MDPI
IEEE Access2263326.71242IEEE
Environmental Science and Pollution1340711.93179Springer
Journal of Cleaner Production1144810.71309Elsevier
Table 4. Bibliographic coupling.
Table 4. Bibliographic coupling.
SourceDocumentsCitations
Journal of Cleaner Production11448
Journal of Environmental Management7231
Journal of Hazardous Materials9100
Journal of Marine Science and Engineering1575
Marine Pollution Bulletin17396
Ocean and Coastal Management657
Ocean Engineering7100
Oceans Conference Record (IEEE)514
Remote Sensing27436
Science of the Total Environment26791
Sensors18362
Sustainability (Switzerland)17405
Water (Switzerland)7321
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Adeoba, M.I.; Pandelani, T.; Ngwangwa, H.; Masebe, T. The Role of Artificial Intelligence in Sustainable Ocean Waste Tracking and Management: A Bibliometric Analysis. Sustainability 2025, 17, 3912. https://doi.org/10.3390/su17093912

AMA Style

Adeoba MI, Pandelani T, Ngwangwa H, Masebe T. The Role of Artificial Intelligence in Sustainable Ocean Waste Tracking and Management: A Bibliometric Analysis. Sustainability. 2025; 17(9):3912. https://doi.org/10.3390/su17093912

Chicago/Turabian Style

Adeoba, Mariam I., Thanyani Pandelani, Harry Ngwangwa, and Tracy Masebe. 2025. "The Role of Artificial Intelligence in Sustainable Ocean Waste Tracking and Management: A Bibliometric Analysis" Sustainability 17, no. 9: 3912. https://doi.org/10.3390/su17093912

APA Style

Adeoba, M. I., Pandelani, T., Ngwangwa, H., & Masebe, T. (2025). The Role of Artificial Intelligence in Sustainable Ocean Waste Tracking and Management: A Bibliometric Analysis. Sustainability, 17(9), 3912. https://doi.org/10.3390/su17093912

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop