Quantifying Marine Macro Litter Abundance on a Sandy Beach Using Unmanned Aerial Systems and Object-Oriented Machine Learning Methods

Trends in the occurrence and accumulation of microplastics in urban soil of Nanjing and their policy implications

Urban soil is an important sink of terrestrial microplastics (MPs), and understanding their distribution over time is essential for effective pollution management. Here, based on soil MP data from Nanjing, a typical megacity in eastern China, this study analyzed MP accumulation trends using decision tree and time series network based on soil attributes, POI (point of interest), and human activity factors such as urban industrial structure, transportation, water use. We also evaluated the impact of plastic policy interventions. In the past 15 years, MPs in urban soil in Nanjing have gradually increased, and highly polluted areas have also grown. From 2010 to 2020, the concentration of MPs in urban soil increased from 326.7 items/kg to 480.9 items/kg, with high pollution areas expanding from only 2.0 km2 (0.7 %) to 48.7 km2 (14.9 %). The accumulation of MPs was also influenced by changing factors due to urbanization. In the early 21st century, residential areas had the largest effect, while in the later period, public passenger transport and domestic water consumption were the dominant factors. The scenarios simulation suggests recent plastic intervention policies have helped alleviate this rate of increase, but MP source management (e.g., laundry fibers, tire wear) still needs improvement. By the proposed method, the past trend of microplastics in urban soil and their relationship with soil properties and human activities can be accurately revealed, which will be helpful for the formulation of countermeasures to mitigate regional soil MP pollution.

Machine learning to support citizen science in urban environmental management

Machine learning (ML) and citizen science (CS) are increasingly prevalent and rapidly evolving approaches to studying and managing environmental challenges. Municipal and other governance actors can benefit from technology advances in ML and public engagement benefits of CS but must also address validity and other quality assurance concerns in their application to particular management contexts. In this article, we take up the pervasive challenge of urban litter to demonstrate how ML can support CS by providing quality assurance in the regulatory context of California's stormwater program. We gave quantitative CS-collected data to five ML models to compare their predictions of a qualitative, site-specific, multiclass "Litter Index" score, an important regulatory metric typically only assessed by trained experts. XGBoost had the best outcome, with scores of 0.98 for accuracy, precision, recall and F-1. These strong results show that ML can provide a reliable complement to CS assessments and increase quality assurance in a regulatory context. To date, ML and CS have each contributed to litter management in novel ways and we find that their integration can provide important synergies with additional applications in other environmental management domains.

Assessment of beach macrolitter using unmanned aerial systems: A study along the Bulgarian Black Sea Coast

Over the years, the Black Sea has been impacted by the issue of marine litter, which poses ecological and health threats. A mid-term monitoring program initiated in 2018 assessed the abundance, density, and composition of beach litter (BL) on 40 frequently visited beaches. From 2018 to 2022, there was a significant increase in average abundance, rising by 261 %. Artificial polymer materials accounted for the majority (84 %) of the litter. Land-based sources dominated 77 % of the litter. The Clean Coast Index (CCI) categorized the beaches as "moderate" with an average value of 8.9 for the period between 2018 and 2022. However, the years 2021 and 2022, during the COVID-19 epidemic, were identified as the "dirtiest period" with 11 beaches classified as "extremely dirty" due to high domestic tourist pressure. The study demonstrates a successful combination of standard in situ visual assessment supported by unmanned aerial systems for beach litter surveys.

Drones for litter monitoring on coasts and rivers: suitable flight altitude and image resolution

Multirotor drones can be efficiently used to monitor macro-litter in coastal and riverine environments. Litter on beaches, dunes and riverbanks, along with floating litter on coastal and river waters, can be spotted and mapped from aerial drone images. Items detection and classification are prone to image resolution, which is expressed in terms of Ground Sampling Distance (GSD). The GSD is determined by drone flight altitude and camera properties. This paper investigates what is a suitable GSD value for litter survey. Drone flight altitude and camera setup should be chosen to obtain a GSD between 0.5 cm/px and 1.25 cm/px. Within this range, the lowest GSD allows litter categorization and classification, whereas the highest value should be adopted for a coarser litter census. In the vision of drawing up a global protocol for drone-based litter surveys, this work sets the ground for homogenizing data collection and litter assessments.

The octopus pot on the North Atlantic Iberian coast: A plague of plastic on beaches and dunes

This baseline focuses on the octopus pot, a litter item found on the North Atlantic Iberian coast. Octopus pots are deployed from vessels in ropes, with several hundred units, and placed on the seabed, to capture mostly Octopus Vulgaris. The loss of gears due to extreme seas state, bad weather and/or fishing-related unforeseen circumstances, cause the octopus pots contaminating beaches and dunes, where they are transported by sea current, waves and wind actions. This work i) gives an overview of the use of octopus pot on fisheries, ii) analyses the spatial distribution of this item on the coast, and iii) discusses the potential measures for tackling the octopus pot plague on the North Atlantic Iberian coast. Overall, it is urgent to promote conducive policies and strategies for a sustainable waste management of octopus pots, based on Reduce, Reuse and Recycle hierarchical framework.

Beach litter survey by drones: Mini-review and discussion of a potential standardization

The abundance of beach litter has been increasing globally during the last decades, and it is an issue of global concern. A new survey strategy, based on uncrewed aerial vehicles (UAV, aka drones), has been recently adopted to improve the monitoring of beach macro-litter items abundance and distribution. This work identified and analysed the 15 studies that used drone for beach litter surveys on an operational basis. The analysis of technical parameters for drone flight deployment revealed that flight altitude varied between 5 and 40 m. The analysis of final assessments showed that, through manual and/or automated items detection on images, most of studies provided litter bulk characteristics (type, material and size), along with litter distribution maps. The potential standardization of drone-based litter survey would allow a comparison among surveys, however it seems difficult to propose a standard set of flight parameters, given the wide variety of coastal environments, the different devices available, and the diverse objectives of drone-based litter surveys. On the other hand, in our view, a set of common outcomes can be proposed, based on the grid mapping process, which can be easily generated following the procedure indicated in the paper. This work sets the ground for the development of a standardized protocol for drone litter data collection, analysis and assessments. This would allow the provision of broad scale comparative studies to support coastal management at both national and international scales.

Recent advances in the application of machine learning methods to improve identification of the microplastics in environment

Environmental pollution by microplastics (MPs) is a significant and complex global issue. Existing MPs identification methods have demonstrated significant limitations such as low resolution, long imaging time, and limited particle size analysis. New and improved methods for MPs identification are topical research areas, with machine learning (ML) algorithms proven highly useful in recent years. Critical literature reviews on the latest developments in this area are limited. This study closes this gap and summarizes the progress made over the last 10 years in using ML algorithms for identifying and quantifying MPs. We identified diverse combinations of ML methods and fundamental techniques for MPs identification, such as Fourier-transform infrared spectroscopy, Raman spectroscopy, and near-infrared spectroscopy. The most widely used ML model is the support vector machine, which effectively improves the conventional analysis method for spectral quality defects and improves detection accuracy. Artificial neural network models exhibit improved recognition effects, with shorter detection times and better MPs recognition efficiency. Our review demonstrates the potential of ML in improving the identification and quantification of MPs.

Deploying deep learning to estimate the abundance of marine debris from video footage

The insatiable desire of society for plastic goods has led to synthetic materials becoming omnipresent in the marine environment. In attempting to address the problem of plastic pollution, we propose an image classifier based on the YOLOv5 deep learning tool that is able to classify and localize marine debris and marine life in images and video recordings. Utilizing the region of interest line and the centroid tracking counting methods, the image classifier was able to count marine debris and fish displayed in video footage. Results revealed that, with a counting accuracy of 79 %, the centroid tracking method proved more efficient thanks to its ability to trace the geometric center of the bounding box of detected marine litter. Remarkably, the proposed method achieved a mean average precision of 89.4 % when validated on nine categories of objects. Finally, its impact can be enhanced substantially if integrated into other surveying methods or applications.

Close-range remote sensing-based detection and identification of macroplastics on water assisted by artificial intelligence: A review

Detection and identification of macroplastic debris in aquatic environments is crucial to understand and counter the growing emergence and current developments in distribution and deposition of macroplastics. In this context, close-range remote sensing approaches revealing spatial and spectral properties of macroplastics are very beneficial. To date, field surveys and visual census approaches are broadly acknowledged methods to acquire information, but since 2018 techniques based on remote sensing and artificial intelligence are advancing. Despite their proven efficiency, speed and wide applicability, there are still obstacles to overcome, especially when looking at the availability and accessibility of data. Thus, our review summarizes state-of-the-art research about the visual recognition and identification of different sorts of macroplastics. The focus is on both data acquisition techniques and evaluation methods, including Machine Learning and Deep Learning, but resulting products and published data will also be taken into account. Our aim is to provide a critical overview and outlook in a time where this research direction is thriving fast. This study shows that most Machine Learning and Deep Learning approaches are still in an infancy state regarding accuracy and detail when compared to visual monitoring, even though their results look very promising.

Detection and Classification of Floating Plastic Litter Using a Vessel-Mounted Video Camera and Deep Learning

Marine plastic pollution is a major environmental concern, with significant ecological, economic, public health and aesthetic consequences. Despite this, the quantity and distribution of marine plastics is poorly understood. Better understanding of the global abundance and distribution of marine plastic debris is vital for global mitigation and policy. Remote sensing methods could provide substantial data to overcome this issue. However, developments have been hampered by the limited availability of in situ data, which are necessary for development and validation of remote sensing methods. Current in situ methods of floating macroplastics (size greater than 1 cm) are usually conducted through human visual surveys, often being costly, time-intensive and limited in coverage. To overcome this issue, we present a novel approach to collecting in situ data using a trained object-detection algorithm to detect and quantify marine macroplastics from video footage taken from vessel-mounted general consumer cameras. Our model was able to successfully detect the presence or absence of plastics from real-world footage with an accuracy of 95.2% without the need to pre-screen the images for horizon or other landscape features, making it highly portable to other environmental conditions. Additionally, the model was able to differentiate between plastic object types with a Mean Average Precision of 68% and an F1-Score of 0.64. Further analysis suggests that a way to improve the separation among object types using only object detection might be through increasing the proportion of the image area covered by the plastic object. Overall, these results demonstrate how low-cost vessel-mounted cameras combined with machine learning have the potential to provide substantial harmonised in situ data of global macroplastic abundance and distribution.

Detection of River Plastic Using UAV Sensor Data and Deep Learning

Plastic pollution is a critical global issue. Increases in plastic consumption have triggered increased production, which in turn has led to increased plastic disposal. In situ observation of plastic litter is tedious and cumbersome, especially in rural areas and around transboundary rivers. We therefore propose automatic mapping of plastic in rivers using unmanned aerial vehicles (UAVs) and deep learning (DL) models that require modest compute resources. We evaluate the method at two different sites: the Houay Mak Hiao River, a tributary of the Mekong River in Vientiane, Laos, and Khlong Nueng canal in Talad Thai, Khlong Luang, Pathum Thani, Thailand. Detection models in the You Only Look Once (YOLO) family are evaluated in terms of runtime resources and mean average Precision (mAP) at an Intersection over Union (IoU) threshold of 0.5. YOLOv5s is found to be the most effective model, with low computational cost and a very high mAP of 0.81 without transfer learning for the Houay Mak Hiao dataset. The performance of all models is improved by transfer learning from Talad Thai to Houay Mak Hiao. Pre-trained YOLOv4 with transfer learning obtains the overall highest accuracy, with a 3.0% increase in mAP to 0.83, compared to the marginal increase of 2% in mAP for pre-trained YOLOv5s. YOLOv3, when trained from scratch, shows the greatest benefit from transfer learning, with an increase in mAP from 0.59 to 0.81 after transfer learning from Talad Thai to Houay Mak Hiao. The pre-trained YOLOv5s model using the Houay Mak Hiao dataset is found to provide the best tradeoff between accuracy and computational complexity, requiring model resources yet providing reliable plastic detection with or without transfer learning. Various stakeholders in the effort to monitor and reduce plastic waste in our waterways can utilize the resulting deep learning approach irrespective of location.

Where does marine litter hide? The Providencia and Santa Catalina Island problem, SEAFLOWER Reserve (Colombia)

The SEAFLOWER Biosphere Reserve (SBR) is the largest Marine Protected Area in the Caribbean Sea and the second largest in Latin America. Marine protected areas are under pressure from various stressors, one of the most important issues being pollution by marine litter, especially plastic. In this study our aim is to establish the distribution pattern and potential sources of solid waste in the different marine/coastal ecosystems of the islands of Providencia and Santa Catalina (SBR), as well as assess any interconnections between these ecosystems. At the same time, the distribution characteristics of marine litter in the different compartments facilitated a more dynamic understanding of the load of marine litter supplied by the islands, both locally and externally. We observed that certain ecosystems, principally back-beach vegetation and mangroves, act as crucial marine litter accumulation zones. Mangroves are important hotspots for plastic accumulation, with densities above eight items/m² (minimum 8.38 and maximum 10.38 items/m²), while back-beach vegetation (minimum 1.43 and maximum 7.03 items/m²) also removes and stores a portion of the marine litter that arrives on the beaches. Tourist beaches for recreational activities have a low density of marine litter (minimum 0.01 and maximum 0.72 items/m²) due to regular clean-ups, whereas around non-tourist beaches, there is a greater variety of sources and accumulation (minimum 0.31 and maximum 5.41 items/m²). The low density of marine litter found on corals around the island (0-0.02 items/m²) indicates that there is still no significant marine litter stream to the coral reefs. Identifying contamination levels in terms of marine litter and possible flows between ecosystems is critical for adopting management and reduction strategies for such residues.

On the 3D Reconstruction of Coastal Structures by Unmanned Aerial Systems with Onboard Global Navigation Satellite System and Real-Time Kinematics and Terrestrial Laser Scanning

A wide variety of hard structures protect coastal activities and communities from the action of tides and waves worldwide. It is fundamental to monitor the integrity of coastal structures, as interventions and repairs may be needed in case of damages. This work compares the effectiveness of an Unmanned Aerial System (UAS) and a Terrestrial Laser Scanner (TLS) to reproduce the 3D geometry of a rocky groin. The Structure-from-Motion (SfM) photogrammetry technique applied on drone images generated a 3D point cloud and a Digital Surface Model (DSM) without data gaps. Even though the TLS returned a 3D point cloud four times denser than the drone one, the TLS returned a DSM which was not representing about 16% of the groin (data gaps). This was due to the occlusions encountered by the low-lying scans determined by the displaced rocks composing the groin. Given also that the survey by UAS was about eight time faster than the TLS, the SFM-MV applied on UAS images was the most suitable technique to reconstruct the rocky groin. The UAS remote sensing technique can be considered a valid alternative to monitor all types of coastal structures, to improve the inspection of likely damages, and to support coastal structure management.

Beached and Floating Litter Surveys by Unmanned Aerial Vehicles: Operational Analogies and Differences

The abundance of litter pollution in the marine environment has been increasing globally. Remote sensing techniques are valuable tools to advance knowledge on litter abundance, distribution and dynamics. Images collected by Unmanned Aerial Vehicles (UAV, aka drones) are highly efficient to map and monitor local beached (BL) and floating (FL) marine litter items. In this work, the operational insights to carry out both BL and FL surveys using UAVs are detailly described. In particular, flight planning and deployment, along with image products processing and analysis, are reported and compared. Furthermore, analogies and differences between UAV-based BL and FL mapping are discussed, with focus on the challenges related to BL and FL item detection and recognition. Given the efficiency of UAV to map BL and FL, this remote sensing technique can replace traditional methods for litter monitoring, further improving the knowledge of marine litter dynamics in the marine environment. This communication aims at helping researchers in planning and performing optimized drone-based BL and FL surveys.

Operational use of multispectral images for macro-litter mapping and categorization by Unmanned Aerial Vehicle

The use of Unmanned Aerial Systems (UAS, aka drones) has shown to be feasible to perform marine litter surveys. We operationally tested the use of multispectral images (5 bands) to classify litter type and material on a beach-dune system. For litter categorization by their multispectral characteristics, the Spectral Angle Mapping (SAM) technique was adopted. The SAM-based categorization of litter agreed with the visual classification, thus multispectral images can be used to fasten and/or making more robust the manual RGB image screening. Fully automated detection returned an F-score of 0.64, and a reasonable categorization of litter. Overall, the image-based litter density maps were in line with the manual detection. Assessments were promising given the complexity of the study area, where different dunes plants and partially-buried items challenged the UAS-based litter detection. The method can be easily implemented for both floating and beached litter, to advance litter survey in the environment.

Pixel-level image classification for detecting beach litter using a deep learning approach

Mitigating and preventing beach litter from entering the ocean is urgently required. Monitoring beach litter solely through human effort is cumbersome, with respect to both time and cost. To address this problem, an artificial intelligence technique that can automatically identify different-sized beach litter is proposed. The technique was established by training a deep learning model that enables pixel-wise classification (semantic segmentation) using beach images taken by an observer on the beach. Eight segmentation classes that include two beach litter classes were defined, and the results were qualitatively and quantitatively verified. Segmentation performance was adequately high based on three metrics: Intersection over Union (IoU), precision, and recall, although there is room for further improvement. The potency of the method was demonstrated when it was applied to images taken in different places from training data images, and the coverage of artificial litter calculated and discussed using drone images provided ground truth.

Is coastal erosion a source of marine litter pollution? Evidence of coastal dunes being a reservoir of plastics

This baseline reports scientific evidence of marine litter items embedded in the dune volume at two study sites on the North Atlantic Portuguese coast. We described how stranded litter participate in the sand dune growth/erosion processes on a natural beach-dune system. From the storm-eroded foredunes on the urbanized beach, we documented exhumed plastics with age up to 38 years. Whether litter burial was due to beach-dune morphodynamic processes, or to irresponsible and/or illegal dumping in the past, this work emphasises the need of improving buried litter census and monitoring on coastal dunes. Coastal erosion processes may further exhume litter buried in dune volumes and on other coastal environments over short- and long-term, re-exposing items into the marine environment. Thus, coastal erosion can be accounted as a secondary diffuse source of littering pollution, beside the multiple sources already identified in the environment.

Citizen Science for Marine Litter Detection and Classification on Unmanned Aerial Vehicle Images

Unmanned aerial vehicles (UAV, aka drones) are being used for mapping macro-litter in the environment. As drone images require a manual processing task for detecting marine litter, it is of interest to evaluate the accuracy of non-expert citizen science operators (CSO) in performing this task. Students from Italian secondary schools (in this work, the CSO) were invited to identify, mark, and classify stranded litter items on a UAV orthophoto collected on an Italian beach. A specific training program and working tools were developed for the aim. The comparison with the standard in situ visual census survey returned a general underestimation (50%) of items. However, marine litter bulk categorisation was fairly in agreement with the in situ survey, especially for sources classification. The concordance level among CSO ranged between 60% and 91%, depending on the item properties considered (type, material, and colour). As the assessment accuracy was in line with previous works developed by experts, remote detection of marine litter on UAV images can be improved through citizen science programs, upon an appropriate training plan and provision of specific tools.

Quantifying Floating Plastic Debris at Sea Using Vessel-Based Optical Data and Artificial Intelligence

Despite recent advances in remote sensing of large accumulations of floating plastic debris, mainly in coastal regions, the quantification of individual macroplastic objects (>50 cm) remains challenging. Here, we have trained an object-detection algorithm by selecting and labeling footage of floating plastic debris recorded offshore with GPS-enabled action cameras aboard vessels of opportunity. Macroplastic numerical concentrations are estimated by combining the object detection solution with bulk processing of the optical data. Our results are consistent with macroplastic densities predicted by global plastic dispersal models, and reveal first insights into how camera recorded offshore macroplastic densities compare to micro- and mesoplastic concentrations collected with neuston trawls.

Drones for litter mapping: An inter-operator concordance test in marking beached items on aerial images

Unmanned aerial systems (UAS, aka drones) are being used to map macro-litter on the environment. Sixteen qualified researchers (operators), with different expertise and nationalities, were invited to identify, mark and categorize the litter items (manual image screening, MS) on three UAS images collected at two beaches. The coefficient of concordance (W) among operators varied between 0.5 and 0.7, depending on the litter parameter (type, material and colour) considered. Highest agreement was obtained for the type of items marked on the highest resolution image, among experts in litter surveys (W = 0.86), and within territorial subgroups (W = 0.85). Therefore, for a detailed categorization of litter on the environment, the MS should be performed by experienced and local operators, familiar with the most common type of litter present in the target area. This work provides insights for future operational improvements and optimizations of UAS-based images analysis to survey environmental pollution.

Spatial and size distribution of macro-litter on coastal dunes from drone images: A case study on the Atlantic coast

This work analyses the cross-shore (80 m) and long-shore (200 m) spatial and size distribution of macro-litter on coastal dunes, employing a mapping framework based on an Unmanned Aerial System (UAS, aka drone) and a GIS mobile application. Over the cross-shore, plastic percentage increased from 60% to 90% landwards. The largest items (processed wood) were found on the embryo dune. Plastic bottles and paper napkins were trapped by the foredune grass, while the largest fishing-related items were intercepted by the low scrub plant community on the backdune. Over the long-shore, plastic percentage and items size increased from the urbanized area towards the natural dunes. This work assessed the abundance of marine litter on coastal dune sectors, underlining the role of distinct vegetation types in trapping items of different size. The mapping framework can promote further marine litter monitoring programs and support specific strategies for protecting the dune ecosystems.

Detecting stranded macro-litter categories on drone orthophoto by a multi-class Neural Network

The use of Unmanned Aerial Systems (UAS, aka drones) images for mapping macro-litter in the environment have been exponentially increasing in the recent years. In this work, we developed a multi-class Neural Network (NN) to automatically identify stranded plastic litter categories on an UAS-derived orthophoto. The best results were assessed for items that did not have substantial intra-class colour variability, such as octopus pots and fishing ropes (F-score = 61%, on average). Instead, performance was poor (37%) for plastic bottles and fragments, due to their changing intra-class colours. On average, the performance improved 24% when the binary detection (litter/non-litter, F-Score = 73%) was considered, however this approach did not discriminate the litter categories. This work gives a new perspective for the automated litter detection on drone images, suggesting that colour-based approach can be used to improve the categorization of stranded litter on UAS orthophoto.

A Handy Open-Source Application Based on Computer Vision and Machine Learning Algorithms to Count and Classify Microplastics

Microplastics have recently been discovered as remarkable contaminants of all environmental matrices. Their quantification and characterisation require lengthy and laborious analytical procedures that make this aspect of microplastics research a critical issue. In light of this, in this work, we developed a Computer Vision and Machine-Learning-based system able to count and classify microplastics quickly and automatically in four morphology and size categories, avoiding manual steps. Firstly, an early machine learning algorithm was created to count and classify microplastics. Secondly, a supervised (k-nearest neighbours) and an unsupervised classification were developed to determine microplastic quantities and properties and discover hidden information. The machine learning algorithm showed promising results regarding the counting process and classification in sizes; it needs further improvements in visual class classification. Similarly, the supervised classification demonstrated satisfactory results with accuracy always greater than 0.9. On the other hand, the unsupervised classification discovered the probable underestimation of some microplastic shape categories due to the sampling methodology used, resulting in a useful tool for bringing out non-detectable information by traditional research approaches adopted in microplastic studies. In conclusion, the proposed application offers a reliable automated approach for microplastic quantification based on counts of particles captured in a picture, size distribution, and morphology, with considerable prospects in method standardisation.

A Citizen Science Unmanned Aerial System Data Acquisition Protocol and Deep Learning Techniques for the Automatic Detection and Mapping of Marine Litter Concentrations in the Coastal Zone

Marine litter (ML) accumulation in the coastal zone has been recognized as a major problem in our time, as it can dramatically affect the environment, marine ecosystems, and coastal communities. Existing monitoring methods fail to respond to the spatiotemporal changes and dynamics of ML concentrations. Recent works showed that unmanned aerial systems (UAS), along with computer vision methods, provide a feasible alternative for ML monitoring. In this context, we proposed a citizen science UAS data acquisition and annotation protocol combined with deep learning techniques for the automatic detection and mapping of ML concentrations in the coastal zone. Five convolutional neural networks (CNNs) were trained to classify UAS image tiles into two classes: (a) litter and (b) no litter. Testing the CCNs’ generalization ability to an unseen dataset, we found that the VVG19 CNN returned an overall accuracy of 77.6% and an f-score of 77.42%. ML density maps were created using the automated classification results. They were compared with those produced by a manual screening classification proving our approach’s geographical transferability to new and unknown beaches. Although ML recognition is still a challenging task, this study provides evidence about the feasibility of using a citizen science UAS-based monitoring method in combination with deep learning techniques for the quantification of the ML load in the coastal zone using density maps.