Mapping marine litter using UAS on a beach-dune system: a multidisciplinary approach

The use of artificial intelligence algorithms to detect macroplastics in aquatic environments: A critical review

The presence of macroplastic (MP) is having serious consequences on natural ecosystems, directly affecting biota and human wellbeing. Given this scenario, estimating MPs' abundance is crucial for assessing the issue and formulating effective waste management strategies. In this context, the main objective of this critical review is to analyze the use of machine learning (ML) techniques, with a particular interest in deep learning (DL) approaches, to detect, classify and quantify MPs in aquatic environments, supported by datasets such as satellite or aerial images and video recordings taken by unmanned aerial vehicles. This article provides a concise overview of artificial intelligence concepts, followed by a bibliometric analysis and a critical review. The search methodology aimed to categorize the scientific contributions through temporal and spatial criteria for bibliometric analysis, whereas the critical review was based on generating homogeneous groups according to the complexity of ML and DL methods, as well as the type of dataset. In light of the review carried out, classical ML techniques, such as random forest or support vector machines, showed robustness in MPs detection. However, it seems that achieving optimal efficiencies in multiclass classification is a limitation for these methods. Consequently, more advanced techniques such as DL approaches are taking the lead for the detection and multiclass classification of MPs. A series of architectures based on convolutional neural networks, and the use of complex pre-trained models through the transfer learning, are currently being explored (e.g., VGG16 and YOLO models), although currently the computational expense is high due to the need for processing large volumes of data. Additionally, there seems to be a trend towards detecting smaller plastic, which need higher resolution images. Finally, it is important to stress that since 2020 there has been a significant increase in scientific research focusing on transformer-based architectures for object detection. Although this can be considered the current state of the art, no studies have been identified that utilize these architectures for MP detection.

Application of improved machine learning in large-scale investigation of plastic waste distribution in tourism Intensive artificial coastlines

Oceans are ultimately a sink of plastic waste. Complex artificial coastlines pose remarkable challenges for coastal plastic waste monitoring. With the development of machine learning methods, high detection accuracy can be achieved; however, many false positives have been noted in various network models used for plastic waste investigation. In this study, extensive surveys of artificial coastlines were conducted using drones along the Dongjiang Port artificial coastline in the Binhai District, Tianjin, China. The deep learning model YOLOv8 was enhanced by integrating the InceptionNeXt and LSK modules into the network to improve its detection accuracy for plastic waste and reduce instances of tourists being misidentified as plastic. In total, 553 high-resolution coastline images with 3488 items of detected plastic waste were compared using the original and improved YOLOv8 models. The improved YOLOv8s-IL model achieved a detection rate of 64.9%, a notable increase of 11.5% compared with that of the original model. The number of false positives in the improved YOLOv8s-IL model was reduced to 32.3%, the multi-class F-score reached 76.5%, and the average detection time per image was only 2.7 s. The findings of this study provide technical support for future large-scale monitoring of plastic waste on artificial coastlines.

Lost and found: Patterns of marine litter accumulation on the remote Island of Santa Luzia, Cabo Verde

Santa Luzia, an uninhabited island in the archipelago of Cabo Verde, serves as a natural laboratory and important nesting site for loggerhead turtles Carettacaretta. The island constitutes an Integral Natural Reserve and a Marine Protected Area. We assessed marine litter accumulation on sandy beaches of the island and analysed their spatial patterns using two sampling methods: at a fine scale, sand samples from 1 × 1 m squares were collected, identifying debris larger than 1 mm; at a coarse scale, drone surveys were conducted to identify visible marine debris (>25 mm) in aerial images. We sampled six points on three beaches of the island: Achados (three points), Francisca (two points) and Palmo Tostão (one point). Then, we modelled the abundance of marine debris using topographical variables as explanatory factors, derived from digital surface models (DSM). Our findings reveal that the island is a significant repository for marine litter (>84% composed of plastics), with up to 917 plastic items per m2 in the sand samples and a maximum of 38 macro-debris items per m2 in the drone surveys. Plastic fragments dominate, followed by plastic pellets (at the fine-scale approach) and fishing materials (at the coarse-scale approach). We observed that north-facing, higher-elevation beaches accumulate more large marine litter, while slope and elevation affect their spatial distribution within the beach. Achados Beach faces severe marine debris pollution challenges, and the upcoming climate changes could exacerbate this problem.

Dune plants as a sink for beach litter: The species-specific role and edge effect on litter entrapment by plants

Anthropogenic litter accumulates along coasts worldwide. In addition to the flowing litter load, wind, sea currents, geomorphology and vegetation determine the distribution of litter trapped on the sandy coasts. Although some studies highlighted the role of dune plants in trapping marine litter, little is known about their efficiency as sinks and about the small-scale spatial distribution of litter across the dune area. Here, we explore these gaps by analysing six plant species widespread in Mediterranean coastal habitats, namely Echinophora spinosa, Limbarda crithmoides, Anthemis maritima, Pancratium maritimum, Thinopyrum junceum, and Salsola kali. The present study analyses for the first time the capture of litter by dune vegetation at a multi-species level, considering their morphological structure. Data on plastic accumulation on dune plants were compared with unvegetated control plots located at embryo-dune and foredune belts. We found that dunal plants mainly entrapped macrolitter (> 0.5 cm). Particularly, E. spinosa, L. crithmoides, A. maritima and P. maritimum mostly accumulated litter in the embryo dune while T. junceum and S. kali entrapped more in the foredune area. Moreover, beach litter was mainly blocked at the edge of the plant patches rather than in the core, highlighting the 'Plant-edge litter effect'. As A. maritima and S. kali entrapped respectively more litter in embryo and foredune habitats, these species could be used to monitor and recollect litter. In this light, our findings provide further insight into the role of dune plants in the beach litter dynamics, suppling useful information for beach clean-up actions.

Marine plastic pollution detection and identification by using remote sensing-meta analysis

The persistent plastic litter, originating from different sources and transported from rivers to oceans, has posed serious biological, ecological, and chemical effects on the marine ecosystem, and is considered a global issue. In the past decade, many studies have identified, monitored, and tracked marine plastic debris in coastal and open ocean areas using remote sensing technologies. Compared to traditional surveying methods, high-resolution (spatial and temporal) multispectral or hyperspectral remote sensing data have been substantially used to monitor floating marine macro litter (FMML). In this systematic review, we present an overview of remote sensing data and techniques for detecting FMML, as well as their challenges and opportunities. We reviewed the studies based on different sensors and platforms, spatial and spectral resolution, ground sampling data, plastic detection methods, and accuracy obtained in detecting marine litter. In addition, this study elaborates the usefulness of high-resolution remote sensing data in Visible (VIS), Near-infrared (NIR), and Short-Wave InfraRed (SWIR) range, along with spectral signatures of plastic, in-situ samples, and spectral indices for automatic detection of FMML. Moreover, the Thermal Infrared (TIR), Synthetic aperture radar (SAR), and Light Detection and Ranging (LiDAR) data were introduced and these were demonstrated that could be used as a supplement dataset for the identification and quantification of FMML.

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.

Socio-economic factors affecting the distribution of marine litter: The Portuguese case study

Marine litter is a growing global problem with serious environmental, economic, social, and health threats. Understanding the socio-economic factors that influence the types and amounts of litter is of utmost importance. In this study, an integrative analysis of the socio-economic factors that characterize the beach litter distribution in continental Portugal and the Azores archipelago was conducted via a cluster analysis, implementing a novel technique to support the difficult task of marine litter characterization. The results highlighted that the most abundant beach litter material is plastic (92.9 %), followed by paper (2.2 %), wood (1.5 %), and metal (1.3 %). The majority of the items could not be attributed to a specific source (46.5 %). The remaining were attributed to public litter (34.5 % of total aggregated items), fishing (9.8 %), sewage-related debris (6.4 %) and shipping (2.2 %). The top-three beach litter categories were small plastic pieces (0-2.5 cm, 43.5 %), cigarette butts (30.1 %), and medium plastic pieces (2.5-50 cm, 26.4 %). A positive relation between both municipality environment expenditures and population density and the quantity and typology of litter was found. Beach litter quantity and categories were also associated with specific economic sectors, as well as with geographical/hydrodynamic conditions, demonstrating the utility of the technique and its applicability to other regions.

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.

Identification of illegally dumped plastic waste in a highly polluted river in Indonesia using Sentinel-2 satellite imagery

Plastic waste monitoring technology based on Earth observation satellites is one approach that is currently under development in various studies. The complexity of land cover and the high human activity around rivers necessitate the development of studies that can improve the accuracy of monitoring plastic waste in river areas. This study aims to identify illegal dumping in a river area using the adjusted plastic index (API) and Sentinel-2 satellite imagery data. Rancamanyar River has been selected as the research area; it is one of the tributaries of Citarum Indonesia and is an open lotic-simple form, oxbow lake type river. Our study is the first attempt to construct an API and random forest machine learning using Sentinel-2 to identify the illegal dumping of plastic waste. The algorithm development integrated the plastic index algorithm with the normalized difference vegetation index (NDVI) and normalized buildup indices. For the validation process, the results of plastic waste image classification based on Pleiades satellite imagery and Unmanned Aerial Vehicle (UAV) photogrammetry was used. The validation results show that the API succeeded in improving the accuracy of identifying plastic waste, which gave a better correlation in the r-value and p-value by + 0.287014 and + 3.76 × 10^-26 with Pleiades, and + 0.143131 and + 3.17 × 10^-10 with UAV.

Understanding through drone image analysis the interactions between geomorphology, vegetation and marine debris along a sandy spit

Marine litter (ML) is recognized as one of the main socio-economic and environmental concerns and monitoring operations have been realized worldwide in order to collect information on the types, quantities and distribution of marine debris. In this study, we used Unmanned Aerial Vehicle (UAV) images to map the presence of ML on a coastal spit in relation to geomorphological aspects and vegetation. Our results show that ML is present everywhere, but concentrates in the beach wrack, dunes, and saltmarshes, highlighting the role of the vegetation in trapping ML. Moreover, ML will most probably remain trapped by the saltmarsh vegetation, since they are not visible and easily accessible to allow cleaning operations. On the contrary, cleaning operations may remove the ML present in the beach wrack. Finally, our results provide useful information to support decision-makers for improving beach cleaning activities in the Po river Delta areas (Italy).

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.

UAV remote sensing applications in marine monitoring: Knowledge visualization and review

With the booming development of information technology and the growing demand for remote sensing data, unmanned aerial vehicle (UAV) remote sensing technology has emerged. In recent years, UAV remote sensing technology has developed rapidly and has been widely used in the fields of military defense, agricultural monitoring, surveying and mapping management, and disaster and emergency response and management. Currently, increasingly serious marine biological and environmental problems are raising the need for effective and timely monitoring. Compared with traditional marine monitoring technologies, UAV remote sensing is becoming an important means for marine monitoring thanks to its flexibility, efficiency and low cost, while still producing systematic data with high spatial and temporal resolutions. This study visualizes the knowledge domain of the application and research advances of UAV remote sensing in marine monitoring by analyzing 1130 articles (from 1993 to early 2022) using a bibliometric approach and provides a review of the application of UAVs in marine management mapping, marine disaster and environmental monitoring, and marine wildlife monitoring. It aims to promote the extensive application of UAV remote sensing in the field of marine research.

Detection and assessment of marine litter in an uninhabited island, Arabian Gulf: A case study with conventional and machine learning approaches

In 2018, the Ministry of Municipality and Environment, Qatar removed 90 t of marine litter (ML) from the Ras Rakan Island (RRI), a remote uninhabited island in the Arabian Gulf (hereinafter referred to as Gulf). To identify the sources of ML and understand the post-cleaning ML accumulation rate, a ML survey was conducted around RRI in 2019. A total of 1341 ML items were found around RRI with an average abundance of 3.4 items/m². In addition, a machine learning approach was applied to extract the quantity and types of ML from 10,400 images from the sampling sites (beaches) to make the ML clean-up process and monitoring effort more efficient. The image coordinates of ML objects were used to train an object detection algorithm 'You Only Look Once (YOLO-v5)' to automatically detect ML from video data. An image enhancement technique was performed to improve the quality of unclear images. The best performing YOLO-v5 model had 90% of mean Average Precision (mAP) while maintaining near real-time processing speeds at 2 ms/image. The abundance of ML around RRI was higher than that found on the coast of mainland Qatar. 61.5% of the sampling locations are considered as 'extremely dirty' based on Clean Coast Index. Windward beaches had higher ML concentrations (derived from neighbouring countries) than the leeward beaches. Like RRI, most of the uninhabited islands in the Arabian Gulf are home to many seabirds and sea turtles, and could act as major sinks for ML deposition. Therefore, implementation of this machine learning technique to all islands allows estimating and mitigating the load of ML for achieving a sustaining and a cleaner ocean.

Assessment of Marine Debris on Hard-to-Reach Places Using Unmanned Aerial Vehicles and Segmentation Models Based on a Deep Learning Approach

It is difficult to assess the characteristics of marine debris, especially on hard-to-reach places such as uninhabited islands, rocky coasts, and seashore cliffs. In this study, to overcome the difficulties, we developed a method for marine debris assessment using a segmentation model and images obtained by UAVs. The method was tested and verified on an uninhabited island in Korea with a rocky coast and a seashore cliff. Most of the debris was stacked on beaches with low slopes and/or concave shapes. The number of debris items on the whole coast estimated by the mapping was 1295, which was considered to be the actual number of coastal debris items. However, the number of coastal debris items estimated by conventional monitoring method-based statistical estimation was 6741 (±1960.0), which was severely overestimated compared with the mapping method. The segmentation model shows a relatively high F1-score of ~0.74 when estimating a covered area of ~177.4 m2. The developed method could provide reliable estimates of the class of debris density and the covered area, which is crucial information for coastal pollution assessment and management on hard-to-reach places in Korea.

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.

Impact of storms and proximity to entry points on marine litter and wrack accumulation along Mediterranean beaches: Management implications

Beach litter can affect public health and economic activities worldwide forcing local authorities to expensive beach cleaning. Understanding the key mechanisms affecting the accumulation of this waste on beaches, such as sea state and proximity to entry points, is critical to plan effective management strategies. In this one-year study, we estimated the impact of storm events and waterways runoff on litter abundance and local economy using as a model a managed, peri-urban beach facing a north-western sector of the Mediterranean Sea. We also investigated the relationship between litter composition/density and beach proximity to major/closest harbors/rivers at regional scale by combining our data with those on litter density available in literature. Autumn/winter storms caused larger litter depositions than spring/summer ones in the peri-urban beach. No preferential accumulation occurred near to waterway mouths. Litter mainly consisted of plastic, and its composition in terms of micro-categories varied over seasons. In total, 367,070 items were deposited along 4.7 km of beach over one year, and the cost for the removal of this waste amounted to approximately 27,600 euros per km/year. At regional scale, beach litter density was positively correlated to the proximity of major harbors while its composition was related to the proximity to both major harbors and rivers. Results indicate that autumn/winter storms are important drivers of marine litter deposition. They also suggest that beaches in front of the convergence zone of littoral currents and close to major harbors can be particularly subjected to this kind of pollutant. To increase their effectiveness, litter mitigation/cleaning activities should be planned based on predictions of major storm events and performed at spatial scales encompassing at least coastal regional sectors.

A review of the application of machine learning in water quality evaluation

With the rapid increase in the volume of data on the aquatic environment, machine learning has become an important tool for data analysis, classification, and prediction. Unlike traditional models used in water-related research, data-driven models based on machine learning can efficiently solve more complex nonlinear problems. In water environment research, models and conclusions derived from machine learning have been applied to the construction, monitoring, simulation, evaluation, and optimization of various water treatment and management systems. Additionally, machine learning can provide solutions for water pollution control, water quality improvement, and watershed ecosystem security management. In this review, we describe the cases in which machine learning algorithms have been applied to evaluate the water quality in different water environments, such as surface water, groundwater, drinking water, sewage, and seawater. Furthermore, we propose possible future applications of machine learning approaches to water environments.

Hydrometeorological assessments of the transport of microplastic pellets in the Eastern Mediterranean

Microplastic pellets were sampled in May and November 2018 during one-week surveys at 13 coastal beaches in Iskenderun Bay/Turkey. Pellet pollution index (PPI) was calculated for the beaches as a tool to assess beach pollution by microplastic pellets. Hydrometeorological conditions, including wind, current, wave, surface run-off, and precipitation, were examined during 2018 to reveal the effect on the transport of microplastic pellets within the study area. Sea-surface heights, including the astronomical tide and the storm surge and the wave runup heights, were also considered in the analysis to study the extent of hydrodynamic forcing on the beach. Hydrometeorological assessments indicated that the pellet concentrations in the coastal zone are mostly related to wind-induced transport. Three major river discharges are considered as the main source of microplastic pellets effluents. A Lagrangian particle transport model was conducted to reveal the possible beaching hotspots of microplastic pellets released from these river mouths. Average microplastic pellets were calculated as 126.04 ± 54.08 items/m² for May 2018 and 70.22 ± 18.25 items/m² for November 2018. An overall mean PPI for May 2018 was calculated as 1.13, indicating a moderate degree of pellet pollution, and 0.56 for November 2018, indicating a low degree of pellet pollution. The simulations showed that Orontes River effluents affected the inner Iskenderun Bay coasts more than the Seyhan and Ceyhan River.

Quantity and type of coastal debris pollution in Taiwan: A rapid assessment with trained citizen scientists using a visual estimation method

Ongoing monitoring of the distribution and composition of coastal debris is a prerequisite for efficient management and cleanups. Therefore, we conducted a rapid assessment of coastal debris along the 1210 km coastline of Taiwan using a visual estimation method. Forty-nine citizen scientists were intensively trained to correctly identify the volume and types of debris. At 121 sampling locations randomly placed along Taiwan's coastline, the citizen scientists recorded the pollution level and the three most abundant debris types within a 100-m transect during four surveys in 2018-2019. Averaging over the four surveys, the mean amount of coastal debris was estimated to be 406.6 kg/km, and the three most abundant debris types were plastic bottles, foamed plastics, and fishing nets and ropes. Using a statistical test which avoids spatial pseudoreplication, we showed that north-facing coastlines had significantly higher pollution levels than the other coastlines, which we suggest is deposited there during strong winter winds. We also showed that fishery-related debris was a much more important part of coastal debris when the volume of it was determined instead of just the number of items. Mean pollution levels were further associated with wind speed, coastline type, and the distance to presumed pollution sources. Our results compare well with similar surveys conducted in Japan and South Korea. In each country, the debris was highly aggregated, which means it was concentrated in a few highly polluted localities. Therefore, the visual estimation method can effectively guide cleanup efforts to the most polluted areas and also reliably generate long-term monitoring data.

UAV-Based Landfill Land Cover Mapping: Optimizing Data Acquisition and Open-Source Processing Protocols

Earth observation technologies offer non-intrusive solutions for monitoring complex and risky sites, such as landfills. In particular, unmanned aerial vehicles (UAVs) offer the ability to acquire data at very high spatial resolution, with full control of the temporality required for the desired application. The versatility of UAVs, both in terms of flight characteristics and on-board sensors, makes it possible to generate relevant geodata for a wide range of landfill monitoring activities. This study aims to propose a robust tool and to provide data acquisition guidelines for the land cover mapping of complex sites using UAV multispectral imagery. For this purpose, the transferability of a state-of-the-art object-based image analysis open-source processing chain was assessed and its sensitivity to the segmentation approach, textural and contextual information, spectral and spatial resolution was tested over the landfill site of Hallembaye (Wallonia, Belgium). This study proposes a consistent open-source processing chain for the land cover mapping using UAV data with accuracies of at least 85%. It shows that low-cost red-green-blue standard sensors are sufficient to reach such accuracies and that spatial resolution of up to 10 cm can be adopted with limited impact on the performance of the processing chain. This study also results in the creation of a new operational service for the monitoring of the active landfill sites of Wallonia.

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.

Drone technology in municipal solid waste management and landfilling: A comprehensive review

The paper discusses the experience of using unmanned aerial vehicles (UAV) in the management of municipal solid waste landfills and dumpsites. Although the use of drones at waste disposal sites (WDS) has a more than ten-year history, the active application of these technologies has increased in the last 3-4 years. The paper analyzes scientific publications of 2010-2021 (July) and identifies the main WDS management task groups for which the solution of UAV can be used. It illustrates that most of the research is devoted to studying spatial and volumetric characteristics of landfills, which is connected with the practical needs. About a quarter of the publications focus on monitoring the emissions of landfill gas or its individual components, mainly methane. Issues of a comprehensive assessment of the technological and environmental safety of landfills and dumps are covered in the scientific literature fragmentarily and insufficiently. At the same time, the current level of technologies for collecting and processing remote sensing air data (UAV, sensors for aerial imagery, software for photogrammetric processing of aerial imagery data, geographic information systems (GIS)) makes it possible to identify and assess many environmental effects of landfills and dumps and to monitor compliance with the standards for the landfills operation, which could bring management of these facilities to a fundamentally different level. Promising areas of further research in the field of UAV application at WDS are indicated: development of processes for automatic interpretation of aerial imagery materials; product analysis of photogrammetric data processing in a GIS environment, etc.

Comparing photography and collection methods to sample litter in seabird nests in a coastal archipelago in the Southwest Atlantic

Different methods are used to quantify and classify litter in seabird nests, such as the collection method (CM) and the photography method (PM). We compared the CM and PM in 195 brown booby (Sula leucogaster) nests breeding in a coastal archipelago in the state of Rio de Janeiro, Brazil. Photographs recorded 109 litter items in 44 nests (23% of nests), compared to 416 litter items in 82 nests (42%) by the CM. Pairwise comparison showed a significant difference in the variety and amount of litter items per nest, which was greater for CM (2.1 ± 1.1 categories, 2.13 ± 4.8 items) than for PM (1.5 ± 0.8 categories; 0.56 ± 1.6 items), in addition to a significant difference in the overall litter composition. The CM has been the most often used method to date. Although PM underestimates the amount and frequency of litter, we encourage its use when litter is abundant in nests and for threatened species.

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.

A Water Surface Contaminants Monitoring Method Based on Airborne Depth Reasoning

Water surface plastic pollution turns out to be a global issue, having aroused rising attention worldwide. How to monitor water surface plastic waste in real time and accurately collect and analyze the relevant numerical data has become a hotspot in water environment research. (1) Background: Over the past few years, unmanned aerial vehicles (UAVs) have been progressively adopted to conduct studies on the monitoring of water surface plastic waste. On the whole, the monitored data are stored in the UAVS to be subsequently retrieved and analyzed, thereby probably causing the loss of real-time information and hindering the whole monitoring process from being fully automated. (2) Methods: An investigation was conducted on the relationship, function and relevant mechanism between various types of plastic waste in the water surface system. On that basis, this study built a deep learning-based lightweight water surface plastic waste detection model, which was capable of automatically detecting and locating different water surface plastic waste. Moreover, a UAV platform-based edge computing architecture was built. (3) Results: The delay of return task data and UAV energy consumption were effectively reduced, and computing and network resources were optimally allocated. (4) Conclusions: The UAV platform based on airborne depth reasoning is expected to be the mainstream means of water environment monitoring in the future.

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.

A rapid assessment of litter magnitudes and impacts along the Torre Guaceto marine protected area (Brindisi, Italy)

This study focuses on assessing litter magnitudes along the Torre Guaceto Marine Protected Area (Brindisi, Italy). Collected litter was grouped into twenty different types and classified into four litter typologies according to the Guidance on Monitoring of Marine Litter in European Seas. All data were analyzed using an index-based approach that allowed the classification of a coastal stretch in terms of cleanliness, and presence of plastics as well hazardous items. The average litter abundance in the study area was 0.5 items/m², being plastics the most common litter item. Hazardous litter items were found along the study area, reaching 21.3% of the total collected items. The application of environmental indices allowed to define the study area with a "moderate cleanliness" and a "moderate" presence of hazardous litter items. Sampled litter typologies and related magnitudes suggest a combination of sources that mainly include direct activities on the nearby coastal zones and river basins (dumping).

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.

UAV Approach for Detecting Plastic Marine Debris on the Beach: A Case Study in the Po River Delta (Italy)

Anthropogenic marine debris (AMD) represent a global threat for aquatic environments. It is important to locate and monitor the distribution and presence of macroplastics along beaches to prevent degradation into microplastics (MP), which are potentially more harmful and more difficult to remove. UAV imaging represents a quick method for acquiring pictures with a ground spatial resolution of a few centimeters. In this work, we investigate strategies for AMD mapping on beaches with different ground resolutions and with elevation and multispectral data in support of RGB orthomosaics. Operators with varying levels of expertise and knowledge of the coastal environment map the AMD on four to five transects manually, using a range of photogrammetric tools. The initial survey was repeated after one year; in both surveys, beach litter was collected and further analyzed in the laboratory. Operators assign three levels of confidence when recognizing and describing AMD. Preliminary validation of results shows that items identified with high confidence were almost always classified properly. Approaching the detected items in terms of surface instead of a simple count increased the percentage of mapped litter significantly when compared to those collected. Multispectral data in near-infrared (NIR) wavelengths and digital surface models (DSMs) did not significantly improve the efficiency of manual mapping, even if vegetation features were removed using NDVI maps. In conclusion, this research shows that a good solution for performing beach AMD mapping can be represented by using RGB imagery with a spatial resolution of about 200 pix/m for detecting macroplastics and, in particular, focusing on the largest items. From the point of view of assessing and monitoring potential sources of MP, this approach is not only feasible but also quick, practical, and sustainable.

Replicate analyses of OSPAR beach litter data

Replicate surveys of beach litter have seldom been performed in the past. In this study, replicate surveys of beach litter were conducted on the beach north of Hörnum (Sylt, Germany), from 2015 to 2019, applying a slightly modified OSPAR protocol of beach litter monitoring. Descriptive statistics and power analyses were calculated on data resulting from these replicate surveys, to find out whether the scatter of replicate beach litter data decreases and the statistical power increases with increasing numbers of replicate surveys. From 2015 to 2019, mean total abundances, given as numbers of litter items, ranged from 19 to 185 litter items on a 50 m section of beach. With increasing numbers of replicate surveys, the scatter given by the coefficient of variation (CV) significantly increased up to 113%. Statistical power considerably increased with increasing numbers of replicate beach sections, e.g. from 82% (two beach sections) to nearly 100% (five beach sections) for a given reduction of beach litter of 50%. Based on these results from a morphologically straight coastline, the use of replicate surveys would be sensible for the future monitoring of beach litter. However, there is high need for studies, which consider coastlines with varying morphology.

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.

Assessment of marine litter through remote sensing: recent approaches and future goals

This bibliographic review provides an overview of techniques used to detect marine litter using remote sensing. The review classified studies in terms of platform (satellite, aircrafts, drones), sensors (passive or active), spectral (visible, infrared, microwaves), spatial resolution (<1 to >30 m), type and size (macroplastics, microplastics), or classification methodology (sighting, photointerpretation, supervised). Most studies applied satellite information to address marine litter using multi- and hyper- spectral optical sensors. The correspondence analysis on analyzed variables exhibited that aircrafts with high spatial resolution (<3 m) with optical sensors (λ = 400 to 2500 nm) seem to be the most optimum combination to target marine litter, while satellites carrying Synthetic Aperture Radar (SAR) sensors (λ = 3.1 to 5.6 cm) may detect sea-slicks associated to surfactants that might contain high concentration of microplastics. Gaps indicate that future goals in marine litter detection should be addressed with platforms including optical and SAR sensors.

A comparative study of deep learning-based network model and conventional method to assess beach debris standing-stock

The conventional survey of marine debris standing-stock has various drawbacks such as high cost and inaccuracy because the total amount of debris in the whole beach is inferred using the results of the manual investigation in selected narrow areas. To overcome the disadvantages, an automatic detection method using a deep learning-based network model was developed to detect and quantify the beach debris. The network model developed in this study classified items with a precision of 0.87 (87%) mAP and showed <5% error compared to actual survey. This study is the first fieldwork in Korea that shows the difference between automatic and conventional methods to predict the beach debris standing-stock. The results provide essential information for the development of effective beach debris management systems and policies.

Remote Hyperspectral Imaging Acquisition and Characterization for Marine Litter Detection

This paper addresses the development of a remote hyperspectral imaging system for detection and characterization of marine litter concentrations in an oceanic environment. The work performed in this paper is the following: (i) an in-situ characterization was conducted in an outdoor laboratory environment with the hyperspectral imaging system to obtain the spatial and spectral response of a batch of marine litter samples; (ii) a real dataset hyperspectral image acquisition was performed using manned and unmanned aerial platforms, of artificial targets composed of the material analyzed in the laboratory; (iii) comparison of the results (spatial and spectral response) obtained in laboratory conditions with the remote observation data acquired during the dataset flights; (iv) implementation of two different supervised machine learning methods, namely Random Forest (RF) and Support Vector Machines (SVM), for marine litter artificial target detection based on previous training. Obtained results show a marine litter automated detection capability with a 70–80% precision rate of detection in all three targets, compared to ground-truth pixels, as well as recall rates over 50%.

Anthropogenic litter density and composition data acquired flying commercial drones on sandy beaches along the Saudi Arabian Red Sea

Anthropogenic litter density and composition data were obtained by conducting aerial surveys on 44 beaches along the Saudi Arabian Coast of the Red Sea [1]. The aerial surveys were completed with commercial drones of the DJI Phantom suite flown at a 10 m altitude. The stills have a resolution of less than 0.5 cm pixels-1, hence, litter objects of few centimetres like bottle caps are easily detectable in the drone images. We here provide a subsample of the drone images acquired. To spare the time needed to visually count the litter objects in the thousands of drone images acquired, these were automatically screened using an object detection algorithm, specifically a Faster R-CNN, able to perform a binary classification in litter and non-litter and to categorize the objects in classes. The multi-class classification, however, is a challenging problem and, hence, it was conducted only on the 15 beaches that showed the highest performance after the binary classification. The performance of the algorithm was calculated by visually screening a subsample of images and it was used to correct the output of the Faster R-CNN. The described steps allowed to obtain an estimate of the litter density in 44 beaches and the litter composition in 15 beaches. By multiplying the relative abundance of each litter class and the median weight of objects belonging to each class, we obtained an estimate of the total mass of plastic beached on 15 beaches. Possible predictors of litter density and mass are the population and marine traffic densities at the site, the exposure of the beach to the prevailing wind and the wind speed, the fetch length and the presence of vegetation where litter could get trapped. Making such raw data (i.e. litter density and composition and their predictors) available can help building the base for a robust global estimate of anthropogenic litter in coastal environments and it is particularly important if data regards an understudied region like the Arabian Peninsula. Moreover, we share a subsample of the original drone images to allow usage from stakeholders.

Enabling a large-scale assessment of litter along Saudi Arabian red sea shores by combining drones and machine learning

Beach litter assessments rely on time inefficient and high human cost protocols, mining the attainment of global beach litter estimates. Here we show the application of an emerging technique, the use of drones for acquisition of high-resolution beach images coupled with machine learning for their automatic processing, aimed at achieving the first national-scale beach litter survey completed by only one operator. The aerial survey had a time efficiency of 570 ± 40 m² min^-1 and the machine learning reached a mean (±SE) detection sensitivity of 59 ± 3% with high resolution images. The resulting mean (±SE) litter density on Saudi Arabian shores of the Red Sea is of 0.12 ± 0.02 litter items m^-2, distributed independently of the population density in the area around the sampling station. Instead, accumulation of litter depended on the exposure of the beach to the prevailing wind and litter composition differed between islands and the main shore, where recreational activities are the major source of anthropogenic debris.

Uncertainty of Drone-Derived DEMs and Significance of Detected Morphodynamics in Artificially Scraped Dunes

This work capitalises on the morphodynamic study of a scraped artificial dune built on the sandy beach of Porto Garibaldi (Comacchio, Italy) as a barrier to protect the touristic facilities from sea storms during the winter season and contributes to understanding of the role of elevation data uncertainty and uniform thresholds for change detection (TCDs) on the interpretation of volume change estimations. This application relies on products derived from unmanned aerial vehicle (UAV) surveys and on the evaluation of the uncertainty associated with volume change estimations to interpret the case study morphodynamics under non-extreme sea and wind conditions. The analysis was performed by comparing UAV-derived digital elevation models (DEMs)—root mean squared error (RMSE) vs. global navigation satellite system (GNSS) < 0.05 m—and orthophotos, considering the significance of the identified changes by applying a set of TCDs. In this case, a threshold of ~0.15 m was able to detect most of the morphological variations. The set of TCD ≤ 0.15 m was considered to discuss the significance of minor changes and the uncertainty of volume change calculations. During the analysed period (21 December 2016–20 January 2017), water levels and waves affected the front of the artificial dune by eroding the berm area; winds remodelled the entire dune, moving the loose sand around the dune and further inland; sediment volumes mobilised by sea and wind forcing were comparable. This work suggests that UAV-derived coastal morphological variations should be interpreted by integrating: (i) a set of uniform thresholds to detect significant changes; (ii) the uncertainty generated by the propagation of the original uncertainty of the elevation products; (iii) the characteristics of the morphodynamic drivers evaluated by adopting uncertainty-aware approaches. Thus, the contribution of subtle morphological changes—magnitudes comparable with the instrumental accuracy and/or the assessed propagated uncertainty—can be properly accounted for.

Spectral reflectance of marine macroplastics in the VNIR and SWIR measured in a controlled environment

While at least 8 million tons of plastic litter are ending up in our oceans every year and research on marine litter detection is increasing, the spectral properties of wet as well as submerged plastics in natural marine environments are still largely unknown. Scientific evidence-based knowledge about these spectral characteristics has relevance especially to the research and development of future remote sensing technologies for plastic litter detection. In an effort to bridge this gap, we present one of the first studies about the hyperspectral reflectances of virgin and naturally weathered plastics submerged in water at varying suspended sediment concentrations and depth. We also conducted further analyses on the different polymer types such as Polyethylene terephthalate (PET), Polypropylene (PP), Polyester (PEST) and Low-density polyethylene (PE-LD) to better understand the effect of water absorption on their spectral reflectance. Results show the importance of using spectral wavebands in both the visible and shortwave infrared (SWIR) spectrum for litter detection, especially when plastics are wet or slightly submerged which is often the case in natural aquatic environments. Finally, we demonstrate in an example how to use the open access data set driven from this research as a reference for the development of marine litter detection algorithms.

Automatic detection of seafloor marine litter using towed camera images and deep learning

Aerial and underwater imaging is being widely used for monitoring litter objects found at the sea surface, beaches and seafloor. However, litter monitoring requires a considerable amount of human effort, indicating the need for automatic and cost-effective approaches. Here we present an object detection approach that automatically detects seafloor marine litter in a real-world environment using a Region-based Convolution Neural Network. The neural network is trained on an imagery with 11 manually annotated litter categories and then evaluated on an independent part of the dataset, attaining a mean average precision score of 62%. The presence of other background features in the imagery (e.g., algae, seagrass, scattered boulders) resulted to higher number of predicted litter items compare to the observed ones. The results of the study are encouraging and suggest that deep learning has the potential to become a significant tool for automatically recognizing seafloor litter in surveys, accomplishing continuous and precise litter monitoring.

Towards the Development of Portable and In Situ Optical Devices for Detection of Micro and Nanoplastics in Water: A Review on the Current Status

The prevalent nature of micro and nanoplastics (MP/NPs) on environmental pollution and health-related issues has led to the development of various methods, usually based on Fourier-transform infrared (FTIR) and Raman spectroscopies, for their detection. Unfortunately, most of the developed techniques are laboratory-based with little focus on in situ detection of MPs. In this review, we aim to give an up-to-date report on the different optical measurement methods that have been exploited in the screening of MPs isolated from their natural environments, such as water. The progress and the potential of portable optical sensors for field studies of MPs are described, including remote sensing methods. We also propose other optical methods to be considered for the development of potential in situ integrated optical devices for continuous detection of MPs and NPs. Integrated optical solutions are especially necessary for the development of robust portable and in situ optical sensors for the quantitative detection and classification of water-based MPs.

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.

Automatic detection and quantification of floating marine macro-litter in aerial images: Introducing a novel deep learning approach connected to a web application in R

The threats posed by floating marine macro-litter (FMML) of anthropogenic origin to the marine fauna, and marine ecosystems in general, are universally recognized. Dedicated monitoring programmes and mitigation measures are in place to address this issue worldwide, with the increasing support of new technologies and the automation of analytical processes. In the current study, we developed algorithms capable of detecting and quantifying FMML in aerial images, and a web-oriented application that allows users to identify FMML within images of the sea surface. The proposed algorithm is based on a deep learning approach that uses convolutional neural networks (CNNs) capable of learning from unstructured or unlabelled data. The CNN-based deep learning model was trained and tested using 3723 aerial images (50% containing FMML, 50% without FMML) taken by drones and aircraft over the waters of the NW Mediterranean Sea. The accuracies of image classification (performed using all the images for training and testing the model) and cross-validation (performed using 90% of images for training and 10% for testing) were 0.85 and 0.81, respectively. The Shiny package of R was then used to develop a user-friendly application to identify and quantify FMML within the aerial images. The implementation of this, and similar algorithms, allows streamlining substantially the detection and quantification of FMML, providing support to the monitoring and assessment of this environmental threat. However, the automated monitoring of FMML in the open sea still represents a technological challenge, and further research is needed to improve the accuracy of current algorithms.

Modelling Beach Litter Accumulation on Mediterranean Coastal Landscapes: An Integrative Framework Using Species Distribution Models

Beach litter accumulation patterns are influenced by biotic and abiotic factors, as well as by the distribution of anthropogenic sources. Although the importance of comprehensive approaches to deal with anthropogenic litter pollution is acknowledged, integrated studies including geomorphologic, biotic, and anthropic factors in relation to beach debris accumulation are still needed. In this perspective, Species Distribution Models (SDMs) might represent an appropriate tool to predict litter accumulation probability in relation to environmental conditions. In this context, we explored the applicability of a SDM–type modelling approach (a Litter Distribution Model; LDM) to map litter accumulation in coastal sand dunes. Starting from 180 litter sampling plots combined with fine–resolution variables, we calibrated LDMs from litter items classified either by their material type or origin. We also mapped litter accumulation hotspots. LDMs achieved fair-to-good predictive performance, with LDMs for litter classified by material type performing significantly better than models for litter classified by origin. Accumulation hotspots were mostly localized along the beach, by beach accesses, and at river mouths. In light of the promising results achieved by LDMs in this study, we conclude that this tool can be successfully applied within a coastal litter management context.