UNO is a underwater images dataset allowing deep-learning networks to localize non-natural objects within underwater images. The dataset consists in 279 videos, 5930 frames, and 10809 labels. UNO is a more consistent and balanced version of the TrashCan image dataset to evaluate models for detecting non-natural objects in the underwater environment. We propose a method to balance the number of annotations and images for cross-evaluation. We then compare the performance of a SOTA object detection model when using TrashCAN and UNO datasets. Additionally, we assess covariate shift by testing the model on an image dataset for real-world application. Experimental results show significantly better and more consistent performance using the UNO dataset.

The MAELSTROM Project performed a literature survey includes existing databases on marine litter data on the water column, sea floor, estuaries, rivers and beaches. Specifically, the European/Regional Seas review is based on existing publications while the study areas review is based on existing publications and raw data, when available. The review intends to provide the knowledge-base on the characteristics, sources and pathways of marine litter in the two demo sites of the lagoon of Venice (Italy) and the Ave River estuary (Portugal). Specifically, the review aims at: ● improving the understanding of the amounts and types of marine litter occurring in Europe and in particular in the study areas; ● improving the understanding of the main sources and pathways of marine litter in Europe and in particular in the study areas; ● supporting the definition of the input data and assumptions related to marine litter to be used in numerical models of marine litter spatial distribution. To achieve this objective, we assume the following constraints: ● the main focus is on macro-litter; ● the review has a geographic scope focused on the study sites; ● marine litter literature has been analysed to indicate the most probable sources and amount. Here the results related to the Adriatic Sea subregion that is characterised by the presence of many sources of marine litter, including large rivers, big coastal cities, touristic facilities, heavy shipping traffic, intense commercial fisheries and mussel farming. For more details, see the project deliverable: Ghezzo, M., MOSCHINO, V., Galvez, D., Mira Veiga, J., Bocci, M., Iglesias, I., Vieira, L., Sousa Pinto, I., Antunes, S. C., & Correia, A. M. (2021). D2.1 Report on the characterization of major sources of marine litter and macro-plastic in the demo sites. MAELSTROM Project. https://doi.org/10.5281/zenodo.14920205

One of the aim of the MAELSTROM project was to provide a new set of integrated and advanced solutions to identify the typology of marine litter and foremost its traceability from the collection to the treatment phase through innovative app and portal. The Project developed a software and hardware tracking platform for ML data mining and sharing to narrate the in-field organization and testing of marine litter tracking, monitoring and clean up activities. The campaign conducted by Venice Lagoon Plastic Free (VLPF) of marine litter monitoring in the lagoon of Venice in Italy was devised to provide guidance and the feedback required to instruct the technical team's work involved in framing, developing, and fine-tuning the marine litter monitoring service within the MAELSTROM app. The dataset represents the results of four beach litter surveys conducted in the area of the Venice Lagoon in 2021. Data report the number of items identified on the beaches in a 100 m long transect along the beach length. The typology of items is identified using the “G code”, as per the Guidelines and forms for gathering marine litter data: beach and seafloor trawling (Galgani et al., 2021). For more information about the survey see the project deliverable 6.1.

The MAELSTROM Project performed a literature survey includes existing databases on marine litter data on the water column, sea floor, estuaries, rivers and beaches. Specifically, the European/Regional Seas review is based on existing publications while the study areas review is based on existing publications and raw data, when available. The review intends to provide the knowledge-base on the characteristics, sources and pathways of marine litter in the two demo sites of the lagoon of Venice (Italy) and the Ave River estuary (Portugal). Specifically, the review aims at: ● improving the understanding of the amounts and types of marine litter occurring in Europe and in particular in the study areas; ● improving the understanding of the main sources and pathways of marine litter in Europe and in particular in the study areas; ● supporting the definition of the input data and assumptions related to marine litter to be used in numerical models of marine litter spatial distribution. To achieve this objective, we assume the following constraints: ● the main focus is on macro-litter; ● the review has a geographic scope focused on the study sites; ● marine litter literature has been analysed to indicate the most probable sources and amount. Here the results related to the Venice lagoon and Venetian coastal area (demonstration site). For more details, see the project deliverable: Ghezzo, M., MOSCHINO, V., Galvez, D., Mira Veiga, J., Bocci, M., Iglesias, I., Vieira, L., Sousa Pinto, I., Antunes, S. C., & Correia, A. M. (2021). D2.1 Report on the characterization of major sources of marine litter and macro-plastic in the demo sites. MAELSTROM Project. https://doi.org/10.5281/zenodo.14920205

The MAELSTROM Project performed a literature survey includes existing databases on marine litter data on the water column, sea floor, estuaries, rivers and beaches. Specifically, the European/Regional Seas review is based on existing publications while the study areas review is based on existing publications and raw data, when available. The review intends to provide the knowledge-base on the characteristics, sources and pathways of marine litter in the two demo sites of the lagoon of Venice (Italy) and the Ave River estuary (Portugal). Specifically, the review aims at: ● improving the understanding of the amounts and types of marine litter occurring in Europe and in particular in the study areas; ● improving the understanding of the main sources and pathways of marine litter in Europe and in particular in the study areas; ● supporting the definition of the input data and assumptions related to marine litter to be used in numerical models of marine litter spatial distribution. To achieve this objective, we assume the following constraints: ● the main focus is on macro-litter; ● the review has a geographic scope focused on the study sites; ● marine litter literature has been analysed to indicate the most probable sources and amount. Here the results related to the NW Portuguese coastal area. For more details, see the project deliverable: Ghezzo, M., MOSCHINO, V., Galvez, D., Mira Veiga, J., Bocci, M., Iglesias, I., Vieira, L., Sousa Pinto, I., Antunes, S. C., & Correia, A. M. (2021). D2.1 Report on the characterization of major sources of marine litter and macro-plastic in the demo sites. MAELSTROM Project. https://doi.org/10.5281/zenodo.14920205

The MAELSTROM Project performed a literature survey includes existing databases on marine litter data on the water column, sea floor, estuaries, rivers and beaches. Specifically, the European/Regional Seas review is based on existing publications while the study areas review is based on existing publications and raw data, when available. The review intends to provide the knowledge-base on the characteristics, sources and pathways of marine litter in the two demo sites of the lagoon of Venice (Italy) and the Ave River estuary (Portugal). Specifically, the review aims at: ● improving the understanding of the amounts and types of marine litter occurring in Europe and in particular in the study areas; ● improving the understanding of the main sources and pathways of marine litter in Europe and in particular in the study areas; ● supporting the definition of the input data and assumptions related to marine litter to be used in numerical models of marine litter spatial distribution. To achieve this objective, we assume the following constraints: ● the main focus is on macro-litter; ● the review has a geographic scope focused on the study sites; ● marine litter literature has been analysed to indicate the most probable sources and amount. Here the results related to the Ave estuary Portuguese demonstration site. For more details, see the project deliverable: Ghezzo, M., MOSCHINO, V., Galvez, D., Mira Veiga, J., Bocci, M., Iglesias, I., Vieira, L., Sousa Pinto, I., Antunes, S. C., & Correia, A. M. (2021). D2.1 Report on the characterization of major sources of marine litter and macro-plastic in the demo sites. MAELSTROM Project. https://doi.org/10.5281/zenodo.14920205

MAELSTROM (Smart Technology for Marine Litter Sustainable Removal and Management) is a Horizon 2020 (H2020) project co-funded by the European Commission, bringing together 14 partners, including research centers, recycling companies, marine scientists, and robotics experts, from eight European countries. The project seeks to reduce the environmental impact of marine litter (ML) on coastal ecosystems by identifying accumulation hotspots, intercepting floating river waste, and removing plastic-based debris from the seabed to prevent its breakdown into microplastics (MPs). At the core of MAELSTROM’s innovative solution is an advanced robotic seabed cleaning platform, developed collaboratively by TECNALIA, CNRS-LIRMM, and "Servizi Tecnici." This floating structure serves as a base station for the cleaning robot, deploying it via cables and winches while integrating a sophisticated suite of underwater sensors to detect, identify, and manage marine litter. The platform supports two key tools: a dredge for collecting smaller debris and a gripper for retrieving larger items, such as tires, boat fragments, and fishing nets. Designed to function as an adaptable and sustainable system, this platform exemplifies cutting-edge technology for marine litter removal and management.

For this project, two study areas were selected and both are characterized by the presence of marine litter that has accumulated over time: a lagoon area (Sacca Fisola) and a coastal area, the latter located on an abandoned mussel farm.The lagoon site of Sacca Fisola is situated in an area where waste accumulates in substantial quantities. Consequently, the channel's seabed is marked by a significant presence of waste. Some of these waste items are buried beneath layers of sediment, while many others remain visible on the surface and can be identified using the bathymetric map generated from MultiBeam EchoSounder (MBES) data.

For this project, two study areas were selected and both are characterized by the presence of marine litter that has accumulated over time: a lagoon area (Sacca Fisola) and a coastal area, the latter located on an abandoned mussel farm.The lagoon site of Sacca Fisola is situated in an area where waste accumulates in substantial quantities. Consequently, the channel's seabed is marked by a significant presence of waste. Some of these waste items are buried beneath layers of sediment, while many others remain visible on the surface and can be identified using the bathymetric map generated from MultiBeam EchoSounder (MBES) data.

As part of the European MAELSTROM project, microplastic monitoring was carried out to assess the impact of marine cleaning operations. The study focused on two representative sites: Sacca Fisola, within the Venice Lagoon, characterised by high maritime traffic, and Mussel Farm, a coastal area near Cavallino-Jesolo, a former mussel farm. Both sites were monitored every six months and divided into before and after cleaning activities performed by the Seabed Robotic Cleaning Platform (autumn 2022 and spring 2023 for the Sacca Fisola site and spring 2023 for the Mussel Farm site). This innovative robotic system has been designed to remove macro-litter from the seabed. Among the different matrices analysed, particular attention was paid to the biota, with the study of fish species representative of the North Adriatic area, both lagoon and coastal. The species analysed included mullet (Liza sp.), sea bream (Sparus aurata), spiny dogfish (Squalus acanthias) and sole (Solea solea). The main objective was to assess whether the removal of macro plastics from the seabed by the robot was correlated with a reduction in microplastics in the fish themselves, thus contributing to an understanding of the effectiveness of cleaning operations not only on visible debris, but also on the microscopic particles that can be accidentally ingested by these organisms.