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.

Marine aquaculture has been expanding rapidly in recent years, driven by the growing demand for marine products. However, this expansion has led to increased competition for space and resources with other coastal zone activities, which has resulted in the need for larger facilities and the relocation of operations to offshore areas. Moreover, the complex environment and exposure to environmental conditions and external threats further complicate the sustainable development of the sector. To address these challenges, new and innovative technologies are needed, such as the incorporation of remote sensing and in-situ data for comprehensive and continuous monitoring of aquaculture facilities. This study aims to create an integrated monitoring and decision support system utilizing both satellite and in-situ data to monitor aquaculture facilities on various scales, providing information on water quality, fish growth, and warning signs to alert managers and producers of potential hazards. This study focuses on identifying and estimating parameters that affect aquaculture processes, establishing indicators that can act as warning signs, and evaluating the system’s performance in real-life scenarios. The resulting monitoring tool, called “Aquasafe”, was evaluated for its effectiveness and performance by test users through real-life scenarios. The results of the implemented models showed high accuracy, with an R² value of 0.67. Additionally, users were generally satisfied with the usefulness of the tool, suggesting that it holds promise for efficient management and decision making in marine aquaculture.

The identification of oceanographic circulation related features is a valuable tool for environmental and fishery management authorities, commercial use and institutional research. Remote sensing techniques are suitable for detection, as in situ measurements are prohibitively costly, spatially sparse and infrequent. Still, these imagery applications require a certain level of technical and theoretical skill making them practically unreachable to the immediate beneficiaries. In this paper a new geospatial web service is proposed for providing daily data on mesoscale oceanic feature identification in the North Aegean Sea, produced by Sentinel-3 SLSTR Sea Surface Temperature (SST) imagery, to end users. The service encompasses an automated process for: raw data acquisition, interpolation, oceanic feature extraction and publishing through a webGIS application. Level-2 SST data are interpolated through a Co-Kriging algorithm, involving information from short term historical data, in order to retain as much information as possible. A modified gradient edge detection methodology is then applied to the interpolated products for the mesoscale feature extraction. The resulting datasets are served according to the Open Geospatial Consortium (OGC) standards and are available for visualization, processing and download though a dedicated web portal.

Fish population spatial distribution data provide essential information for fleet monitoring and fishery spatial planning. Modern high resolution ocean color remote sensing sensors with daily temporal coverage can enable consistent monitoring of highly productive areas, giving insight in seasonal and yearly variations. Here is presented the methodology to monitor small pelagic fish spatial distribution by means of 500m resolution satellite data in a geographically and oceanographically complex area. Specifically, anchovy (Engraulis encrasicolus) and sardine (Sardina pilchardus) acoustic biomass data are modeled against environmental proxies obtained from the Sentinel-3 satellite mission. Three modeling techniques (Logistic Regression, Generalized Additive Models, Random Forest) were applied and validated against the in-situ measurements. The accuracy of anchovy presence detection peaked at 76% and for sardine at 78%. Additionally, the spatial distribution of the models’ output highlighted known fishing grounds. For anchovy, biomass modeling highlighted the importance of bathymetry, SST, and the distance from thermal fronts, whereas for sardine, bathymetry, CHL and chlorophyll fronts. The models are applied to a sample dataset to showcase a potential outcome of the proposed methodology and its spatial characteristics. Finally, the results are discussed and compared to other habitat studies and findings in the area.