Abstract
This paper presents the implementation of an innovative solution based on heterogeneous autonomous vehicles to tackle maritime pollution (in particular, oil spills). This solution is based on native microbial consortia with bioremediation capacity, and the adaptation of air and surface autonomous vehicles for in situ release of autochthonous microorganisms (bioaugmentation) and nutrients (biostimulation). By doing so, these systems can be applied as the first line of the response to pollution incidents from several origins that may occur inside ports, around industrial and extraction facilities, or in the open sea during transport activities in a fast, efficient, and low-cost way. The paper describes the work done in the development of a team of autonomous vehicles able to carry as payload, native organisms to naturally degrade oil spills (avoiding the introduction of additional chemical or biological additives), and the development of a multi-robot framework for efficient oil spill mitigation. Field tests have been performed in Portugal and Spain's harbors, with a simulated oil spill, and the coordinate oil spill task between the autonomous surface vehicle (ASV) ROAZ and the unmanned aerial vehicle (UAV) STORK has been validated.

Abstract
Solar energy will contribute to global economic growth, increasing worldwide photovoltaic (PV) solar energy production. More recently, one of the outstanding energy achievements of the last decade has been the development of floating photovoltaic panels. These panels differ from conventional (terrestrial) panels because they occupy space in a more environmentally friendly way, i.e., aquatic areas. In contrast, land areas are saved for other applications, such as construction or agriculture. Developing autonomous inspection systems using unmanned aerial vehicles (UAVs) represents a significant step forward in solar PV technology. Given the frequently remote and difficult-to-access locations, traditional inspection methods are no longer practical or suitable. Responding to these challenges, an innovative inspection framework was developed to autonomously inspect photovoltaic plants (offshore) with a Vertical Takeoff and Landing (VTOL) UAV. This work explores two different methods of autonomous aerial inspection, each adapted to specific scenarios, thus increasing the adaptability of the inspection process. During the flight, the aerial images are evaluated in real-time for the autonomous detection of the photovoltaic modules and the detection of possible faults. This mechanism is crucial for making decisions and taking immediate corrective action. An offshore simulation environment was developed to validate the implemented system.

Abstract
We present a pilot study where spectral unmixing is applied to hyperspectral images captured in a controlled environment with a threefold purpose in mind: validation of our experimental setup, of the data processing pipeline, and of the usage of spectral unmixing algorithms for the aforementioned research avenue. Results from this study show that classical techniques such as VCA and FCLS can be used to distinguish between plastic and nonplastic materials, but struggle significantly to distinguish between spectrally similar plastics, even in the presence of multiple pure pixels.

Abstract
This paper explores the potential use of acoustic imaging and the use of a multi-frequency multibeam-echosounder (MBES) for monitoring marine litter in the water column. The main goal is to perform a test and validation setup using a simulation and actual experimental setup to determine if the MBES data can detect marine litter in a water column image (WCI) and if using multi-frequency MBES data will allow to better distinguish and characterize marine litter debris in detection applications. Results using simulated HoloOcean Environment and actual marine litter data revealed the successful detection of objects commonly found in ocean litter hotspots at various ranges and frequencies, enablingthe pursue of novel means of automatic detection and classification in MBES WCI data while using multi-frequency capabilities.

Abstract
This paper introduces an advanced acoustic imaging system leveraging multibeam water column data at various frequencies to detect and classify marine litter. This study encompasses (i) the acquisition of test tank data for diverse types of marine litter at multiple acoustic frequencies; (ii) the creation of a comprehensive acoustic image dataset with meticulous labelling and formatting; (iii) the implementation of sophisticated classification algorithms, namely support vector machine (SVM) and convolutional neural network (CNN), alongside cutting-edge detection algorithms based on transfer learning, including single-shot multibox detector (SSD) and You Only Look once (YOLO), specifically YOLOv8. The findings reveal discrimination between different classes of marine litter across the implemented algorithms for both detection and classification. Furthermore, cross-frequency studies were conducted to assess model generalisation, evaluating the performance of models trained on one acoustic frequency when tested with acoustic images based on different frequencies. This approach underscores the potential of multibeam data in the detection and classification of marine litter in the water column, paving the way for developing novel research methods in real-life environments.

Abstract
Exploiting stronger winds at offshore farms leads to a cyclical need for maintenance due to the harsh maritime conditions. While autonomous vehicles are the prone solution for O&M procedures, sub-sea phenomena induce severe data degradation that hinders the vessel's 3D perception. This article demonstrates a hybrid underwater imaging system that is capable of retrieving tri-dimensional information: dense and textured Photogrammetric Stereo (PS) point clouds and multiple accurate sets of points through Light Stripe Ranging (LSR), that are combined into a single dense and accurate representation. Two novel fusion algorithms are introduced in this manuscript. A Joint Masked Regression (JMR) methodology propagates sparse LSR information towards the PS point cloud, exploiting homogeneous regions around each beam projection. Regression curves then correlate depth readings from both inputs to correct the stereo-based information. On the other hand, the learning-based solution (RHEA) follows an early-fusion approach where features are conjointly learned from a coupled representation of both 3D inputs. A synthetic-to-real training scheme is employed to bypass domain-adaptation stages, enabling direct deployment in underwater contexts. Evaluation is conducted through extensive trials in simulation, controlled underwater environments, and within a real application at the ATLANTIS Coastal Testbed. Both methods estimate improved output point clouds, with RHEA achieving an average RMSE of 0.0097 m -a 52.45% improvement when compared to the PS input. Performance with real underwater information proves that RHEA is robust in dealing with degraded input information; JMR is more affected by missing information, excelling when the LSR data provides a complete representation of the scenario, and struggling otherwise.