Alfredo Martins

Abstract
Climate change has led to the need to transition to clean technologies, which depend on an number of critical metals. These metals, such as nickel, lithium, and manganese, are essential for developing batteries. However, the scarcity of these elements and the risks of disruptions to their supply chain have increased interest in exploiting resources on the deep seabed, particularly polymetallic nodules. As the identification of these nodules must be efficient to minimize disturbance to the marine ecosystem, deep learning techniques have emerged as a potential solution. Traditional deep learning methods are based on the use of convolutional layers to extract features, while recent architectures, such as transformer-based architectures, use self-attention mechanisms to obtain global context. This paper evaluates the performance of representative models from both categories across three tasks: detection, object segmentation, and semantic segmentation. The initial results suggest that transformer-based methods perform better in most evaluation metrics, but at the cost of higher computational resources. Furthermore, recent versions of You Only Look Once (YOLO) have obtained competitive results in terms of mean average precision.

Abstract
EMSO ERIC is a unique European distributed marine Research Infrastructure dedicated to the observation and study of the deep ocean in the long term in fixed regional areas. It provides different services of which access to its infrastructure by external users -engineers, scientists and researchers-, working both in the public and private sectors. The aim of this service, called physical access, is to facilitate access to instrumented platforms deployed at different sites across the European seas, from the seabed to the surface, in order to perform experiments in geosciences and engineering in real ocean conditions. Depending on the logistics and availability of each site, users may deploy their own platforms, instruments, systems or technologies to be tested by the existing equipment that, in this case, can provide reference measurements. Users may also deploy their own systems on the existing EMSO platforms, either in standalone mode or connected to them, receiving power and, in some cases, being able to transmit data by satellite or by cable, depending on the site. Projects requiring the use of several EMSO sites are also accepted. The host EMSO Regional Facility provides logistics and technical support in order to deploy and recover the systems, access the data and it may also offer training and co-development. EMSO ERIC launches the physical access call on a yearly basis and evaluates the received project proposals every two months. Access is free of charge and funding is available for travel, consumables, shipping, operations and hardware adaptations needed to run the project. Since 2022, when the first call was launched, ten projects with varied topics have been funded and are in different phases of execution.

Abstract
The deep ocean is vast and challenging to observe; however, it is key to knowledge of the sea and its impact on global climate. Fixed sea observing points (such as the EMSO observing nodes) provide a limited view and are complemented by expensive oceanographic campaigns with systems demanding high logistical requirements such as deep-sea ROVs.  These costs not only limit our capability for key ocean data collection in the deep but also introduce their own environmental costs.Emerging challenges in knowledge and pressure on the exploration of the deep ocean demand new technological solutions for monitoring and safeguarding the marine ecosystem.Innovative robotic technologies such as the TURTLE robotic deep-sea landers can combine long-term permanence at the seabed with mobility and dynamic reconfigurability in spatial and temporal deep-sea observation.Robotic systems of a heterogeneous nature (from conventional gliders, AUVs, or robotic landers) can be combined with standard and new sensing systems, such as bottom-deployed sensor nodes, moored systems, and cabled points when feasible.These systems can provide underwater localization services for the different assets, energy supply and high bandwidth data transfer with robotic docking stations for other mobile elements. An example of the synergy obtained with these new systems is the possibility of using robotic landers as carriers of EGIM (EMSO Generic Instrument Module) sensor payloads, providing power and data storage and flexibility in the deployment and recovery process.This approach, partly taken in the EU-funded Trident project to develop technical solutions for cost-effective and efficient observation of environmental impacts on deep seabed environments, allows for a substantial reduction in the operational and logistic requirements for deep-sea observation, greatly reducing the need for costly oceanographic campaigns or the use of expensive (economic and logistical) deep sea ROV systems.In this work, we present some of the new developments and discuss the transition from existing technological solutions to new ones integrating these recent developments.

Abstract
The deep seabed is composed of heterogeneous ecosystems, containing diverse habitats for marine life. Consequently, understanding the geological and ecological characteristics of the seabed's features is a key step for many applications. The majority of approaches commonly use optical and acoustic sensors to address these tasks; however, each sensor has limitations associated with the underwater environment. This paper presents a survey of the main techniques and trends related to seabed characterization, highlighting approaches in three tasks: classification, detection, and segmentation. The bibliography is categorized into four approaches: statistics-based, classical machine learning, deep learning, and object-based image analysis. The differences between the techniques are presented, and the main challenges for deep sea research and potential directions of study are outlined.

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.