Abstract
This work addresses the use of hyperspectral imaging systems for remote detection of marine litter concentrations in oceanic environments. The work consisted on mounting an off-the-shelf hyperspectral imaging system (400-2500 nm) in two aerial platforms: manned and unmanned, and performing data acquisition to develop AI methods capable of detecting marine litter concentrations at the water surface. We performed the campaigns at Porto Pim Bay, Fail Island, Azores, resorting to artificial targets built using marine litter samples. During this work, we also developed a Convolutional Neural Network (CNN-3D), using spatial and spectral information to evaluate deep learning methods to detect marine litter in an automated manner. Results show over 84% overall accuracy (OA) in the detection and classification of the different types of marine litter samples present in the artificial targets.

Abstract
This paper presents the development of a hyperbaric system able to collect, transport and maintain deep-sea species in controlled condition from the sea floor up to the surface (HiperSea System). The system is composed by two chambers coupled with a transference set-up. The first chamber is able to reach a maximum of 1km depth collecting both benthic and pelagic deep-sea species. The second chamber is a life support compartment to maintain the specimens alive at the surface, in hyperbaric conditions.

Abstract
This paper addresses the development of a novel zero-shot learning method for remote marine litter hyperspectral imaging data classification. The work consisted of using an airborne acquired marine litter hyperspectral imaging dataset that contains data about different plastic targets and other materials and assessing the viability of detecting and classifying plastic materials without knowing their exact spectral response in an unsupervised manner. The classification of the marine litter samples was divided into known and unknown classes, i.e., classes that were hidden from the dataset during the training phase. The obtained results show a marine litter automated detection for all the classes, including (in the worst case of an unknown class) a precision rate over 56% and an overall accuracy of 98.71%.

Abstract
The Feedfirst Intelligent Monitoring System is a novel tool for intelligent monitoring of fish nurseries in aquaculture scenarios, mainly focusing on monitoring three essential items: water quality control, biomass estimation, and automated feeding. The system is based on machine vision techniques for fish larvae population size detection, and larvae biomass estimation is monitored through size measurement. We also show that the perception-actuation loop in automated fish tanks can be closed by using the vision system output to influence feeding procedures. The proposed solution was tested in a real tank in an aquaculture setting with real-time performance and logging capabilities.

Abstract
The impact of wildfires is increasing worldwide. The root causes of these effects are manifold, encompassing among others climate change and the accumulation of fuels and increasing settlements in wildland-urban interfaces (WUI). Reports and initiatives to better understand and govern these developments have been launched and call for more integrated approaches to wildfire risk management, including the use of targets or Key Performance Indicators (KPIs). However, despite some examples such as Portugal, wildfire risk management targets are still mainly lacking in Europe. This is surprising since they find wider application in the U.S. and are also more widely applied for flooding in Europe. This perspective hence takes a closer look at the use of targets in reducing disaster risk for different hazards worldwide and reflects about the opportunities and challenges for wildfire risk reduction targets for Europe. It concludes with some suggestions for the application of wildfire risk reduction targets for Europe.

Abstract
This paper presents the development and implementation of learning-based detection and tracking methods using multibeam data to detect marine litter in the water column. The presented work encompasses (i) the creation of acoustic videos and the application of multiple post-processing techniques; (ii) the training of multiple You Only Look Once (YOLO) detection models, specifically YOLOv8, across different variants, acoustic frequencies, and input types (both raw and post-processed); (iii) and the development of a marine litter tracking system based on DeepSORT. The results include a multibeam multi-frequency data study demonstrating the potential of acoustic image sensing for detecting and tracking marine litter materials in the water column.