Abstract
The objective of this paper is to delineate the ongoing doctoral research work that is focused on the development of a digital model intended to emulate the real-time operation of an electrolyzer that is powered by a DC/DC converter. The digital model of the converter and the proton exchange membrane (PEM) electrolyzer (EL) is presented, and it is based on an electrical equivalent model. A primary contribution of this study is the analysis of the errors resulting from the discretization process. Furthermore, the implementation and development of the digital model requires a comprehensive study of the errors and key affecting factors. Additionally, the formulation of a mechanism to reduce these errors is essential for advancing this topic. Preliminary results obtained using the digital emulator developed demonstrated its capacity to reproduce the voltage and current response applied to the electrolyzer with a reduced error compared to the continuous-time model.

Abstract
This paper presents a novel approach to classical linear regression, enabling accurate model computation from data streams or in a distributed setting while preserving data privacy in federated environments. We extend this framework to generalized linear models (GLMs), ensuring scalability and adaptability to diverse data distributions while maintaining privacy-preserving properties. To assess the effectiveness of our approach, we conduct numerical studies on both simulated and real datasets, comparing our method with conventional maximum likelihood estimation for GLMs using iteratively reweighted least squares. Our results demonstrate the advantages of the proposed method in distributed and federated settings.

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

Abstract
This paper focuses on an innovative application of deep learning (DL) techniques, particularly 3D convolutional neural networks (CNNs), for land cover classification using multispectral Sentinel-2 (S-2) data. In this study, we evaluated the performance of window-pixel-wise 2D, 3D, and 3D Multiscale CNN architectures for land cover classification. 3D and 3D multiscale CNNs were using the spectral dimension as the third dimension for convolutions. Methodology was applied to classify large area (23,217 km2) in Czechia according to the Land use, land-use change and forestry (LULUCF) categories, a key sector in greenhouse gas inventories. The input dataset included S-2 data, along with NDVI, NDVI variance, and SRTM elevation data, all resampled to the 10 m S-2 grid and forming multi-dimensional input 5 x 5 pixel patches. The results show that a 3D CNN with 3 x 3 x 3 spatial-spectral filters and classical training achieved the best F1 score of 0.84, outperforming other proposed CNN architectures and a baseline Random Forest classifier. The study highlights the ability of 3D CNNs to integrate spatial-spectral information, making them highly effective for multispectral data analysis, even with limited (small) training ground truth datasets. This approach provides valuable information for researchers seeking to optimize DL methods for land cover classification, particularly for applications aligned with the LULUCF frameworks.

Abstract
The Haka'a'Museum workshop in Madeira explores how augmented reality (AR) enhances marine conservation education. This one-day, hands-on experience engages participants in co-creating AR experiences that make complex environmental issues more accessible. Following a structured approach, participants explore museum exhibits, collaborate on AR concepts, implement content using no-code tools, and evaluate their experiences. Leveraging Madeira's unique marine ecosystem, the workshop addresses ocean pollution, climate change, and sustainability. Data from AR interactions will inform the best practices for museum education. Ultimately, the workshop fosters awareness and action for ocean sustainability, redefining how museums educate through immersive technology.