The frequency and severity of large, destructive fires have increased in the recent past, with extended impacts on the landscape, the human population, and ecosystems. Earth observations provide a means for the frequent, wide coverage and accurate monitoring of fire impacts. This study describes an unsupervised approach for the mapping of burned areas from Sentinel-2 satellite imagery, which is based on multispectral thresholding, and introduces an adaptive thresholding method. It takes into account the localized variability of the spectral responses in a two-phase approach. The first phase detects areas that are burned with a high probability, while the second phase adaptively adjusts this preliminary mapping by expanding and refining its boundaries. The resulting classification contains two main classes of interest: burned and unburned. The latter is further classified into four (4) fire impact severity classes, according to the Copernicus Emergency Management Service (CEMS) and the NASA United States Geological Survey (USGS)’s widely acknowledged nomenclature examples. Three distinct wildfire events are assessed, which occurred during the summers of 2020 and 2021 in Greece and Portugal. The classification accuracy is calculated by juxtaposing the classification outputs to burned area validation maps created through the photointerpretation of very high-resolution (VHR) satellite imagery. The corresponding CEMS On-Demand Mapping products are also juxtaposed against the validation maps for comparison purposes. The accuracy assessment showcases that the unsupervised approach closely follows the capacity provided by the CEMS maps (e.g., the kappa coefficient—k—of the proposed unsupervised approach is 0.91, 0.83 and 0.83 for the events processed, while the CEMS products achieve a k of 0.94, 0.93 and 0.8, respectively). The proposed approach considers the variability of the affected areas’ spectral response; thus, it generalizes well to different areas, e.g., areas characterized by different land cover types. It seems to offer an effective means of mapping the wildfire-induced changes, which can be further incorporated and used by forest fire management services and further decision support systems complementary to the CEMS maps.

Mapping underwater aquatic vegetation (UVeg) is crucial for understanding the dynamics of freshwater ecosystems. The advancement of artificial intelligence (AI) techniques has shown great potential in improving the accuracy and efficiency of UVeg mapping using remote sensing data. This paper presents a comparative study of the performance of classical and modern AI tools, including logistic regression, random forest, and a visual-prompt-tuned foundational model, the Segment Anything model (SAM), for mapping UVeg by analyzing air- and space-borne images in the few-shot learning regime, i.e., using limited annotations. The findings demonstrate the effectiveness of the SAM foundation model in air-borne imagery ($GSD$ = 3–6 cm) with an $F1$ score of $86.5\%\pm 4.1\%$ when trained with as few as 40 positive/negative pairs of pixels, compared to $54.0\%\pm 9.2\%$ using the random forest model and $42.8\%\pm 6.2\%$ using logistic regression models. However, adapting SAM to space-borne images (WorldView-2 and Sentinel-2) remains challenging, and could not outperform classical pixel-wise random forest and logistic regression methods in our task. The findings presented provide valuable insights into the strengths and limitations of AI models for UVeg mapping, aiding researchers and practitioners in selecting the most suitable tools for their specific applications.

Wildfire detection and mapping is crucial for managing natural resources and preventing further environmental damage. In this study, we compared two methods of mapping burn scars using Sentinel-2 satellite imagery, a pixel-based approach and an object-based approach, at test sites located in various climatic zones with diverse land cover synthesis. The study aimed to determine the advantages and limitations of each method in terms of accuracy and precision in detecting burn scars. The results showed that both methods could detect burn scars with high accuracy, but with some limitations. The F1 score was in the range of 0.64–0.89 for the object-based approach, and 0.58–0.90 for the pixel-based approach. The pixel-based method produced a more precise delineation of the burnt area, but it was only suitable for detecting burn scars in a limited area of interest. The object-based method, on the other hand, was able to detect burn scars over a larger area accurately but with some commission errors. The results of both methods were also compared to the Copernicus Emergency Management Service (CEMS) rapid mapping product.

Authorship attribution stems from the idea that one can use a text to derive useful conclusions about its author. It is a rather old idea, that has recently gained momentum due to the major technological leaps achieved in computer science. These leaps enabled researchers to process large amounts of information in reasonable time and to employ sophisticated algorithms for extracting textual features that may indicate something useful about the author. In this paper, a method for authorship attribution is investigated that resorts to Word Adjacency Networks (WANs). The method was originally proposed for author attribution in English corpora by Segarra, Eisen, and Ribeiro [23]. The paper builds upon this method by demonstrating its capability to capture the stylometric patterns of authors in Greek literature. Contrary to English, Greek is a strongly synthetic language. The data used in the experiments comprise literature pieces from 20 Greek authors that belong to two different groups. The first 9 (i.e., Eftaliotis, Karkavitsas, Kondylakes, Moraitides, Nirvanas, Papadiamantes, Rhoides, Vikelas, and Viziinos) form the first group. The remaining 11 (i.e., Delta, Empirikos, Karagatsis, Kastanakis, Kontoglou, Mirivilis, Politis, Prevelakis, Terzakis, Theotokas, and Venezis) form the second group whose nucleus is the so-called Generation of 30s’. The problem is formulated mathematically and the attribution algorithm is tested for a wide range of parameter values. The experimental findings show that authorship attribution with WANs can give satisfactory results as long as there are adequate training data. After fine tuning the parameters of the method, the total attribution accuracy was found to be in the first group of authors and in the second group of authors. This demonstrates the potential of the method and its applicability to morphologically and syntactically rich languages.

Phased Array Antennas are among the most important 5G enabling technologies. Optimizing a Phased Array Antenna (PAA) is an elaborate task, especially for PAAs with increased number of elements. Traditional optimization methods that are either based on greedy, local optimization such as gradient methods or consist of random walk solution space searches, are far from ideal for solving the problem of arbitrary pattern synthesis in 1D and 2D antenna arrays, mainly due to the high dimensional, multimodal functional domains involved but also due to the inherent limitations of these approaches e.g., the majority of these methods assume the object function is continuous or even differentiable. On the other hand, natural optimization methods, e.g., genetic algorithms, simulated annealing and particle swarm optimization can be used to tackle this problem efficiently. In this study, a genetic algorithm was developed for optimizing a Planar (2D) Phased Array Antenna, using a custom objective function so that the Array Factor has specific characteristics, in terms of directivity, beamwidth and side-lobe level (SLL). The experimental results showed that the genetic algorithm can be used for optimizing a 2D PAA with very satisfactory results.