Abstract. The present contribution constitutes the first comprehensive attempt to (a) record the spatial characteristics of the beaches of the Aegean archipelago (Greece), a critical resource for both the local and national economy, and (b) provide a rapid assessment of the impacts of the longterm and episodic sea level rise (SLR) under different scenarios. Spatial information and other attributes (e.g., presence of coastal protection works and backshore development) of the beaches of the 58 largest islands of the archipelago were obtained on the basis of remote-sensed images available on the web. Ranges of SLR-induced beach retreats under different morphological, sedimentological and hydrodynamic forcing, and SLR scenarios were estimated using suitable ensembles of cross-shore (1-D) morphodynamic models. These ranges, combined with empirically derived estimations of wave runup induced flooding, were then compared with the recorded maximum beach widths to provide ranges of retreat/erosion and flooding at the archipelago scale. The spatial information shows that the Aegean "pocket" beaches may be particularly vulnerable to mean sea level rise (MSLR) and episodic SLRs due to (i) their narrow widths (about 59 % of the beaches have maximum widths < 20 m), (ii) their limited terrestrial sediment supply, (iii) the substantial coastal development and (iv) the limited existing coastal protection. Modeling results indeed project severe impacts under mean and episodic SLRs, which by 2100 could be devastating. For example, under MSLR of 0.5 m -representative concentration pathway (RCP) 4.5 of the Fifth Assessment Report (AR5) of the Intergovernmental Panel on Climate change (IPCC) -a storm-induced sea level rise of 0.6 m is projected to result in a complete erosion of between 31 and 88 % of all beaches (29-87 % of beaches are currently fronting coastal infrastructure and assets), at least temporarily. Our results suggest a very considerable risk which will require significant effort, financial resources and policies/regulation in order to protect/maintain the critical economic resource of the Aegean archipelago.Published by Copernicus Publications on behalf of the European Geosciences Union.

This paper investigates the potential of using a polynomial radial basis function (RBF) neural network to extract the shoreline position from coastal video images. The basic structure of the proposed network encompasses a standard RBF network module, a module of nodes that use Chebyshev polynomials as activation functions, and an inference module. The experimental setup is an operational coastal video monitoring system deployed in two sites in Southern Europe to generate variance coastal images. The histogram of each image is approximated by non-linear regression, and associated with a manually extracted intensity threshold value that quantifies the shoreline position. The key idea is to use the set of the resulting regression parameters as input data, and the intensity threshold values as output data of the network. In summary, the data set is extracted by quantifying the qualitative image information, and the proposed network takes the advantage of the powerful approximation capabilities of the Chebyshev polynomials by utilizing a small number of coefficients. For comparative reasons, we apply a polynomial RBF network trained by fuzzy clustering, and a feedforward neural network trained by the back propagation algorithm. The comparison criteria used are the standard mean square error; the data return rates, and the root mean square error of the crossshore shoreline position, calculated against the shorelines extracted by the aforementioned annotated threshold values. The main conclusions of the simulation study are: (a) the proposed method outperforms the other networks, especially in extracting the shoreline from images used as testing data; (b) for higher polynomial orders it obtains data return rates greater than 84%, and the root mean square error of the cross-shore shoreline position is less than 1.8 meters.

No abstract

Opinion mining techniques, investigating if text is expressing a positive or negative opinion, continuously gain in popularity, attracting the attention of many scientists from different disciplines. Specific use cases, however, where the expressed opinion is indisputably positive or negative, render such solutions obsolete and emphasize the need for a more in-depth analysis of the available text. Emotion analysis is a solution to this problem, but the multi-dimensional elements of the expressed emotions in text along with the complexity of the features that allow their identification pose a significant challenge. Machine learning solutions fail to achieve a high accuracy, mainly due to the limited availability of annotated training datasets, and the bias introduced to the annotations by the personal interpretations of emotions from individuals. A hybrid rule-based algorithm that allows the acquisition of a dataset that is annotated with regard to the Plutchik’s eight basic emotions is proposed in this paper. Emoji, keywords and semantic relationships are used in order to identify in an objective and unbiased way the emotion expressed in a short phrase or text. The acquired datasets are used to train machine learning classification models. The accuracy of the models and the parameters that affect it are presented in length through an experimental analysis. The most accurate model is selected and offered through an API to tackle the emotion detection in social media posts.

A Legendre polynomial feedforward neural network is proposed to model/predict beach rotation. The study area is the reef-fronted Ammoudara beach, located at the northern coastline of Crete Island (Greece). Specialized experimental devices were deployed to generate a set of input-output data concerning the inshore bathymetry, the wave conditions and the shoreline position. The presence of the fronting beachrock reef (parallel to the shoreline) increases complexity and imposes high non-linear effects. The use of Legendre polynomials enables the network to capture data non-linearities. However, in order to maintain specific functional requirements, the connection weights must be confined within a predetermined domain of values; it turns out that the network's training process constitutes a constrained nonlinear programming problem, solved by the barrier method. The performance of the network is compared to other two neural-based approaches. Simulations show that the proposed network achieves a superior performance, which could be improved if an additional wave parameter (wave direction) was to be included in the input variables.