Georgia D. Kalantzi

HPC-Driven oceanographic predictions with Graph Neural Networks (GNNs) and Gated Recurrent Units (GRUs)

Paraskevi Vourlioti, Theano Mamouka, Maria Banti, Charalampos Paraskevas et autres

In this work, we utilized the high-performance computing (HPC) capabilities of the Vienna Scientific Cluster (VSC5) to develop and validate advanced AI models for oceanographic forecasting, with a focus on predicting Significant Wave Height (SWH). Using the computational power of VSC5, particularly …

A smart beekeeping platform based on remote sensing and artificial intelligence

Nikos Grammalidis, Andreas Stergioulas, Aggelos Avramidis, Konstantinos Karystinakis et autres

Honey bees play an essential role in the food chain, being responsible for one third of the global food supply due to pollination. Thus, preserving the health of beehives is of paramount environmental and economic importance. Unfortunately, at present a decline in …

gr (code pays fourni par la source)

SeaLoc: A pilot forecasting system providing sea characteristics and other support services on high local resolution

Georgia D. Kalantzi, Stilianos Kotsopoulos, Konstandinos Panitsidis, Athanasios Partozis

SeaLoc project aims in developing an integrated forecasting system with accompanying services for the Greek seas. Further development, however, can facilitate the whole Mediterranean region. It will provide interaction both with specialists as well as with everyday users through the internet and …

Fuel type mapping in a typical Mediterranean ecosystem using object-based image analysis of Sentinel 2 imagery and auxiliary GIS data

Konstantinos Karystinakis, Vasileios Alexandridis, Stefanos P. Stefanidis, Georgia D. Kalantzi

Wildfires have been an integral part of the Mediterranean ecosystem. Moreover, the Intergovernmental Panel on Climate Change (IPCC) Fifth Assessment Report emphasizes that the Mediterranean basin is expected to be drier by the end of the 21st century, while future warming will …

Assessment of surface circulation using remote-sensed data, in-situ measurements and directional statistics

Georgia D. Kalantzi, Takvor Soukissian, K. Nittis

Assessment of WAVEWATCH III dissipation formulations by using collocated TOPEX data

Georgia D. Kalantzi, Christine P. Gommenginger, Meric A. Srokosz, David Kevin Woolf

A New Method For Applying R-Largest Maxima Model For Design Sea-State Prediction

Takvor Soukissian, Georgia D. Kalantzi

A frequent problem in design sea-state prediction is the limited amount of available extreme wave data. Thus, several methods to characterize extreme values have been developed, in order to allow the modeling of a sequence of maxima rather than the block maximum …

gr, gb (code pays fourni par la source)

Assessing the Performance of the Dissipation Parameterizations in WAVEWATCH III Using Collocated Altimetry Data

Georgia D. Kalantzi, Christine P. Gommenginger, Meric A. Srokosz

Abstract Wave-breaking dissipation is one of the least understood processes implemented in contemporary wave models. Significant effort has been put in its parameterization, but it has not proven to be totally satisfactory, either theoretically or practically. In this work, the WAVEWATCH III …

gb (code pays fourni par la source)

Extreme Value Analysis Methods Used for Extreme Wave Prediction

Takvor Soukissian, Georgia D. Kalantzi

This work aims to review the variety of the extreme wave analysis methods that are utilized in Ocean Engineering and to present the practical inconveniences arising in relevant applications. The paper is formulated in terms of the different dependence structures of stochastic …

gr (code pays fourni par la source)

De-clustering of S H -Time Series For Applying the Peaks-Over-Threshold Method

Takvor Soukissian, Georgia D. Kalantzi, Ioanna Karagali

In this work, a new de-clustering method is presented and applied for the estimation of design values of S H by means of the “Peaks-OverThreshold” (POT) method. An essential requirement of the POT method refers to the independency among exceedances of a …

gr (code pays fourni par la source)