Ilias Chamatidis

Mr. Ilias Chamatidis

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 June 2024 in Water
Verified
Journal Article
Open access
PDF file
ICIlias Chamatidis
Ilias Chamatidis
Denis IstratiDenis Istrati
Denis Istrati
Nikos LagarosNikos Lagaros
Nikos Lagaros
Floods are devastating phenomena that occur almost all around the world and are responsible for significant losses, in terms of both human lives and economic damages. When floods occur, one of the challenges that emergency response agencies face is the identification of the flooded area so that access points and safe routes can be determined quickly. This study presents a flood detection methodology that combines transfer learning with vision transformers and satellite images from open datasets. Transformers are powerful models that have been successfully applied in Natural Language Processing (NLP). A variation of this model is the vision transformer (ViT), which can be applied to image classification tasks. The methodology is applied and evaluated for two types of satellite images: Synthetic Aperture Radar (SAR) images from Sentinel-1 and Multispectral Instrument (MSI) images from Sentinel-2. By using a pre-trained vision transformer and transfer learning, the model is fine-tuned on these two datasets to train the models to determine whether the images contain floods. It is found that the proposed methodology achieves an accuracy of 84.84% on the Sentinel-1 dataset and 83.14% on the Sentinel-2 dataset, revealing its insensitivity to the image type and applicability to a wide range of available visual data for flood detection. Moreover, this study shows that the proposed approach outperforms state-of-the-art CNN models by up to 15% on the SAR images and 9% on the MSI images. Overall, it is shown that the combination of transfer learning, vision transformers, and satellite images is a promising tool for flood risk management experts and emergency response agencies.

Verified
Conference Paper
Open access
PDF file
ICIlias Chamatidis
Ilias Chamatidis
Georgios Theodoros TzanesGeorgios Theodoros Tzanes
Georgios Theodoros Tzanes
DIDenis Istrati
Denis Istrati
NLNikos D. Lagaros
Nikos D. Lagaros
Anastasios I. StamouAnastasios I. Stamou
Anastasios I. Stamou
Weather prediction is a key aspect of today’s society and its activities. Accurate predictions are crucial for efficiently organizing human activities, particularly in the agricultural, transportation and energy sectors. In this paper, two deep neural networks, designed based on a long short-term memory architecture, are developed to predict the occurrence of rainfall events and the respective amount of rainfall on the island of Nisyros in the south Aegean Sea. Two deep neural networks are developed, serving two different learning tasks. The first network acts as a classifier that assesses whether it is going to rain or not and, sequentially, the second network performs a regression task, quantifying the anticipated amount of rainfall. The performance of such prediction models is highly dependent on input sequences. Among others, the lookback time window shapes those input sequences by determining the number of past time steps to be taken into account. The ideal time window for the classifier involves 24 time steps (i.e., 4 h), resulting in increased accuracy levels exceeding 96.45%. The predictions of the regression model, which has the same lookback time window, feature low errors, measured as 6.635 and 1.411 mm using the mean-square-error and mean-absolute-error indices, respectively.

4 December 2023
Verified
Conference Paper
Open access
ATAlexandros Troupiotis-Kapeliaris
Alexandros Troupiotis-Kapeliaris
GSGiannis Spiliopoulos
Giannis Spiliopoulos
GGGeorgios Grigoropoulos
Georgios Grigoropoulos
EFEvangelia Filippou
Evangelia Filippou
ICIlias Chamatidis
Ilias Chamatidis
DZDimitris Zissis
Dimitris Zissis

28 December 2025 in Discover Civil Engineering
Verified
Journal Article
Open access
PDF file
SVStefanos Voulgaris
Stefanos Voulgaris
SCSpyros Chandrinos
Spyros Chandrinos
ICIlias Chamatidis
Ilias Chamatidis
GKGeorge Kazakis
George Kazakis
PTPantelis Tsakalis
Pantelis Tsakalis
Nikos LagarosNikos Lagaros
Nikos Lagaros
In this work we develop and validate neural-network (NN) constitutive models for structural steels under monotonic and cyclic loading, using internal-variable inputs to encode path dependence. For monotonic tension at \(200-800^{\circ }C\) (Kirby-Preston dataset), a feed-forward NN (\(1-10-10-1\), sigmoid activation) reproduces experimental stress-strain curves to high fidelity; across temperature-specific curves extracted from the experimental data, the median normalized Chamfer distance is \(0.355\%\) of the plot height \((IQR: 0.026-0.361\%)\). For cyclic compression of stainless steel 316 (Chaboche dataset), the internal-variable NN (\(5-30-30-1\)) aligns with the experimental hysteresis loops with median normalized Chamfer distance \(0.032\%\), indicating near-pixel-level curve overlap. We provide new quantitative validation tables and sensitivity plots; results indicate weak dependence on hidden-node count and epochs within practical ranges. The approach is computationally lightweight at inference and amenable to generalization via internal-state encoding. Limitations at very high temperatures (\(>750^{\circ }C\)) and low-strain transitions are discussed, along with integration paths for physics-guided constraints.