ΕΛ EN
Home | People | Kalogirou, Eleftheria
25
Scholarly Works
52%
OA Ratio
40%
Collaborative Ratio
Scholar

Kalogirou, Eleftheria

4
H-index (Scopus)
105
Scholar Citations

Scholarly Works

Research Output

Recent Publications

Marine Oil Spill Monitoring using Sentinel-1 Dual-Pol SAR Data: An Operational GEE Framework

Hadjimitsis, Diofantos G., Iqbal, Muhammad Amjad, Kalogirou, Eleftheria, Makri, Despina, Mettas, Christodoulos
Publishing year: 2026
Journal article
IEEE Geoscience and Remote Sensing Letters, 2026
Repository
Oil Spills (OS) pose serious hazards to economies relying on the sea. Remote sensing facilitates effective offshore OS monitoring. As a result, the Sentinel-1 Synthetic Aperture Radar (SAR) missions regularly deliver open-source cloud-stored data through the Google Earth Engine (GEE) platform. This paper proposed an interactive GEE framework for operational use with Sentinel-1 Ground Range Detected (GRD) Dual-pol SAR data. An Eigen descriptor is developed to examine multiple OS incidents in GEE, and two OS from Cyprus are described in detail. OS signatures extracted from Single Look Complex (SLC) SAR and GRD are compared with the baseline Random Forest (RF) algorithm. Also, OS delineation results are showcased for the three SAR scenes reported in the literature. Qualitative outcomes show effectiveness for the GEE-based framework, whereas quantitative results are outstanding. Collectively, the proposed technique achieved an mIoU of 96%, a recall of 99%, an F1-score of 99% and accuracy of 98%. The novelty of the developed technique is an operational value of the GEE platform for Near-Real-Time (NRT) OS monitoring and actionable remote marine environment safety using SAR images as a “Black-box”.

Oil Spill Detection using Convolutional Neural Networks and Sentinel-1 SAR Imagery

Christofi, Konstantinos, Hadjimitsis, Diofantos G., Iqbal, Muhammad Amjad, Kalogirou, Eleftheria, La Pegna, Valeria, Makri, Despina, Mettas, Christodoulos, Tzouvaras, Marios
Publishing year: 2025
Conference paper
ISPRS Geospatial Week 2025 “Photogrammetry & Remote Sensing for a Better Tomorrow, 2025, Volume 48, Issue XLVIII-G-2025
Repository
Pages 757-764
Oil spills impose significant environmental challenges, leading to critical consequences for marine ecosystems and sea habitant’s health. Early delineatin and efficient surveillance are absolutely important to prevent more contamination and support quick hazards reduction. This study focuses on detecting oil spills using satellite imagery and deep learning models, specifically Convolutional Neural Networks (CNN). The dataset used to train the CNN comprised 695 images extracted from Sentinel-1 Synthetic Aperture Radar (SAR) data over the Mediterranean Sea. In particular, 486 images (70%) were allocated for training, 139 images (20%) for validation, and 70 images (10%) for testing. Preprocessing involved a thresholding technique to enhance feature extraction and improve classification precision. The CNN model achieved a high test accuracy of 98.57%, with perfect precision (1.0000), recall of 96.43%, and F1 score of 0.9818, demonstrating strong performance and reliability. These high accuracy levels underscore the model’s efficiency in identifying oil spills and its soundness in handling unseen data. The significance of this work is in using satellite-based deep learning models for scalable and automated oil spill detection, therefore providing a reliable and effective substitute for more traditional monitoring systems. The model may be applied over large oceanic areas by using satellite images, thereby supporting marine ecosystem preservation and enhancing environmental risk ma...

Integrated Coastal Vulnerability Index (ICVI) Assessment of Protaras Coast in Cyprus: Balancing Tourism and Coastal Risks

Doukanari, Marina, Eliades, Marinos, Hadjimitsis, Diofantos G., Kalogirou, Eleftheria, Kontoes, Charalampos, Neocleous, Kyriacos, Prodromou, Maria, Theocharidis, Christos
Publishing year: 2025
Journal article
Geographies, 2025, Volume 5, Issue 1
Repository
Pages 1-27
Coastal areas are highly dynamic environments, vulnerable to natural processes and human interventions. This study presents the first application of the Integrated Coastal Vulnerability Index (ICVI) in Cyprus, focusing on two major tourism-dependent beaches, Fig Tree Bay and Vrysi Beach, located along the Protaras coastline. Despite their economic significance, these coastal areas face increasing vulnerability due to intensive tourism-driven modifications and natural coastal dynamics, necessitating a structured assessment framework. This research addresses this gap by integrating the ICVI with geographical information system (GIS) and analytic hierarchy process (AHP) methodologies to evaluate the coastal risks in this tourism-dependent environment, providing a replicable approach for similar Mediterranean coastal settings. Ten key parameters were analysed, including coastal slope, rate of coastline erosion, geomorphology, elevation, tidal range, wave height, relative sea level rise, land cover, population density, and road network. The results revealed spatial variations in vulnerability, with 16% of the coastline classified as having very high vulnerability and another 16% as having high vulnerability. Fig Tree Bay, which is part of this coastline, emerged as a critical hotspot due to its geomorphological instability, low elevation, and intensive human interventions, including seasonal beach modifications and infrastructure development. This study underscores the need for su...

Habitat types mapping using remote sensing techniques in Cyprus

Hadjimitsis, Diofantos G., Iqbal, Muhammad Amjad, Kalogirou, Eleftheria, Makri, Despina, Mettas, Christodoulos
Publishing year: 2025
Conference paper
2025, Volume 13816
Repository
Pages 1381606-1381607
Oceans cover 75% of the Earth's surface and account for 99% of the planet's living space by volume. They are home to around 200,000 known species, with Posidonia oceanica meadows being among the oldest. These habitats are very important coastal ecosystems, providing vital services such as habitat for marine life, coastal protection, and oxygen generation. Despite their importance, seagrass meadows, including Posidonia oceanica, face significant threats, including degradation and loss, with slow regeneration rates. As a result, their monitoring and conservation are essential for maintaining biodiversity and the health of marine ecosystems. This study presents an innovative approach for mapping and monitoring seagrass meadows in western Cyprus using the Google Earth Engine (GEE) platform. Leveraging freely available satellite data from the Copernicus Program, we demonstrate how Earth observation tools can be utilized to map the spatial extent of seagrass meadows and other significant habitat types. This approach supports the monitoring efforts of the European Union’s conservation frameworks and aligns with the United Nations' Sustainable Development Goal (SDG) 14, focusing on the conservation of marine life. The integration of GEE for seagrass mapping offers a scalable and efficient method to track habitat changes, contributing to more effective conservation strategies and ensuring the sustainable use of coastal ecosystems.

Comparison of Novel, Classical and Developed AI Techniques for SAR Oil Spill Detection

Hadjimitsis, Diofantos G., Iqbal, Muhammad Amjad, Kalogirou, Eleftheria, Makri, Despina, Mettas, Christodoulos, Tzouvaras, Marios
Publishing year: 2025
Conference paper
International Conference on Machine Intelligence for Geoanalytics and Remote Sensing, 2025
Repository

CFAR-based automatic ship detection exploiting polarimetric correlation descriptors

Hadjimitsis, Diofantos G., Iqbal A, Muhammed, Kalogirou, Eleftheria, Makri, Despoina, Mettas, Christodoulos, Tzouvaras, Marios
Publishing year: 2025
Conference paper
Eleventh International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2025), 2025, Volume 13816
Repository
Pages 1381603-1381607
Synthetic Aperture Radar (SAR) provides a reliable remote sensing solution for detecting ships over vast oceanic regions under all-weather and day-night conditions. However, the normalized radar cross-section (NRCS) often encounters ambiguities that hinder accurate detection. To address this, we utilized the polarimetric correlation of SAR channels, including co-, cross-, and dual-polarization, to effectively mitigate or suppress these ambiguities (or clutter). By integrating these polarimetric correlation descriptors with a constant false alarm rate (CFAR) algorithm, we achieve automatic and robust ship detection. Experimental results demonstrate that the proposed approach yields high detection accuracy with minimal root mean square error (RMSE), outperforming conventional manual image interpretation methods. The framework was applied to SAR data for the Mediterranean Sea near Cyprus, showcasing its potential for detecting and monitoring ships, preventing illegal fishing, and addressing maritime security challenges.

25
Unique publications
52%
Open access (13 publications; 3 without information)
40%
With other institutions (10 publications; 3 without information)

H-Index Reports

Index type Scopus Google Scholar Web of Science
H-index 4 4 0
H5-index 4 4 0
H10-index 4 4 0

Publications per year and source

No description yet.