In dynamic optimization problems where optimal solutions change over time, traditional ant colony optimization (ACO) algorithms face limitations. This study explores the adaptation of multi-colony ACO algorithms, known for their enhanced search capabilities in stationary problems, to tackle optimization problems in dynamic environments. Various strategies for exchanging information between colonies, which is a critical factor influencing algorithm performance, are investigated. Using the dynamic traveling salesman problem as a foundation, we generate test cases to reflect real-world complexities. Our results on a set of problem instances reveal that the choice of communication strategy between colonies significantly impacts the adaptability and efficiency of multi-colony ACO algorithms in tracking moving optimum.

Neural Radiance Fields (NeRFs) is emerging as an innovative approach for generating in the reality-based 3D modelling techniques by employing an artificial neural network that optimizes a volumetric scene function based on a collection of input views [1], [2], [3]. This approach offers unprecedented prospects for multiscale 3D modelling and analysis.This study delves into the application of NeRF technology for processing aerial-born imagery [4] to evaluate its effectiveness for the creation of Digital Surface Models (DSM) compared with traditional photogrammetric techniques.

Kouris dam is the main water reservoir in Cyprus, located in Limassol, transferring water from the western part of Troodos mountains to the eastern part of the island, both for domestic and irrigation use. It is a 113 m high zoned earthfill dam with a central clay core. Since its construction, in 1988, it has overflown three times in 2004, 2012 and 2020. Therefore, the need for its continuous inspection is of great importance for safety reasons. For the detection of surface deformation in Kouris dam, the Persistent Scatterers Interferometry technique was applied on 167 Sentinel-1 images from 2015 to 2023. The InSAR time-series processing revealed small-scale displacements on the downstream slope of the dam with a maximum rate of -5mm/y. The LOS displacements were validated by geodetic measurements, provided by the Water Development Department of Cyprus. This can serve as a valuable tool for risk assessment and mitigation.

The MedRIN (Mediterranean Regional Information Network) established in 2018, is a network composed of investigators in the United States and Europe, with the charter to further Earth Observation (EO) scientific collaboration in the Mediterranean region of the globe [1]. The MedRIN is structured within the framework of the Global Observations of Forests Cover and Land-use Dynamics (GOFC-GOLD), which is a coordinated international program led by the National Aeronautics and Space Administration (NASA) and the European Space Agency (ESA), working to provide ongoing space-based and in-situ observations of the land surface to support sustainable management of terrestrial resources at different scales [2]. The GOFC-GOLD program acts as an international forum to exchange information, coordinate satellite observations, and provide a framework for and advocacy to establish long-term monitoring systems. It was established as a part of a Committee on Earth Observation Satellites (CEOS) pilot project in 1997, with a focus on global observations of forest cover [3]. The GOFC-GOLD supports the structuring of ad-hoc collaborative scientific communities, such as MedRIN, to serve as a liaison between land-cover/land-use change remote sensing researchers, developers, and stakeholders.

Ultraviolet B (UVB) radiation plays a crucial role in supporting life on Earth and sustaining ecosystems; however, excessive exposure poses risks, such as sunburns, premature aging, and an elevated susceptibility to skin cancers. The Ultraviolet Index (UVI), a numerical scale quantifying solar UV radiation intensity with respect to its efficiency in causing erythema in the human skin, serves as a valuable tool for guiding sun exposure practices and implementing protective measures.Cyprus, a sun-drenched country, experiences exceptionally high UVI levels (10+) during the summer months. Despite this, there is currently no official forecast or related information available regarding UV levels on the island. To address this gap, we introduce the Cyprus Erythemal Radiation Forecasting System (CERYFOS), a novel initiative designed to provide guidance on prudent sun exposure. By delivering UVI forecasts and harnessing Cyprus-specific UV radiation data, CERYFOS aims to educate the public on optimal sun exposure durations and empower authorities to proactively address risks associated with prolonged exposure to UV radiation.

This report examines the extent of research on coastal erosion and the developing techniques for identifying shorelines in the Mediterranean region. The Insight Review consolidates findings from scientific literature, employing advanced remote sensing technologies, AI machine learning algorithms, and geospatial analytic methodologies. The report offers a comprehensive analysis of the issues encountered by Mediterranean coastlines by investigating multiple causes that contribute to coastal erosion, including climate change, human activities, and natural processes.It provides a concise overview of the consequences of climate change in the area. The text underscores the significance of employing different data sources to improve accuracy and precision. The paper also emphasizes the recent progress in satellite images, LiDAR technology, unmanned aerial vehicles, and neural network techniques, which could significantly revolutionize coastal monitoring. The findings presented in this study have practical implications for politicians, environmental agencies, and coastal communities. They provide essential information on how to effectively address the negative impacts of erosion and preserve the natural balance of coastlines.

In this paper, we present the new research infrastructure of the ERATOSTHENES CoE for aerosol and cloud remote sensing observations and its capabilities to participate in cal/val activities. The research facility is installed less than 2 km from the coastline of Limassol, Cyprus. The multiplatform for atmospheric research consists of a multiwavelength lidar, 35 GHz cloud radar, a microwave radiometer, and ancillary instruments to become a fully ACTRIS cloud and aerosol remote sensing station. Measurements performed at Limassol’s station were already utilized for the validation of the aerosol products of Sentinel 5P and AEOLUS and will be used for the validation of the EarthCARE mission.

Over a decade, Pissouri village has suffering from an active and fast-moving landslide causing severe damages in many properties and the broader landscape. This study presents an investigation to estimate the absolute velocity of the landslide using integrated satellite-based techniques, utilizing the only strategic infrastructure unit for monitoring geohazards in Cyprus, named CyCLOPS. A dataset of 37 Sentinel-1 acquisitions in ascending mode, covering an interval time from July 2021 to November 2023 were processed in GAMMA software. The GNSS monitoring of Pissouri was performed using the cutting-edge equipment of CyCLOPS, showing significant local displacements. In cases of an active and fast-moving landslide, the integration of both Synthetic Aperture Radar (SAR) and Global Navigation Satellite System (GNSS) data is essential to monitor, estimate and understand the absolute velocity of the landslide.

This paper explores how the Eratosthenes CoE that has been established in Cyprus through the EXCELSIOR H2020 Teaming project can be a hub for Earth Observation activities in Cyprus and the Eastern Mediterranean, Middle East and North Africa (EMMENA) region. Due to its geographical proximity, EXCELSIOR can become a hub for partners in Middle Eastern and Northern African countries. Cyprus' unique geostrategic position can support Earth Observation from satellite programmes in three continents and provide valuable services in the processes of satellite calibration and validation. Finally, the distinct needs and opportunities that motivate the establishment of an Earth Observation Centre of Excellence in Cyprus are presented in this paper.

Oil spills are a major source of marine pollution affecting the environment, economy, and marine ecosystems. Toxic chemicals from oil spills can remain in the ocean for years and even sink to the seabed, affecting sedimentation rates. Although many oil spills are caused by accident, some are caused intentionally by cargo ships dumping waste oil and bilge water. It is very difficult to locate, detect and remove oil from the ocean surface. However, regular monitoring can help prevent illegal dumping and aid remediation efforts. This work aims to detect oil spills in the North-Eastern part of Cyprus using a deep learning model. The results are compared with a conventional Adaptive Thresholding Algorithm. The comparisons demonstrate that the deep learning model has higher accuracy than the adaptive thresholding algorithm.

Flood is defined as one of the most devastating natural hazards that lead to immeasurable damages in terms of human settlements and economic losses. As part of the Mediterranean region, Cyprus suffers from this disaster, being subjected to extreme events, land use changes and economic development. In this study, flood hazard is estimated and its extent on residential areas, villages, and agricultural areas located within the Garyllis basin is mapped and analyzed with the integration of remote sensing techniques, GIS, in-situ data, field visits and hydraulic modeling. Open-source HEC-RAS software has been used to estimate the spatial pattern of water surface depths during a 24-hour event for a 1000-year return period. Preliminary results indicate that the areas most susceptible to flooding are observed at the southern part of the basin. The intent is to assist policy makers and planners in the development of flood mitigation measures.

This study uses advanced spatial analysis and geoinformatics to evaluate how urbanization affects archaeological sites. The research focuses on Amathus in Cyprus. Using data cube, remote sensing, and GIS, the study examines environmental changes, particularly vegetation patterns, around the site. Techniques such as Principal Component Analysis and Pearson correlation uncover a moderate positive relationship between changes in the Normalized Difference Vegetation Index and urban development. The study also investigates the spatial connection between urban structures and the archaeological site within 100 and 300-meter buffer zones. Emphasizing the importance of geospatial technologies in assessing and managing cultural heritage risks, the research highlights their role in real-time monitoring and developing predictive models. This approach is crucial for comprehending and mitigating the effects of urban expansion on heritage sites, advocating for the integration of these methodologies in heritage management.

This paper analyses polarimetric weather radar data to explore their potential for comprehensive and reliable precipitation and thus, drought monitoring in Cyprus. Reflectivity measurements from the two ground-based X-band dual-polarization radars of the Department of Meteorology of the Republic of Cyprus are compared with measurements obtained from the Dual-Frequency Precipitation Radar (DPR) onboard NASA’s Global Precipitation Measurement (GPM) mission in order to calibrate the ground-based reflectivity. The comparison is done using a volume matching method that allows us to associate the datasets both in space and time. To correct the attenuation, we examine a Z-A relationship approach and the forward gate-by-gate attenuation correction based on an iterative approach with scalable constraints. Preliminary results show a significant underestimation of the ground-based reflectivity, as well as a notable impact of attenuation that leads to a major source of error for rainfall estimation.

The geological, ecological, and biological ecosystems of the planet have changed because of the global climate crisis, and this poses a serious threat to humanity as well as the conservation of agricultural productivity and food security. The European Commission outlined the continent's objective to become climate neutral by 2050 with zero net Greenhouse Gas (GHG) emissions. Soil organic carbon (SOC) is closely related to soil quality and has a significant impact on how soil and plants interact. SOC monitoring gives a unique role in agricultural sustainability thus precise prediction and monitoring of SOC is essential. Remote Sensing (RS) evolution, big data accessibility and Deep Learning (DL) architectures present enormous potential for extensive SOC monitoring. Several RS applications (e.g., Sentinels, MODIS, Landsat etc.) along with machine learning and DL methodologies (e.g., RF, ANN, CNN etc.) used in literature for SOC prediction. The current review paper emphasizes on the latest RS approaches used for SOC monitoring.

Soil organic matter (SOM) is an important component that exists in soils because it is closely related to soil health and fertility. Hence, knowing the existence of SOM in soils is crucial for management corrections. So far laboratory analysis is required for SOM determination. However, such procedures are costly and labor-time consuming. Alternative methodologies for SOM determination are needed to achieve sustainability. The rise of artificial intelligence and machine learning provide promising approaches that can be exploited for this purpose. The aim of this study is to identify the best regression algorithm for SOM prediction for citrus planted soils. Several machine learning approaches are investigated, including adaptive boosting, gradient boosting, random forest, and multi-layer perceptron neural network.

The rapid growth of Earth Observation (EO) and Remote Sensing (RS) data has underscored the critical need for identifying optimal solutions to effectively manage EO Big Data. This entails simplifying data sharing and facilitating adaptation across multidisciplinary applications to better serve the research community. Various architectures and structures have been developed to manage and deploy these data in an analysis-ready format. In this study, we provide a concise overview of an advanced EO Big Data infrastructure located in Limassol, Cyprus, comprising diverse data sources acquired from an acquisition station, an atmospheric ground base station, and various living labs. Additionally, we present the EO data ecosystem of Cyprus that is specifically designed to efficiently store the aforementioned data.

Monitoring groundwater quality is a costly and time-consuming process. The use of machine learning models has proven to be a suitable alternative for predicting groundwater quality indicators. In this work, an artificial neural network model has been trained via particle swarm optimization (PSO) with hydrochemical data collected from a coastal aquifer in Tunisia. The validity of the PSO-trained model is evaluated based on different performance indicators, demonstrating higher accuracy than the model trained with the traditional gradient descent method concerning all the evaluation metrics. These results are consistent with the well-known ability of these methods to perform more effective searching in the solution space.

Wildfires detection is a major issue for authorities. There are various causes of fire events with the most common being human influence. A fire risk prediction model through the analysis of geo-environmental and climate data is important for early warning and fire management. In this work, a dataset from multiple modalities, including road density, travelers, forest-agriculture interface, burned areas from historical fire events, metrological data, land cover, vegetation indices from data cube, is generated. Artificial intelligence and machine learning models can use this multimodal dataset to improve forest fire management.

This study examines the long-term dynamics of the Paphos forest in Cyprus using Landsat satellite data for Vegetation Indices (VIs), MODIS data for evapotranspiration, and CHIRPS data for precipitation from 1991 to 2022. Sen's slope method was applied to analyse the trends in the data, revealing statistically significant positive trends in the vegetation indices despite the nearly constant precipitation, indicating increased forest vegetation over the past 30 years. Scatterplots were created mainly to examine correlations within the VIs and precipitation data but with low R-squared values ranging between 0.15-0.44. The study outcomes highlight a complex relationship with evapotranspiration and a weak correlation between precipitation and vegetation indices. These findings could be essential in understanding how forests work, especially in a semi-arid environment like Cyprus.

This paper aims to introduce the concept and objectives of the recently funded AI-OBSERVER Horizon Europe Twinning project titled “Enhancing Earth Observation capabilities of the Eratosthenes Centre of Excellence on Disaster Risk Reduction through Artificial Intelligence”. The AIOBSERVER project aims to significantly strengthen and stimulate the scientific excellence and innovation capacity of the ERATOSTHENES Centre of Excellence on the use of Artificial Intelligence for Earth Observation in the Disaster Risk Reduction thematic area, as well as the research management and administrative skills, of the Centre. This will be achieved through a series of capacity building and targeted research activities, having the support of internationally leading institutions, i.e., the German Research Centre for Artificial Intelligence from Germany and the University of Rome Tor Vergata from Italy, assisting the ERATOSTHENES Centre of Excellence to reach its longterm objective of raised excellence on Artificial Intelligence for Earth Observation on environmental hazards.

This review delves into the pressing need and evolving perspectives on stakeholder engagement to achieve sustainable, resilient, and inclusive ecosystem services, particularly in the context of climate change mitigation and adaptation. Understanding and collaboration among key sectors are crucial to reach these objectives. The failure of many initiatives to meet their targets often results from the absence of a unified strategy for involving all stakeholders. Moreover, this review underscores the importance of co-governance and co-creation as integral aspects of effective stakeholder engagement, fostering a sense of ownership among stakeholders. By examining the current landscape and diverse strategies, this study emphasizes the significance of adopting the quintuple helix innovation framework as a holistic approach for sustainable and inclusive stakeholder engagement in advancing EU climate objectives. Finally, the study introduces the co-eco-approach as a potential step forward for achieving the targets of the European Green Deal and New Bauhaus initiatives.

This study focused on burned area mapping and burn severity estimation for the Arakapas fire event in Cyprus. For the purpose of the study Sentinel-2 images, before and after the fire event were used for the development of the dNBR and the RdNBR spectral indices, which are the most common spectral indices for assessing the burn severity and burned area estimation. For the validation of the fire severity map, field data were collected for the CBI and GeoCBI index calculation. The fire severity maps were compared with the field measurements of the CBI and GeoCBI. Based on Pearson Correlation the RdNBR map has a very high correlation with GeoCBI (PC=83%) and high correlation with CBI (PC=71%) in contrast with the dNBR spectral index which has a moderate correlation (PC=59% and PC=54%) with CBI and GeoCBI respectively. Based on these results the RdNBR spectral index is better for the burned severity mapping.

Landslides are a significant geohazard with global implications, causing fatalities, infrastructure damage, and economic consequences. Cyprus, located over the Mediterranean fault zone in the Eastern Mediterranean region, experiences active landslides and slope instabilities due to its unique geodynamic regime and seismic activity. Monitoring ground displacements caused by landslides is crucial for early detection and response and can be performed using many techniques like ground-based or satellite-based geodetic, photogrammetric, and Earth Observation (EO)- based techniques. The study focuses on utilizing the Google Earth Engine (GEE) platform and Sentinel-1 and Sentinel-2 satellite imagery to rapidly map landslides in the Paphos District of Cyprus. Multitemporal SAR change detection using Sentinel-1 images and spectral indices from Sentinel-2 data were employed. The results were validated using highresolution images from Google Earth and data from the Geological Survey Department. The study successfully identified landslide areas, confirmed by ground truthing, and provided insights into the timing of landslide occurrences.

This paper aims to explore the integration of field spectroscopy and satellite remote sensing approaches to detect underground structures in Cyprus. An SVC-HR1024 field spectroradiometer was used and in-band reflectances were determined for high resolution Landsat 8 satellite sensor. In this study, three test areas were identified, analyzed and modelled: Area (a) which is a Vegetation Area covered with vegetation (barley), in the presence of an underground military structure, Area (b) which is a Vegetation Area covered with vegetation (barley), in the absence of an underground military structure and Area (c) with the existing natural soil, in the presence of an underground military structure. Also measurements are taken in order to study possible differences of the spectral signature of vegetation as a result of the existence underground structures and non - existence underground structures.

This paper aims to explore the integration of field spectroscopy and satellite remote sensing approaches to detect underground structures in Cyprus. A SVC-HR1024 field spectroradiometer was used and in-band reflectances were determined for medium resolution Landsat 7 ETM satellite sensor. In order to study possible differences of the spectral signature of vegetation, Normalized Difference Vegetation Index (NDVI), Simple Ratio (SR) and Enhanced Vegetation Index (EVI) have been used for the detection of underground military structures. The simulation results show that Vegetation Indices are highly useful and extremely valuable for detection underground infrastructures in Cyprus. In this study, two test areas were identified, analyzed and modelled: Area (a) which is a Vegetation Area covered with vegetation (barley), in the presence of an underground military structure, and Area (b) which is a Vegetation Area covered with vegetation (barley), in the absence of an underground military structure.