Stella Girtsou

Dr. Stella Girtsou


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
2 March 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
AAAlexis Apostolakis
Alexis Apostolakis
SGStella Girtsou
Stella Girtsou
GGGiorgos Giannopoulos
Giorgos Giannopoulos
NBNikolaos S. Bartsotas
Nikolaos S. Bartsotas
CKCharalampos (Haris) Kontoes
Charalampos (Haris) Kontoes
Next day wildfire prediction is an open research problem with significant environmental, social, and economic impact since it can produce methods and tools directly exploitable by fire services, assisting, thus, in the prevention of fire occurrences or the mitigation of their effects. It consists in accurately predicting which areas of a territory are at higher risk of fire occurrence each next day, exploiting solely information obtained up until the previous day. The task’s requirements in spatial granularity and scale of predictions, as well as the extreme imbalance of the data distribution render it a rather demanding and difficult to accurately solve the problem. This is reflected in the current literature, where most existing works handle a simplified or limited version of the problem. Taking into account the above problem specificities, in this paper, we present a machine learning methodology that effectively (sensitivity > 90%, specificity > 65%) and efficiently performs next day fire prediction, in rather high spatial granularity and in the scale of a country. The key points of the proposed approach are summarized in: (a) the utilization of an extended set of fire driving factors (features), including topography-related, meteorology-related and Earth Observation (EO)-related features, as well as historical information of areas’ proneness to fire occurrence; (b) the deployment of a set of state-of-the-art classification algorithms that are properly tuned/optimized on the setting; (c) two alternative cross-validation schemes along with custom validation measures that allow the optimal and sound training of classification models, as well as the selection of different models, in relation to the desired trade-off between sensitivity (ratio of correctly identified fire areas) and specificity (ratio of correctly identified non-fire areas). In parallel, we discuss pitfalls, intuitions, best practices, and directions for further investigation derived from our analysis and experimental evaluation.

13 September 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AYAnastasia Yfantidou
Anastasia Yfantidou
Melpomeni ZokaMelpomeni Zoka
Melpomeni Zoka
NSNikolaos Stathopoulos
Nikolaos Stathopoulos
MKMartha Kokkalidou
Martha Kokkalidou
SGStella Girtsou
Stella Girtsou
CKCharalampos (Haris) Kontoes
Charalampos (Haris) Kontoes
Forest fires can result in loss of life, damage to infrastructure, and adverse environmental impacts. This study showcases an integrated approach for conducting high-detail fire risk assessment and supporting strategic planning and management of fire events in peri-urban areas that are susceptible to forest fires. The presented methodology encompasses fire hazard modeling, vulnerability and exposure assessment, and in situ observations. Numerous fire hazard scenarios were tested, simulating the spatiotemporal spread of fire events under different wind characteristics. The vulnerability of the studied areas was assessed by combining population data (density and age) and building characteristics, while the exposure parameter employed land value (EUR/m2) as an indicator for qualitatively estimating potential economic effects in the study area. Field campaigns facilitated the identification and recording of critical areas and points, including high-risk buildings and population gathering areas, which subsequently informed the mitigation and fire management planning suggestions. Moreover, field recordings acted as an iterative process for validating and updating the fire risk maps. This research work utilizes state-of-the-art techniques to achieve an analysis of fire risk at a building-block level. Overall, the study presents an applied and end-to-end methodology for effectively addressing forest fire risk in peri-urban areas.

Verified
Conference Paper
Open access
PDF file
MPMaria Prodromou
Maria Prodromou
SGStella Girtsou
Stella Girtsou
GLGeorgios Leventis
Georgios Leventis
GCGeorgia Charalampous
Georgia Charalampous
AAAlexis Apostolakis
Alexis Apostolakis
DHDiofantos Hadjimitsis
Diofantos Hadjimitsis
Wildfire detection remains a critical challenge for authorities, with human activity being the leading cause. The historical conditions prevailing in burned forest areas require a comprehensive analysis at both the environmental and anthropogenic levels. This study presents a multidimensional dataset comprising data from 2008 to 2024 and integrating Earth observation data and anthropogenic, environmental, meteorological, topographic, and fire-related features. This study evaluates, through time series analysis, the impact of climate trends such as increased temperature in comparison with anthropogenic activities such as deliberate fires. Time series analysis reveals that although climatic conditions with increased temperature and reduced precipitation in Cyprus intensify the risk of fire, the presence of fire events is primarily due to deliberate actions. The findings of this study support national-scale fire modeling, offering a foundation for targeted prevention, early warning systems, and sustainable forest fire management strategies.

20 January 2025
Verified
Conference Paper
Open access
MPMaria Prodromou
Maria Prodromou
SGStella Girtsou
Stella Girtsou
GLGeorgios Leventis
Georgios Leventis
Dimitrios KoumoulidisDimitrios Koumoulidis
Dimitrios Koumoulidis
Marios TzouvarasMarios Tzouvaras
Marios Tzouvaras
DHDiofantos Hadjimitsis
Diofantos Hadjimitsis
This study presents the actions that are currently been conducted through a demonstration project in the framework of the EXCELSIOR funded project, entitled “Capitalizing on the ERATOSTHENES Data Cube to support the development of the Fire Risk Prediction Model” between the ERATOSTHENES Centre of Excellence and the National Observatory of Athens. 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. An effective wildfire risk prediction and management depend on the up-to-date, spatial explicit representation of the environment, mainly focusing on the biomass and characteristics of live and dead vegetation, which is the primary factor influencing fire behaviour and risk. In this work, a dataset from multiple modalities, including road density, travellers, forest-agriculture interface, burned areas from historical fire events, metrological data, land cover, vegetation indices from data cube, is generated. These factors are selected based on their potential correlation with the unique characteristics of the area investigated, the historical fire events, and the availability of relevant data. Artificial intelligence and machine learning models can use this multimodal dataset to improve forest fire management. Specifically, the combination of data cubes, machine learning, and geospatial ontology-based data access (OBDA) technologies, allows for effective harmonization of diverse data sources, enhancing the accuracy and efficiency of fire risk computations.ACKNOWLEDGEMENTThe authors acknowledge the 'EXCELSIOR': ERATOSTHENES: Excellence Research Centre for Earth Surveillance and Space-Based Monitoring of the Environment H2020 Widespread Teaming project (www.excelsior2020.eu). The 'EXCELSIOR' project has received funding from the European Union's Horizon 2020 research and innovation programme under Grant Agreement No 857510, from the Government of the Republic of Cyprus through the Directorate General for the European Programmes, Coordination and Development and the Cyprus University of Technology.

15 March 2025
Verified
Conference Paper
Open access
SGStella Girtsou
Stella Girtsou
LFLilli Freischem
Lilli Freischem
KBKyriaki-Margarita Bintsi
Kyriaki-Margarita Bintsi
GCGuiseppe Castiglione
Guiseppe Castiglione
ESEmiliano Diaz Salas-Porras
Emiliano Diaz Salas-Porras
JMJoppe Massant
Joppe Massant
Clouds affect Earth’s radiation balance by reflecting incoming sunlight (cooling effect) and trapping outgoing infrared radiation (warming effect). Their vertical distribution in the atmosphere significantly influences their radiative properties and overall climate impacts. However, how clouds will respond to climate change remains unknown: cloud feedbacks are the largest source of uncertainty in climate projections. Global 3D cloud data can help reduce these uncertainties, improve climate predictions, and support better decision-making.Clouds are observed globally from space using satellites, which provide insights into their distribution, structure, and evolution. Observations from the Cloud Profiling Radar (CPR) aboard NASA’s CloudSat mission have provided valuable information on the vertical distribution of clouds. However, its long revisit times (~ 16 days), narrow swath (1.4 km) and observations limited to the same local time each day hinder our ability to study the temporal evolution of clouds or their diurnal cycle. In contrast, imaging instruments observe larger regions with higher temporal resolution but only offer a top-down view with limited vertical information.In this work, we apply deep learning to images observed by geostationary satellites paired with vertical cloud profiles to extrapolate the vertical profiles beyond the observed tracks. Specifically, we use 11-channel imagery from the MSG/SEVIRI instrument, colocated with CPR vertical profiles. First, we pre-train models using self-supervised learning methods, specifically (geospatially-aware) Masked Autoencoders, applied to MSG/SEVIRI data from 2010. The pre-trained models are then fine-tuned for the 3D cloud reconstruction task using paired image-profile data. As only a small fraction of images overlap with CloudSat observations, the pre-training step enables us to exploit the full information contained in the MSG/SEVIRI images. We find that pre-training consistently improves reconstruction performance, particularly in complex regions such as the inter-tropical convergence zone. Notably, geospatially-aware pre-trained models incorporating time and coordinate encodings outperform both randomly initialized networks and simpler U-Net architectures, leading to improved reconstruction results compared to previous work.In the future, we plan to extend this method to longer time periods and apply it to ESA’s EarthCARE data, once available, to further improve 3D reconstructions and enable the development of long-term 3D cloud products.

15 May 2023
Verified
Other
Open access
SGStella Girtsou
Stella Girtsou
AAAlex Apostolakis
Alex Apostolakis
GGGiorgos Giannopoulos
Giorgos Giannopoulos
HKHarris Kontoes
Harris Kontoes
Introduction. This abstract presents FireRisk (https://riskmap.beyond-eocenter.eu/), a web platform that produces and visualizes timely, highly granular and accurate next day fire risk predictions on a country scale. FireRisk deploys a thorough data fusion process, and a state of the art machine learning (ML) pipeline, considering a large set of fire driving factors, in order to train scalable and accurate models for next day fire prediction. On top of them, it implements a web service that supports the visualization of fire risk predictions and metadata on a user friendly, map-based web application. The FireRisk platform. The high-level architecture is depicted in the following figure. It comprises three major components.(a) Data fusion: This component implements the collection, preprocessing, curation and harmonization of data, leading to the generation of a rich feature set of factors that affect fire occurrence and spread. 25 fire influencing factors were considered, including topography-related, meteorology-related, Earth Observation (EO) derived variables, and historical fire occurrence information. These have been extensively documented in [1].(b) ML model learning: This component implements a complete ML pipeline, that includes training and comparison of various ML algorithms, hyperparameter tuning and model (cross-)validation and selection. This pipeline allows the configurable production of robust ML models for fire risk prediction. It is extensively documented in [2].(c) Web platform: This component provides an interactive daily fire risk map to users through a web interface. The user is able to view the next day fire risk predictions for the current, as well as for historical days. The predictions are depicted in a five-grade scale (from very low to very high) adopting a five-grade coloring (blue to red). The user is also able to seamlessly change the zoom level, from the whole country level, to individual fine grained areas (grid cells 500m wide), for which individual predictions are provided. Finally, the web interface can be displayed on mobile devices, where the user can additionally view their position on the map.The risk map visualization functionality is implemented through a Web Map Service (WMS) that is configured on a GeoServer back-end installation. The daily map is stored in PostgreSQL as a raster image, using the geospatial extension PostGIS. For implementing we engage the WMS GeoServer’s capability to convert PostGIS geospatial tables to WMS.Ongoing work. Our ongoing work focuses on two directions: (a) We are adapting Deep Learning algorithms (Siamese Neural Networks and Semantic Segmentation CNNS), to better handle the extreme imbalance and the strong spatio-temporal correlations in the data. (b) We are incorporating explainability mechanisms that will allow the end user of the web application to receive simple and intuitive explanations on each individual prediction visualized on the map, based on the underlying fire driving factors.1. Girtsou, S. et al.. A Machine Learning methodology for next day wildfire prediction. In IGARSS, 2021.2. Apostolakis, A.; et al. Estimating Next Day’s Forest Fire Risk via a Complete Machine Learning Methodology. In Remote Sens. 2022. https://doi.org/10.3390/rs14051222