Кафедра математичного моделювання та аналізу даних (ММАД)
Постійне посилання на фонд
Сайт кафедри: http://mmda.ipt.kpi.ua/
Переглянути
Перегляд Кафедра математичного моделювання та аналізу даних (ММАД) за Автор "Drozd, Sofiia"
Зараз показуємо 1 - 11 з 11
Результатів на сторінці
Налаштування сортування
Документ Відкритий доступ A Novel Approach for Rapid Detection of Forest Degradation and Diseases Through Anomaly Analysis of Sentinel-2 Spectral Data(Anhalt University of Applied Sciences, 2025-04) Drozd, Sofiia; Kussul, Nataliia; Yailymova, HannaForest degradation is an ongoing global issue, with significant environmental impacts that necessitate efficient monitoring and management. This paper presents a simple yet effective method for detecting forest degradation using freely available Sentinel-2 satellite data and an anomaly detection approach. The aim of this study was to develop an accessible and reliable technique that could match the performance of more complex algorithms while using minimal computational resources. The research focused on spectral bands with 10-20 m resolution and vegetation indices (NDVI, NDMI, GCI, PSSRa) to analyze forest damage in the Harz region. The method involved identifying anomalies in the spectral data relative to randomly selected reference points from healthy forest areas, which were verified with high-resolution imagery from Google Earth Pro. The results demonstrated that specific Sentinel-2 bands, particularly B3 and B5, were the most informative for detecting damaged forests, while vegetation indices were less effective. By analyzing anomalies in these bands, we successfully tracked forest degradation from 2020 to 2024, revealing a significant increase in damage between 2020 and 2021, with a total of 68.1 thousand hectares of forest lost by 2024. The theoretical relevance of this study lies in the development of a cost-effective and straightforward method for forest monitoring, while the practical relevance is evident in its potential for large-scale forest management and conservation. This method provides an efficient tool for monitoring forest health with minimal data requirements and computational effort, offering a promising solution for forest managers and conservationists worldwide.Документ Відкритий доступ Assessing damage to agricultural fields from military actions in Ukraine: An integrated approach using statistical indicators and machine learning(2023) Kussul, Nataliia; Drozd, Sofiia; Yailymova, Hanna; Shelestov, Andrii; Lemoine, Guido; Deininger, KlausThe ongoing full-scale Russian invasion of Ukraine has led to widespread damage of agricultural lands, jeopardizing global food security. Timely detection of impacted fields enables quantification of production losses, guiding recovery policies and monitoring military actions. This study presents a robust methodology to automatically identify agricultural areas damaged by wartime ground activities using free Sentinel-2 satellite data. The 10 m resolution spectral bands and vegetation indices are leveraged, alongside their statistical metrics over time, as inputs to a Random Forest classifier. The algorithm efficiently pinpoints damaged fields, with accuracy metrics around 0.85. Subsequent anomaly detection delineates damages within the fields by combining spectral bands and indices. Applying the methodology over 22 biweekly periods in 2022, approximately 500 thousand ha of cropland across 10 regions of Ukraine were classified as damaged, with the most significant impacts occurring from March to September. The algorithm provides updated damage information despite cloud cover and vegetation shifts. The approach demonstrates the efficacy of automated satellite monitoring to assess agricultural impacts of military actions, supporting recovery analysis and documentation of war crimes.Документ Відкритий доступ Assessing Ukraine`s solar power potential: a comprehensive analysis using satellite data and fuzzy logic(Assembled by Conference Management Services, Inc., 2024) Drozd, Sofiia; Kussul, NataliiaThis study evaluates the land suitability for the placement of solar power stations in Ukraine, utilizing satellite data on climate factors (Global Horizontal Irradiance, temperature, precipitation, wind speed), topography (elevation, slope), and land use. Fuzzy logic, pairwise comparisons, and weighted linear combination methods were utilized to develop a high-resolution (100 m) land suitability map for the installation of solar power plants. The results show that more than half (54.5%) of Ukraine’s territory has a high suitability score (exceeding 0.65) for solar power stations, particularly in the southern and eastern regions, such as Odessa, Kherson, Mykolaiv, Zaporizhia, Donetsk, and Crimea. Only 10.68% of the land has a suitability score less than 0.6, and 18.18% is deemed absolutely unsuitable (with a score of 0, due to land cover), primarily located in the western and northern parts of the country. This indicates that Ukraine has significant potential for green energy production. The study provides an effective and useful tool for decision-making on the optimal location of solar power facilities in Ukraine.Документ Відкритий доступ Assessing Ukrainian Territory Suitability for Solar Power Station Placement Using Satellite Data on Climate and Topography(IEEE, 2023) Kussul, Nataliia; Drozd, SofiiaThis research aims to assess the suitability of Ukrainian territories for the placement of solar power stations using satellite data on climate and topographic characteristics. The suitability of the territories was determined using a weighted sum method, incorporating input parameters from climate maps sourced from ERA5- Land dataset, which included data on annual global horizontal solar irradiation (GHI), accumulated annual temperature above 25°C, average annual wind speed, and maps of accumulated annual precipitation. Additionally, topographic maps from the SRTM dataset were utilized, providing information on elevations, slopes, and terrain shading. Furthermore, data from Wikimapia on the locations of existing major solar power stations in Ukraine were used to verify the placement optimization. The results of the study revealed that the largest portion of the country (over 48%) exhibits moderate suitability scores (0.3-0.4). Favorable territories (suitability score above 0.3) outweigh unsuitable ones for solar power stations. The southern regions and the Crimean Peninsula offer the most favorable conditions for the placement of solar farms. Overall, all analyzed major solar power stations in Ukraine were located in optimal territories. Furthermore, it was found that certain regions such as Odessa, Poltava, Kharkiv, Zaporizhia, Dnipropetrovsk, Donetsk, and Luhansk demonstrate good suitability scores (0.3-0.4), yet they are not fully exploited. These regions hold significant potential for the future construction of powerful and productive solar power stations.Документ Відкритий доступ Detection of War-Caused Agricultural Field Damages Using Sentinel-2 Satellite Data with Machine Learning and Anomaly Detection(ACM Special Interested Group on Applied Computing (SIGAPP), 2024) Drozd, SofiiaThis research aims to detect war-caused damages on agricultural fields in Ukraine using Sentinel-2 satellite data. To achieve this, a Random Forest-based classification and an anomaly detection method deployed in the GEE cloud environment are applied. Two spectral bands - blue (B2) and green (B3) and two vegetation indices - NDVI and GCI - were used as input parameters. According to the results, the f1-score of classification reach 0.9. Using the developed methodology, more than 1.5 millions ha of fields were identified as damaged during the period of 2022--2023.Документ Відкритий доступ Digital Twins for Land Use Change(Springer Cham, 2025) Kussul, Nataliia; Giuliani, Gregory; Shelestov, Andrii; Drozd, Sofiia; Kolotii, Andrii; Salii, Yevhenii; Cherniatevych, Anton; Yavorskyi, Oleksandr; Malyniak, Volodymyr; Poussin, CharlotteRapid environmental, socio-economic, and geopolitical changes are accelerating transformations in land use patterns worldwide. To effectively monitor and predict these dynamics, DTs offer a promising approach by integrating real-time Earth observation data, climate models, AI-driven analytics, and socio-economic indicators. This paper identifies a critical gap in the application of Digital Twins (DT) frameworks for land use change monitoring, which remains underexplored. We propose a novel two-timescale DT architecture designed to track both rapid event-driven land cover changes (such as floods, wildfires, war-induced damage) and gradual long-term transformations, such as climate-induced agricultural shifts and urban expansion. By bridging the gap between advanced Earth observation technologies and decision-making processes, the proposed framework contributes to the development of AI-enhanced DT systems that facilitate climate adaptation, disaster response, and long-term sustainability in dynamic land systems.Документ Відкритий доступ Foundation Model Integration in a Multi-Instance Digital Twin System for Land Use Change(IEEE, 2025-09) Kussul, Nataliia; Shelestov, Andrii; Giuliani, Gregory; Drozd, Sofiia; Kolotii, Andrii; Salii, Yevhenii; Cherniatevych, Anton; Yavorskyi, Oleksandr; Malyniak, Volodymyr; Poussin, CharlotteThis paper presents a novel approach to monitoring land use change by integrating foundation models within a dual-timescale Digital Twin (DT) framework. While existing Earth system DTs primarily focus on atmospheric variables, our architecture explicitly addresses the dynamics of land use transformation. The proposed system utilizes a hierarchical structure of Digital Twin Instances and Aggregators that operate on two temporal scales: a rapid change component for near real-time vegetation monitoring and a gradual change component for long-term land use classification. O ur i mplementation r elies o n cloud-based data pipelines and foundation models for analyzing satellite imagery. It features a cognitive user interface that transforms complex geospatial data into contextually relevant insights. By incorporating pre-trained foundation models and physics-informed neural networks, our framework is designed to improve change detection accuracy while reducing computational requirements. Implementation experiences in Ukrainian and Swiss landscapes demonstrate the framework’s effectiveness across diverse geographic contexts.Документ Відкритий доступ Fusion of very high and moderate spatial resolution satellite data for detection and mapping of damages in agricultural fields(IEEE, 2023) Kussul, Natallia; Drozd, Sofiia; Skakun, Sergii; Duncan, Erik; Becker-Reshef, InbalThe war in Ukraine has resulted in significant losses in the agricultural sector due to damages to farmlands posing a threat to global food security. To restore the prosperity of the agricultural sector it is essential to detect and assess damages in agricultural fields and monitor their evolution. Commercial satellite data at very high spatial resolution $(\lt3 \mathrm{m})$ such as sub-meter imagery acquired by Maxar’s WorldView and Planet Labs’ SkySat platforms allow detection and mapping of artillery craters at fine scale. However, the frequency of acquisition and geographical coverage of this type of data is limited and may be quite low, e.g., 1-2 scenes per agriculture season. With the aim to continuously monitor the state of the fields over large areas in Ukraine we must compliment the analysis with satellite data at lower spatial resolution, e.g., daily PlanetScope at $\sim 3-\mathrm{m}$ and 10-m Sentinel-2/MSI. Here, we propose a data fusion approach to monitor artillery craters in agricultural fields using combination of satellite images acquired at different spatial and temporal resolution. Specifically, we use a single-date SkySat image at 0.5-m resolution with crater detection using previously developed deep learning approach along with multi-temporal data acquired by PlanetScope and Sentinel-2 images. For the latter, we detect anomalies of refelecant signal in the blue and green spectral bands and the Normalized Difference Water Index (NDWI). This approach is applied to a test area of 8,800 ha in Donetsk oblast. We found that with PlanetScope images at 3-m we were able to identify 202 ha of craters, or 63% of those in SkySat imagery; with Sentinel-2 at 10-m we detected 165 ha (or 51%) of craters. Craters with an area smaller than $100 \mathrm{m}{2}$ were poorly detected. By analyzing anomalies in multi-temporal PlanetScope and Sentinel-2 images, we were able to identify craters that were not detected in SkySat data highlighting the importance of temporal component in the data. Furthermore, with daily PlanetScope data combined with Sentinel-2 data (3-5 days), we were able to estimate the dates of crater appearances and analyze the dynamics of craters and their evolution.Документ Відкритий доступ Generative adversarial network augmentation for solving the training data imbalance problem in crop classification(2023) Shumilo, Leonid; Okhrimenko, Anton; Kussul, Nataliia; Drozd, Sofiia; Shkalikov, OlehDeep learning models offer great potential for advancing land monitoring using satellite data. However, they face challenges due to imbalanced real-world data distributions of land cover and crop types, hindering scalability and transferability. This letter presents a novel data augmentation method employing Generative Adversarial Neural Networks (GANs) with pixel-to-pixel transformation (pix2pix). This approach generates realistic synthetic satellite images with artificial ground truth masks, even for rare crop class distributions. It enables the creation of additional minority class samples, enhancing control over training data balance and outperforming traditional augmentation methods. Implementing this method improved the overall map accuracy (OA) and intersection over union (IoU) by 1.5% and 2.1%, while average crop type classes’ user accuracy (UA) and producer accuracies (PA), as well as IoU, were improved by 11.2%, 6.4% and 10.2%.Документ Відкритий доступ iMERMAID Project: Integrating Satellite and In-Situ Data for Water Pollution Identification in the Mediterranean Basin(2025 Living Planet Symposium, 2025-06) Shelestov, Andrii; Drozd, Sofiia; Yailymov, Bogdan; Henitsoi, Pavlo; Donate, J.; Milián, M.; Rostan, J.; Sedano, R.Monitoring and improving water quality in the Mediterranean Sea is critical for preserving its unique biodiversity and addressing environmental challenges caused by anthropogenic activities. The Mediterranean Sea serves as a hotspot of ecological and economic importance, yet it faces significant threats from chemical pollution and overexploitation. As part of the Horizon Europe iMERMAID project, “Innovative Solutions for Mediterranean Ecosystem Remediation via Monitoring and Decontamination from Chemical Pollution”, our research focuses on advancing satellite-based methodologies to monitor key water quality indicators, specifically chlorophyll-a concentration and water turbidity. These indicators are vital for assessing biological productivity, phytoplankton dynamics, and water clarity, providing insights into the health of marine ecosystems. Traditional methods of measuring chlorophyll-a and water turbidity rely on costly and time-intensive laboratory analyses, which are limited in spatial and temporal scope. In contrast, satellite remote sensing offers an efficient and scalable solution for monitoring large and diverse marine areas. Leveraging satellite data from Sentinel-2, Sentinel-3, MODIS, and GCOM-C missions, the iMERMAID project develops integrated methodologies that combine spectral band analysis, in-situ measurements, and advanced machine learning models. Our research prioritizes improving the spatial and temporal resolution of chlorophyll-a and turbidity data to facilitate effective environmental management and pollution remediation strategies. A key innovation in our approach is the use of machine learning models, including Random Forest (RF) and multilayer perceptron (MLP), to analyze the non-linear relationships between spectral satellite data and in-situ chlorophyll-a measurements [1]. For example, regression models applied to GCOM-C and Aqua MODIS data achieved significant accuracy improvements, with RF models yielding an R² of 0.603 (RMSE = 0.008) for GCOM-C and R² of 0.74 (RMSE = 0.006) for Aqua MODIS. By downscaling coarse-resolution data (e.g., MODIS and GCOM-C) and upscaling Sentinel-3 data, we enhanced spatial resolution from 4 km to 300 m, making these models particularly effective for coastal regions where traditional methods often fail due to complex environmental conditions [2-4]. The integration of in-situ measurements allows us to validate and refine model predictions, ensuring consistency and accuracy in highly dynamic environments like the Mediterranean Sea. In addition to chlorophyll-a monitoring, the project addresses water turbidity by quantifying suspended particulate matter using satellite-derived spectral data. This parameter is critical for identifying sediment transport, pollution hotspots, and other ecological disturbances. By combining data-driven insights with high-resolution mapping capabilities, our methodologies enable timely detection of pollution and provide actionable information for marine ecosystem remediation. A crucial component of the project is the integration of maritime traffic density data to establish potential correlations between anthropogenic activity and water pollution. Using data from the EMODnet Map Viewer, historical navigation patterns in the Mediterranean Sea were analyzed, focusing on regions of high, medium, and low traffic densities. Areas of interest include regions with significant maritime activity, such as the southern Italian coast, the Balearic Islands, and northern Libya, alongside relatively lower-traffic zones like eastern Crete. This approach identifies pollution risks linked to shipping routes, oil spills, and port activities, complementing water quality assessments. Findings reveal a significant correlation between high maritime traffic areas, such as near Malta, and increased occurrences of oil spills, underscoring the role of vessel density in environmental contamination. Additionally, PRISMA images were utilized to explore potential links between satellite images and potential pollutants, such as water turbidity, to evaluate the utility of hyperspectral data for monitoring water quality indicators in the Mediterranean basin [5]. The results of the iMERMAID project demonstrate the potential of advanced remote sensing and data analytics to transform water quality monitoring in marine ecosystems. The integration of multiple data sources and machine learning techniques not only enhances monitoring accuracy but also supports sustainable management strategies. These methodologies are applicable to a wide range of use cases, including early warning systems for pollution, biodiversity conservation, and sustainable fisheries management. Acknowledgment This research was carried out within the Horizon Europe iMERMAID project “Innovative Solutions for Mediterranean Ecosystem Remediation via Monitoring and Decontamination from Chemical Pollution” (Grant agreement 101112824). References 1. P. Henitsoi, A. Shelestov, Transfer Learning Model for Chlorophyll-a Estimation Using Satellite Imagery, International Symposium on Applied Geoinformatics 2024 (ISAG2024), Wroclaw, Poland, 2024, p. 54. https://www.kongresistemi.com/panel/UserUploads/Files/ a3fe58047d50fbc.pdf. 2. B. Yailymov, N. Kussul, P. Henitsoi, A. Shelestov, Improving spatial resolution of chlorophyll-a in the Mediterranean Sea based on machine learning, Radioelectronic and Computer Systems 2024 (2024) 52–65. https://doi.org/10.32620/reks.2024.2.05. 3. H. Wu, W. Li, Downscaling land surface temperatures using a random forest regression model with multitype predictor variables, IEEE Access 7 (2019) 21904-21916. https://doi.org/10.1109/ACCESS.2019.2896241. 4. J. Peng, A. Loew, O. Merlin, N.E. Verhoest, A review of spatial downscaling of satellite remotely sensed soil moisture, Reviews of Geophysics 55 (2017) 341-366. https://doi.org/10.1002/2016RG000543 5. Amieva, Juan Francisco, Daniele Oxoli, and Maria Antonia Brovelli. "Machine and Deep Learning Regression of Chlorophyll-a Concentrations in Lakes Using PRISMA Satellite Hyperspectral Imagery." Remote Sensing 15.22 (2023): 5385. https://www.mdpi.com/2072-4292/15/22/5385Документ Відкритий доступ Solar energy potential mapping in Ukraine through integration of GIS, remote sensing, and fuzzy logic(Associazione Italiana di Telerilevamento (AIT), 2024) Drozd, Sofiia; Kussul, NataliiaThe Green Deal strategic plan for the development of renewable energy until 2030 is ofparticular importance in the context of the restoration of Ukraine’s post-war energy infrastruc-ture. One of the key topics is the analysis of the possibilities of installing large solar powerplants in Ukraine. In this article, a multi-criteria analysis of the suitability of the territory ofUkraine is carried out on the basis of climatic, topographic and land use criteria. To assess landsuitability, criteria standardized using fuzzy logic with weights determined by experts throughthe method of pairwise comparisons were combined using a weighted sum model. Uponcompleting the study, a suitability map was generated, depicting zones with varying levels ofsuitability (ranging from 0 to 1) for solar power plant placement. It was found that more than35.68% of the country has average values of the suitability index (0.65–0.7), and approximately18.82% show high indicators (<0.7). Conditions are especially favorable in the south of Ukraine.