Перегляд за Автор "Drozd, Sofiia"

Зараз показуємо 1 - 4 з 4
  • Ескіз
    ДокументВідкритий 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, Klaus
    The 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.
  • Ескіз
    ДокументВідкритий доступ
    Assessing Ukrainian Territory Suitability for Solar Power Station Placement Using Satellite Data on Climate and Topography
    (IEEE, 2023) Kussul, Nataliia; Drozd, Sofiia
    This 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.
  • Ескіз
    ДокументВідкритий 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, Inbal
    The 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.
  • Ескіз
    ДокументВідкритий 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, Oleh
    Deep 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%.