Кафедра математичного моделювання та аналізу даних (ММАД)

Постійне посилання на фонд

https://ela.kpi.ua/handle/123456789/43446
Сайт кафедри: http://mmda.ipt.kpi.ua/

Переглянути

Перегляд Кафедра математичного моделювання та аналізу даних (ММАД) за Автор "Drozd, Sophia"

Зараз показуємо 1 - 5 з 5
  • Ескіз
    ДокументВідкритий доступ
    Agriculture land appraisal with use of remote sensing and infrastructure data
    (IEEE, 2022) Kussul, Nataliia; Shelestov, Andrii; Yailymova, Hanna; Shumilo, Leonid; Drozd, Sophia
  • Ескіз
    ДокументВідкритий доступ
    Crop Yield Forecasting for Major Crops in Ukraine
    (IEEE, 2021) Shelestov, Andrii; Shumilo, Leonid; Yailymova, Hanna; Drozd, Sophia
  • Ескіз
    ДокументВідкритий доступ
    Forecast of Yield of Major Crops in Ukraine in War Conditions 2022 based on MODIS and Sentinel-2 Satellite Data
    (2023) Kussul, Nataliia; Drozd, Sophia; Yailymova, Hanna
    Ukraine was one of the main exporters of plant products. However, as a result of the aggression, the country's agriculture has suffered greatly, export volumes are decreasing, which may provoke a shortage of agricultural products on world markets. It is impossible to assess crop yield and forecast the harvest volume locally, as the collection of information has become difficult due to the active conduct of hostilities and the occupation of a large part of the territories. Therefore, it is necessary to use land remote sensing data to assess crop yield. In this research, we will build regression models based on a random forest for each region of Ukraine to estimate crop yield based on 16-day composites of the NDVI time series during the summer vegetation period from Sentinel-2 (10m) and MODIS (500m) satellites, involving in the calculation NDVI crop maps. The official yield of maize, sunflower, soybean, rapeseed, and wheat for the years 2016-2021 was used as training data. According to the results of the analysis, models based on NDVI from the MODIS satellite showed better accuracy (relative error within 8-18%), but models based on NDVI data from Sentinel-2 better described the variance of the predicted yield. During the research, we found a sharp drop in land productivity indicators compared to the productivity of 2021 for the territories of central, southern and eastern Ukraine. According to our estimates based on MODIS data, the average yield at the country level is expected to be 40.98 t/ha for wheat, 57.66 t/ha for maize, 23.57 t/ha for sunflower, 21.06 t/ha for soybeans, 21.15 t/ha for rapeseed. Estimates based on Sentinel-2 data: 43.22 t/ha for wheat, 71.93 t/ha for maize, 26.86 t/ha for sunflower, 22.94 t/ha for soybeans, 28.23 t/ha for rapeseed.
  • Ескіз
    ДокументВідкритий доступ
    Validation of the Global Human Settlement Layer and NASA Population Data for Ukraine
    (IEEE, 2022) Kussul, Nataliia; Yailymova, Hanna; Drozd, Sophia; Shelestov, Andrii
  • Ескіз
    ДокументВідкритий доступ
    War Damage Detection Based on Satellite Data
    (2023) Shelestov, Andrii; Drozd, Sophia; Mikava, Polina; Barabash, Illia; Yailymova, Hanna
    As a result of the resolution of the armed military conflict on the territory of Ukraine on February 24, 2022, the agricultural infrastructure of the latter was marked by large-scale destruction. Thousands of hectares of fields, the harvest from which previously provided both domestic and world needs, were mined, destroyed, damaged by artillery shelling, explosions and movements of military equipment. To restore the affected areas to ensure food security of Ukraine and the world, the state government, with the support of international organizations, must correctly distribute financial resources between affected landowners and farmers. For this, there is a need for accurate identification of war-affected territories. This task can be effectively performed using remote sensing data. In this work, damage to agricultural fields due to military operations is searched for by calculating the relative difference of the vegetation indices based on Sentinel-2 satellite data. Cloud-free composites of normalized difference vegetation index (NDVI) are compared for the nearest period before and after active hostilities in a specific area (dates and locations are obtained from the ACLED source). Pixels whose relative difference exceeds a given threshold are considered damaged. The survey of the country's territories was conducted from February 24 to September 25, 2022, dividing the dates into biweekly periods. According to the results of the research, such damage to agricultural fields as craters from explosions and shelling, traces of machinery, burnt fields, etc., were found. The relative difference between the minimum and average values of vegetation indices in the affected areas averaged 25% versus 15% for the minimum period before and after the lesion. The detected damaged areas were validated using ACLED data. It was determined that more than 50% of the total number of areas identified as damaged were located within a radius of up to 5 km from the zone of combat activities.