Assessment of war-induced agricultural land use changes in Ukraine using machine learning applied to Sentinel satellite data

Скорочена інформація про документ
dc.contributor.authorNataliia Kussul
dc.contributor.authorAndrii Shelestov
dc.contributor.authorBohdan Yailymov
dc.contributor.authorHanna Yailymova
dc.contributor.authorGuido Lemoine
dc.contributor.authorKlaus Deininger
dc.date.accessioned2025-05-26T09:24:54Z
dc.date.available2025-05-26T09:24:54Z
dc.date.issued2025-05-08
dc.description.abstractThe ongoing war in Ukraine has significantly disrupted agricultural land use, leading to reduced cropland areas, increased land abandonment, and heightened uncertainty in food production. This study presents a multi-year assessment of war-induced agricultural land use changes in Ukraine using machine learning-based classification applied to Sentinel-1 and Sentinel-2 satellite imagery. By leveraging cloud computing platforms, including Google Earth Engine (GEE) and the Copernicus Data Space Ecosystem (CDSE), we develop high-resolution KPI-Ukraine (Igor Sikorsky Kyiv Polytechnic Institute (KPI) in Ukraine) land use maps spanning from 2016 to 2024. The study integrates Random Forest and Multi-Layer Perceptron classification techniques to improve accuracy, addressing spectral ambiguities and classification noise. Additionally, a novel transfer learning approach enables reliable classification in conflict-affected areas with limited ground-truth data. We achieved high classification accuracy across the 14 major crop types in Ukraine and abandoned land, validated through F1-scores exceeding 90% for most classes. The fusion of the results generated on the GEE and CDSE platforms enhanced the classification accuracy for minor classes. Our analysis reveals significant reductions in cultivated land in 2022-2024, particularly in conflict zones, where agricultural activity has been heavily disrupted. Overall, Ukraine’s arable land area shrunk by 10% nationwide. The consistently high accuracy of our classification methodology across the nine-year study period demonstrates its robustness and suitability for long-term monitoring of agricultural dynamics in conflict-affected regions and provides a valuable tool for guiding post-war recovery efforts. Our findings underscore the importance of leveraging satellite data for timely and accurate land use monitoring, supporting policymakers in addressing food security challenges and promoting sustainable agricultural practices. This framework also holds potential for broader applications in monitoring land use changes in conflict zones and regions undergoing rapid environmental shifts.
dc.description.sponsorshipThis work was supported by the European Commission through the joint World Bank/EU project ‘Supporting Transparent Land Governance in Ukraine’ [grant numbers ENI/2017/387–093 and ENI/2020/418–654], expert contracts EC Joint Research Center (JRC) [CT-EX2022D670387-101, CT-EX2022D670387-102], National research foundation of Ukraine project "Geospatial monitoring system for the war impact on the agriculture of Ukraine based on satellite data" [grant number 2023.04/0039] (impact of war on agricultural land cultivation), “DT4LC: Developing Scalable Digital Twin Models for Land Cover Change Detection Using Machine Learning” [grant number 2023.01/0040] (impact of war on land use change), Ministry of Education and Science of Ukraine “Information technologies of geospatial analysis of the development of rural areas and communities” [grant number PH/27-2023].
dc.format.extent24 p.
dc.format.pagerangeP. 1-24
dc.identifier.citationAssessment of war-induced agricultural land use changes in Ukraine using machine learning applied to Sentinel satellite data / Nataliia Kussul, Andrii Shelestov, Bohdan Yailymov, Hanna Yailymova, Guido Lemoine, Klaus Deininger // International Journal of Applied Earth Observation and Geoinformation. - Volume 140. - June 2025. - 104551.
dc.identifier.doihttps://doi.org/10.1016/j.jag.2025.104551
dc.identifier.urihttps://ela.kpi.ua/handle/123456789/73926
dc.language.isoen
dc.publisherElsevier BV
dc.relation.ispartofInternational Journal of Applied Earth Observation and Geoinformation, Volume 140, June 2025
dc.subjectAgricultural land use change
dc.subjectWar impact
dc.subjectCropland
dc.subjectUncultivated lands
dc.subjectUkraine
dc.subjectGoogle Earth Engine
dc.subjectCopernicus Data Space Ecosystem
dc.subjectSentinels
dc.subjectMachine learning
dc.titleAssessment of war-induced agricultural land use changes in Ukraine using machine learning applied to Sentinel satellite data
dc.typeArticle

Файли

Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
1-s2.0-S1569843225001980-main.pdf
Розмір:
27.25 MB
Формат:
Adobe Portable Document Format
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Ескіз недоступний
Назва:
license.txt
Розмір:
8.98 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити

Зібрання

Статті (ММАД)