Кузьменко, ДмитроКузнецова, Анна2025-09-092025-09-092025https://ekmair.ukma.edu.ua/handle/123456789/36546This course paper focuses on the development of a machine learning model for classifying destroyed buildings based on the type of damage caused. It explores and compares different approaches to model creation and training, using real-life data of buildings in Ukraine that were damaged as a result of Russian military aggression. The study aims to contribute to effective damage estimation and planning for urban reconstruction in the context of the ongoing war in Ukraine.en-USImage ClassificationShellingConvolutional Neural NetworkDeep LearningComputer Visionterm paperOther