Перегляд за Автор "Malyniak, Volodymyr"

Зараз показуємо 1 - 2 з 2
  • Ескіз
    ДокументВідкритий 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, Charlotte
    Rapid 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.
  • Ескіз
    ДокументВідкритий 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, Charlotte
    This 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.