Georgi Marko Dimirovski

Flood prediction remains a critical challenge in environmental risk management and disaster preparedness. Accurate river-level forecasting is essential for the development of reliable early warning systems and the mitigation of flood-related risks. However, conventional ensemble approaches, such as averaging and majority voting, often exhibit limited adaptability when individual models respond differently to anomalies or incomplete data. To address this limitation, this study proposes a graph-based synchronization framework that integrates XGBoost and Random Forest models using a Graph Convolutional Network (GCN). The proposed framework represents the outputs of the base prediction models as graph nodes and employs graph message passing to learn context-dependent relationships between their predictions. The framework is evaluated using real-world hydrological observations from the Lepenec River Basin in North Macedonia together with meteorological data obtained from the OpenWeatherMap API. Experimental results demonstrate that the proposed GCN-based synchronization framework outperforms both the standalone prediction models and the previously proposed linear synchronization method, achieving an R² value of 0.91 and a Mean Absolute Error (MAE) of 0.21. The obtained results indicate that graph-based synchronization provides an adaptive approach for integrating heterogeneous machine-learning models and has the potential to support future flood early-warning systems and intelligent environmental monitoring applications.

This research delves into the passivity-based pinning synchronization problem for switched directed networks (SDNs) within the context of a sampled-data-based event-triggered (SDET) communication environment. An improved state-dependent switching strategy (SDSS) using sampled measurements alongside a novel time-dependent Lyapunov-Krasovskii functional (LKF) approach is constructed. Subsequently, a relaxed passivity analysis framework is then presented, ensuring that the resultant synchronization error system (SES) remains passive, and that the examined SDNs achieve asymptotic synchronization in the absence of external inputs. Unlike conventional strategies, the proposed switching protocol depends exclusively on system states at discrete sampling instants and effectively utilizes historical state data, yielding a less conservative theoretical framework for passivity synthesis in SDNs. Furthermore, the resulting synchronization criterion is independent of the number of network nodes, rendering it suitable for SDNs with large size. Ultimately, two examples involving relevant application in image encryption and decryption are provided to verify the effectiveness and applicability of the proposed scheme, and highlight the distinct advantage of switching behaviors in enhancing encryption confidentiality.