4 papers
ChaosNetBench: Benchmarking Spatio-Temporal Graph Neural Networks on Chaotic Lattice Dynamics
Henok Tenaw Moges, Charalampos Skokos, Deshendran Moodley
Spatio-temporal graph neural networks (STGNNs) are widely used for short-term forecasting in dynamic physical systems such as traffic and weather. However, the prevailing evaluatio…
A lightweight Spatial-Temporal Graph Neural Network for Long-term Time Series Forecasting
Henok Tenaw Moges, Deshendran Moodley
We propose Lite-STGNN, a lightweight spatial-temporal graph neural network for long-term multivariate forecasting that integrates decomposition-based temporal modeling with learnab…
Hamiltonian Chaos: From Galactic Dynamics to Plasma Physics
Henok Tenaw Moges
The primary focus of this thesis is the numerical investigation of chaos in Hamiltonian models describing charged particle orbits in plasma, star motions in barred galaxies, and or…
On the behavior of the Generalized Alignment Index (GALI) method for dissipative systems
Henok Tenaw Moges, Thanos Manos, Ovidiu Racoveanu +1
The behavior of the Generalized Alignment Index (GALI) method has been extensively studied and successfully applied for the detection of chaotic motion in conservative Hamiltonian…