Physics-constrained coupled neural differential equations for one dimensional blood flow modeling
Background: Computational cardiovascular flow modeling plays a crucial role in
understanding blood flow dynamics. While 3D models provide acute details, they are …
understanding blood flow dynamics. While 3D models provide acute details, they are …
Data-driven prediction of large-scale spatiotemporal chaos with distributed low-dimensional models
CR Constante-Amores, AJ Linot… - arXiv preprint arXiv …, 2024 - arxiv.org
Complex chaotic dynamics, seen in natural and industrial systems like turbulent flows and
weather patterns, often span vast spatial domains with interactions across scales. Accurately …
weather patterns, often span vast spatial domains with interactions across scales. Accurately …
Improved deep learning of chaotic dynamical systems with multistep penalty losses
Predicting the long-term behavior of chaotic systems remains a formidable challenge due to
their extreme sensitivity to initial conditions and the inherent limitations of traditional data …
their extreme sensitivity to initial conditions and the inherent limitations of traditional data …
Invariant Measures in Time-Delay Coordinates for Unique Dynamical System Identification
Invariant measures are widely used to compare chaotic dynamical systems, as they offer
robustness to noisy data, uncertain initial conditions, and irregular sampling. However, large …
robustness to noisy data, uncertain initial conditions, and irregular sampling. However, large …
[PDF][PDF] Differentiable Turbulence: Closure as a PDE-constrained optimization
Deep learning is emerging as a powerful tool for enhancing sub-grid scale (SGS) turbulence
models used in large eddy simulations (LES). By employing a differentiable turbulence …
models used in large eddy simulations (LES). By employing a differentiable turbulence …