fluid dynamics
PulseAugur coverage of fluid dynamics — every cluster mentioning fluid dynamics across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New AI models enhance PDE simulations with variable initial conditions
Researchers have developed new methods for improving the accuracy and efficiency of surrogate models used to simulate physical systems governed by partial differential equations (PDEs). One approach, Latent Dynamics Net…
-
New AI Framework Creates High-Fidelity Digital Twin Data Models
This paper introduces a novel framework for creating digital twin data models (DTMs) by integrating randomized dynamic mode decomposition with deep learning. The proposed method aims to generate simplified models that a…
-
New variational method enhances long-horizon PDE prediction stability
Researchers have developed a new variational approach to improve the long-horizon prediction capabilities of neural partial differential equation (PDE) solvers. This method introduces latent Markov dynamics, where physi…
-
Physics-Informed Neural Networks applied to aortic aneurysm study
Researchers have developed a novel three-dimensional Physics-Informed Neural Network (PINN) framework to study blood flow dynamics within the human aorta. This model simulates pulsatile blood flow over a two-minute peri…
-
New diffusion model guidance improves physical accuracy in simulations
Researchers have developed a novel physics-informed approach for diffusion models to generate more accurate spatiotemporal signals in fields like fluid dynamics. This method, termed Self-Augmented Diffusion Guidance, in…
-
New method ranks neural operator models without ground truth data
Researchers have developed a novel method to efficiently select the best neural operator model for deployment without needing high-fidelity reference solutions. By analyzing the low-dimensional span of candidate differe…
-
PhyxMamba framework reconstructs chaotic systems from limited data
Researchers have introduced PhyxMamba, a novel framework designed to reconstruct chaotic dynamical systems from limited observational data. This approach combines Mamba-based state-space models with physics-informed pri…
-
Eikonal Regularisation in PINNs for 3D Fluid Dynamics Explored
A new research paper explores the effectiveness of Eikonal Regularisation in physics-informed neural networks (PINNs) for simulating three-dimensional fluid dynamics. The study, authored by Muhammad Akbar Khan, investig…
-
Quantum-Classical Framework Boosts PINN Accuracy for Complex Equations
Researchers have developed a hybrid quantum-classical framework to improve the accuracy and efficiency of Quantum Physics-Informed Neural Networks (QPINNs) for solving complex differential equations. This new approach i…
-
New hybrid method enhances neural operators for complex multiscale problems
Researchers have developed LOD-MSNO, a novel hybrid approach that combines the LOD method with neural operators to address challenges in solving multiscale problems. This method aims to improve the accuracy of neural op…
-
HydroGym platform standardizes RL for fluid dynamics control
Researchers have introduced HydroGym, a new reinforcement learning platform designed to standardize and accelerate research in fluid dynamics control. This platform offers over 60 validated environments across various f…
-
Author links fluid dynamics, spacetime, and economics
Brandon Bedard's Substack series explores the intersection of fluid dynamics and spacetime, drawing parallels between astrophysical phenomena and economic principles. The author posits that understanding these fluidic p…