partial differential equation
PulseAugur coverage of partial differential equation — every cluster mentioning partial differential equation across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
NEST framework learns local physics for geometry-universal PDE solving
Researchers have developed a new framework called NEST (Neural-Schwarz Tiling) for solving partial differential equations (PDEs) across various geometries and scales. Unlike previous methods that trained global operator…
-
New hybrid neural integrator improves accuracy for nonlinear dispersive equations
Researchers have developed HIN-LRI, a novel hybrid framework that combines classical numerical solvers with neural operators to improve the accuracy of solving nonlinear dispersive partial differential equations (PDEs).…
-
AI model discovers nonlinear dye plume dynamics from video data
Researchers have developed a novel pipeline to derive continuum models from video data, overcoming challenges of uncalibrated intensity readings and noisy frame differentiation. This method converts grayscale plume reco…
-
PerFlow model speeds up spatiotemporal dynamics reconstruction with physics embedding
Researchers have introduced PerFlow, a novel method for reconstructing spatiotemporal dynamics governed by partial differential equations (PDEs) from sparse data. This physics-embedded rectified flow model decouples obs…
-
New VMLFN method accelerates multiphysics simulations with neural networks
Researchers have developed a new method called Variational Matrix-Learning Fourier Networks (VMLFN) to create efficient surrogate models for multiphysics simulations. This approach uses a sine neural representation and …
-
PILIR model overcomes spectral bias for improved PDE solving accuracy
Researchers have introduced PILIR, a novel approach to Physics-Informed Neural Networks designed to overcome spectral bias limitations. PILIR separates the physical domain into a discrete latent feature space and a cont…
-
AI solves complex inverse partial differential equations, a major math challenge
Researchers have employed artificial intelligence to solve a challenging class of mathematical problems known as inverse partial differential equations (PDEs). This AI-driven approach offers a novel method for finding s…
-
New Dirac-Frenkel-Onsager principle enhances PDE solution parametrization
Researchers have introduced a new principle for minimizing residuals in nonlinear parametrizations of partial differential equation (PDE) solutions. This Dirac-Frenkel-Onsager principle addresses ill-conditioning by int…
-
New PDE models enhance image despeckling while preserving details
Researchers have developed two new partial differential equation (PDE) based frameworks to improve image despeckling, a process that reduces noise while preserving details. One framework uses a weighted combination of s…
-
New grey-box method integrates physics models into generative AI
Researchers have developed a novel grey-box method that integrates incomplete physics models into generative AI models, specifically flow matching and diffusion models. This approach learns dynamics from observational d…
-
LatentPDE framework reconstructs sparse scientific data using interpretable PDE representations
Researchers have developed LatentPDE, a new framework that uses latent diffusion models to improve scientific data reconstruction. This model addresses challenges like noise, incomplete data, and low resolution by creat…