physics-informed neural networks
PulseAugur coverage of physics-informed neural networks — every cluster mentioning physics-informed neural networks across labs, papers, and developer communities, ranked by signal.
8 天有情绪数据
-
PINNs improve climate modeling by integrating physics with neural networks
Researchers have developed a coupled physics-informed neural network (PINN) approach to reconstruct and identify parameters in greenhouse climate dynamics. This method integrates physical laws into neural network traini…
-
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…
-
New theories explore how pre-training and sparse connectivity enhance deep learning generalization
Three new papers explore the theoretical underpinnings of generalization in deep learning. One paper identifies pre-training as a critical factor for weak-to-strong generalization, demonstrating its emergence through a …
-
LAM-PINN framework uses compositional meta-learning for physics-informed neural networks
Researchers have developed a new framework called LAM-PINN to improve the training efficiency and generalization of physics-informed neural networks (PINNs). This compositional approach addresses the challenge of task h…
-
An adaptive wavelet-based PINN for problems with localized high-magnitude source
Researchers have developed an adaptive wavelet-based physics-informed neural network (AW-PINN) to address limitations in solving differential equations, particularly those with localized high-magnitude source terms. Thi…
-
Physics-Informed Neural Networks compared to numerical methods for nanobeam analysis
Researchers have developed a novel Physics-Informed Functional Link Constrained Framework with Domain Mapping (DFL-TFC) to analyze the bending behavior of perforated nanobeams. This method embeds governing differential …
-
Physics-informed neural networks offer unified approach for change-point detection
Researchers have developed a new method for analyzing nonlinear dynamical systems that exhibit regime switching. This approach utilizes physics-informed neural networks to jointly estimate piecewise parameters and ident…
-
AI models predict offshore wind turbine wakes with high fidelity
Researchers have developed a new method for modeling the dynamic wakes of floating offshore wind turbines using Fourier Neural Operators (FNOs) and Physics-Informed Neural Networks (PINNs). The study found that FNOs wer…
-
PINNs face spurious solutions; adaptive pseudo-time stepping offers a fix
Researchers have identified a critical flaw in Physics-Informed Neural Networks (PINNs) where they can converge to incorrect solutions despite low residual losses. The study proposes a new adaptive pseudo-time stepping …
-
Physics-informed neural networks simulate pollution spread under thermal inversion
Researchers have developed a robust Physics-Informed Neural Network (PINN) framework to simulate time-dependent pollution propagation, particularly under thermal inversion conditions. This new framework incorporates a r…
-
PINNs leverage differential geometry for AI loss minimization in new research
A new paper explores the application of Physics-Informed Neural Networks (PINNs) to problems in differential geometry. The research proposes that by framing geometric constructions as the minimization of differential fu…
-
New Pi-PINN framework enhances physics-informed neural network generalization
Researchers have developed a new framework called Pi-PINN to improve the generalization capabilities of physics-informed neural networks (PINNs). This approach learns transferable physics-informed representations, allow…
-
New neural solver uses Green-Integral method for efficient Helmholtz equation simulation
Researchers have developed a novel Green-Integral (GI) neural solver designed to more efficiently simulate the acoustic Helmholtz equation, particularly in complex heterogeneous media. This new method departs from tradi…
-
AI methods tackle complex nonlinear PDEs with sparse identification
Researchers have developed a novel framework using sparse radial basis function networks to solve nonlinear partial differential equations (PDEs). This approach incorporates sparsity-promoting regularization to manage o…