partial differential equations
PulseAugur coverage of partial differential equations — every cluster mentioning partial differential equations across labs, papers, and developer communities, ranked by signal.
- instance of partial differential equation 95%
- instance of alphaXiv 90%
- instance of Allen–Cahn equation 90%
- used by Neural Operators 70%
- instance of Neural Operators 70%
- used by ScienceCast 70%
- used by Gotit.pub 70%
- uses Neural Operators 70%
- used by alphaXiv 70%
- instance of Influence Flower 70%
- instance of Gotit.pub 70%
- instance of Fourier Neural Operators 70%
9 day(s) with sentiment data
-
New DPG loss functions enhance neural network accuracy for PDEs
Researchers have developed new residual-based loss functions for machine learning models that aim to accurately predict solutions for parameter-dependent partial differential equations (PDEs). These functions, particula…
-
New GA-AMNO method improves PDE neural operators with adaptive computation and interaction
Researchers have introduced the Gauge-Aware Adaptive Mesh Neural Operator (GA-AMNO), a novel approach to enhance neural operators for partial differential equations (PDEs). This method addresses not only where computati…
-
New method improves training of physics-informed neural networks
Researchers have developed Norm-PCGrad, a novel method to improve the training of physics-informed neural networks (PINNs) and physics-informed Kolmogorov-Arnold Networks (PIKANs) when using domain decomposition. This t…
-
New research tackles PINN limitations for solving PDEs · 4 sources tracked
Recent research explores advancements in physics-informed neural networks (PINNs) for solving partial differential equations (PDEs). One paper introduces a physics-informed random feature method to address spectral bias…
-
New PI-CP method enhances uncertainty quantification for neural operators
Researchers have developed a new method called Physics-Informed Conformal Prediction (PI-CP) to provide reliable uncertainty estimates for neural operators used in approximating solutions to partial differential equatio…
-
Neural networks infer unknown functions in PDEs from data
Researchers have developed a novel method to infer unknown functional components within partial differential equations (PDEs) using neural networks. This approach embeds neural networks directly into the PDE framework, …
-
New framework uses neural networks to simplify boundary conditions in PDEs
Researchers have developed a framework for learning when a simplified boundary condition can replace a more complex one in parametric partial differential equations. This method uses paired solutions to train a neural n…
-
Research compares automatic differentiation and discretization for AI-powered PDE solvers
A new research paper systematically analyzes the trade-offs between automatic differentiation (AD) and discretization-based constraints for physics-informed neural networks (PINNs) used in solving partial differential e…
-
PINNs enhanced with wave physics improve seismic analysis accuracy
Researchers have critically assessed the application of Physics-Informed Neural Networks (PINNs) for solving the elastic wave equation, a crucial task in seismology. Their findings indicate that while PINNs offer a prom…
-
Latent-MoE architecture enhances physics-informed neural networks for complex PDEs
Researchers have developed Latent-MoE, a novel domain-aware Mixture-of-Experts architecture designed to improve the performance of physics-informed neural networks (PINNs) on partial differential equations (PDEs) with c…
-
New Local Gradient Neural Operator offers interpretable AI for dynamical systems
Researchers have introduced the Local Gradient Neural Operator (LGNO), a novel deep learning approach for predicting field temporal evolution and identifying sources in dynamical systems. Unlike existing neural operator…
-
New infinite-dimensional normalizing flow model for Bayesian inverse problems
Researchers have developed a novel infinite-dimensional continuous normalizing flow model to address Bayesian inference for inverse problems involving partial differential equations. This model utilizes a neural ordinar…
-
New active learning framework enhances ROMs with Bayesian operator inference
Researchers have developed a new active learning framework designed to improve data-driven reduced-order models (ROMs) for parametric dynamical systems. This framework uses Bayesian operator inference, framed as Bayesia…
-
New GeoLAMP model tackles complex partial differential equations
Researchers have developed GeoLAMP, a novel geometry-aware latent autoregressive generative model designed to solve complex partial differential equations (PDEs). This model utilizes a dual-encoder architecture on graph…
-
New Graph Spectral Neural Operator Learns PDEs on Irregular Domains
Researchers have developed a new Graph Spectral Neural Operator (GSNO) designed to learn solutions for partial differential equations (PDEs) on irregular domains. This method combines spatial graph spectral decompositio…
-
New framework learns PDE geometry using inductive bias
Researchers have developed a new framework for learning continuous latent representations of partial differential equations (PDEs). This approach embeds scientific inductive bias directly into the training distribution,…
-
Deflation-PINNs framework identifies multiple PDE solutions using neural networks
Researchers have developed Deflation-PINNs, a novel framework that integrates physics-informed neural networks (PINNs) with Deep Operator Networks (DeepONets) to address the challenge of identifying multiple solutions f…
-
PINNs struggle with noisy data compared to traditional methods, study finds
A new research paper investigates the effectiveness of Physics-Informed Neural Networks (PINNs) when dealing with noisy data in inverse problems. The study found that while PINNs may require less specialized knowledge, …
-
Quantum SEDONet advances neural operator networks for PDEs
Researchers have developed Quantum SEDONet, an advancement in quantum deep operator networks designed to solve partial differential equations. This new model embeds spectral bases, such as Fourier or Chebyshev features,…
-
New Frame Kernel Method Advances Multiscale Operator Learning
Researchers have introduced the Frame Kernel Method, a novel approach to multiscale operator learning designed for modeling complex partial differential equations (PDEs). This method utilizes a unique multiscale kernel …