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.
- instance of HSPINN 95%
- instance of Physics-Informed Neural Network 95%
- developed by HSPINN 95%
- instance of alphaXiv 90%
- developed Gotit.pub 90%
- used by Navier–Stokes equations 90%
- used by HSPINN 90%
- instance of convection 90%
- used by partial differential equation 90%
- developed HSPINN 90%
- used by automatic differentiation 80%
- competes with Neural Operators 80%
14 day(s) with sentiment data
-
New PIRNN model leverages historical physical data for improved time series forecasting
Researchers have developed a Physics Informed Recurrent Neural Network (PIRNN) that improves time series forecasting by incorporating physical knowledge from historical data. Unlike previous Physics Informed Neural Netw…
-
Physics-informed neural networks accelerate solar spectral analysis
Researchers have developed a novel physics-informed neural network (PINN) framework to significantly accelerate multilayer spectral inversion (MLSI) for analyzing solar chromospheric spectral lines. This new method, MLS…
-
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 arXiv papers benchmark optimizers and debias PINNs for inverse problems
Two new arXiv papers explore solving inverse problems using differentiable physics simulators and physics-informed neural networks (PINNs). The first paper benchmarks various optimizers across 12 differentiable physics …
-
Physics-enriched neural networks accelerate glacier simulations
Researchers have developed a novel method to enhance neural network solvers for complex ice-flow simulations. By incorporating physics-derived inputs into the neural network, the new approach significantly improves robu…
-
Physics-Informed Neural Networks Infer Plasma Conductivity in Stellarators
Researchers have developed a novel framework using Physics-Informed Neural Networks (PINNs) to infer the perpendicular energy conductivity in the scrape-off layer of stellarator devices. This method combines plasma prof…
-
New PI-GNN offers improved stress localization modeling
Researchers have developed a novel variational physics-informed graph neural network (PI-GNN) designed to more accurately model stress localization in heterogeneous solids. Unlike traditional physics-informed neural net…
-
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…
-
Physics-Informed Neural Networks Model Granular Avalanches
Researchers have developed a physics-informed neural network (PINN) model to simulate granular avalanche dynamics on curved topography. This novel approach, based on the Savage-Hutter equations and Mohr-Coulomb theory, …
-
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 framework PhysSAE enhances interpretability of physics-informed neural networks
A new framework called PhysSAE has been developed for mechanistic interpretability of Physics-Informed Neural Networks (PINNs). This framework uses overcomplete sparse autoencoders to analyze the internal representation…
-
New Mamba-based model PPIM enhances 3D bioheat simulation accuracy
Researchers have developed a new physics-informed neural network model called PPIM, designed for simulating heat distribution in biological tissues. This model, based on the Pennes bioheat equation and incorporating a S…
-
New Bi-HYCO Framework Enhances PDE Parameter Identification with Fragmented Data
Researchers have introduced Bi-HYCO, a novel cooperative learning framework designed for identifying parameters in Partial Differential Equations (PDEs) when observations are fragmented. This method couples complementar…
-
PINNStudio launches as a free, no-code GUI for physics-informed neural networks
PINNStudio, a new open-source, no-code GUI, has been released to simplify the process of setting up, training, and visualizing physics-informed neural networks (PINNs). Developed to assist users with limited coding expe…
-
New PINN Architecture Models Strontium Titanate Memristor Dynamics
Researchers have developed a novel physics-informed neural network (PINN) architecture to model complex ion-electronic transport in strontium titanate memristive heterostructures. This cascaded PINN approach, combined w…
-
Fourier spectral differentiation offers significant speedup for physics-informed neural networks
A new research paper compares two methods for calculating spatial derivatives in physics-informed neural networks (PINNs): automatic differentiation (AD) and Fourier spectral differentiation. The study found that Fourie…
-
New GUM method tackles conflicting gradients in physics-informed neural networks
Researchers have identified a problem called Gradient-Update Mismatch (GUM) in training Physics-Informed Neural Networks (PINNs). GUM occurs when optimizers, even after gradient surgery methods attempt to resolve confli…
-
Physics-Informed Neural Networks enhance subsurface abnormality prediction
Researchers have developed a novel approach using Physics-Informed Neural Networks (PINNs) to predict the growth of subsurface abnormalities, drawing parallels to medical imaging for tumor prediction. The proposed deep …