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.
- developed by HSPINN 95%
- instance of HSPINN 95%
- instance of Physics-Informed Neural Network 95%
- developed Gotit.pub 90%
- instance of Gotit.pub 90%
- instance of ScienceCast 90%
- used by Navier–Stokes equations 90%
- developed HSPINN 90%
- used by partial differential equation 90%
- instance of convection 90%
- used by HSPINN 90%
- competes with Neural Operators 80%
14 day(s) with sentiment data
-
Twindex offers exact proofs for model parameter indistinguishability
Twindex is a new tool that provides exact, replayable proofs to demonstrate when different parameter sets for a model are indistinguishable based on given data. It generates a JSON certificate and a checker that verifie…
-
New AI method enhances domain decomposition for physics-informed neural networks
Researchers have introduced Adaptive Domain Decomposition Finite Basis Physics-Informed Neural Networks (ADD-FBPINNs), a novel method that combines Partition of Unity Networks (POUNets) with finite Basis Physics-Informe…
-
Physics-Informed Neural Networks Solve Nonlinear Westervelt Equation
Researchers have developed a novel approach using Physics-Informed Neural Networks (PINNs) to solve the nonlinear Westervelt equation, which models acoustic wave propagation in biological tissues. This method addresses …
-
New evaluation protocol and embedding method for Physics-Informed Neural Networks
Researchers have introduced PINNeval, a new evaluation protocol and accompanying JAX package called PINNpipe, designed to systematically assess Physics-Informed Neural Networks (PINNs). This protocol addresses limitatio…
-
New weighted loss function enhances PINN accuracy for BGK model
Researchers have developed a new approach to improve the accuracy of Physics-Informed Neural Networks (PINNs) when solving the Bhatnagar-Gross-Krook (BGK) model. The standard $L^2$ loss function in PINNs is insufficient…
-
New theory guarantees stability and consistency for physics-informed neural networks
A research paper published on arXiv, titled "Non-Asymptotic Stability and Consistency Guarantees for Physics-Informed Neural Networks via Coercive Operator Analysis," introduces a theoretical framework for analyzing the…
-
New HCP-PINN method improves fluid dynamics simulation accuracy
Researchers have developed a novel Hard Constraint Projection (HCP) method for physics-informed neural networks (PINNs) to better simulate fluid dynamics. This new approach extends the HCP method to nonlinear partial di…
-
New hybrid AI framework boosts accuracy for solving complex differential equations
Researchers have developed a new hybrid framework that combines Physics-Informed Neural Networks (PINNs) with boosting methods to solve complex differential equations. This approach enhances the accuracy of standard PIN…
-
PINNs offer new approach to semiconductor device modeling
Researchers have developed a novel approach using Physics Informed Neural Networks (PINNs) to solve complex drift-diffusion equations, which are fundamental to semiconductor device modeling. This method offers a powerfu…
-
New PINN method significantly boosts PDE solution accuracy
A new research paper introduces a novel method for improving the accuracy of physics-informed neural networks (PINNs) when solving complex partial differential equations (PDEs). The proposed technique, called Residual-B…
-
AI research papers propose new methods for evaluation and gradient optimization
Two new research papers explore methods for optimizing the evaluation process in AI development. The first paper, "Where Should the Evaluation Budget Go in LLM-Driven Agent Scaffold Evolution?", proposes a framework cal…
-
New PINN model learns hybrid systems with discrete jumps
Researchers have developed Hybrid-time PINNs (HT-PINNs), a novel approach to modeling hybrid dynamical systems that exhibit both continuous flow and discrete jumps. Unlike traditional PINNs that struggle with discontinu…
-
New RE-PINN method enhances uncertainty estimates in physics-informed neural networks
Researchers have developed a new method called Repulsive Ensembles for Bayesian Inference in Physics-informed Neural Networks (RE-PINN) to improve uncertainty quantification in physics-informed neural networks (PINNs). …
-
Physics-informed neural networks reveal tidal creek groundwater exchange dynamics
Researchers have utilized sediment temperature monitoring combined with physics-informed neural networks (PINNs) to investigate groundwater-surface water exchange in a tidal creek system. Their study in Texel, Netherlan…
-
New GeoDiv KAN architecture advances fluid dynamics simulations
Researchers have developed a new machine learning architecture called GeoDiv KAN to solve complex fluid dynamics problems. This model, which incorporates geometry-dependent feature gating and a streamfunction formulatio…
-
Physics-AI hybrid models enhance forecasting with nonlinear flow insights
A new review explores the integration of physics-informed neural networks with AI for enhanced forecasting. The research emphasizes how nonlinear flow mechanisms, including stress sensitivity and threshold pressure grad…
-
New AI model HypoNet Nankai PS improves earthquake hypocenter determination
Researchers have developed HypoNet Nankai PS, an advancement of their previous HypoNet Nankai system, to more accurately and rapidly determine earthquake hypocenters. This new version incorporates both P- and S-wave tra…
-
PINNs can fail to learn correct Hamilton-Jacobi solutions
A new research paper explores the limitations of physics-informed neural networks (PINNs) when solving Hamilton-Jacobi-Isaacs equations. The study found that PINNs, which typically judge solutions by the size of their s…
-
New MINN method infers electrolytes from ECGs with low-label data
Researchers have developed a novel Manifold-Informed Neural Network (MINN) that can infer electrolyte levels from electrocardiogram (ECG) data, even with limited labeled samples. Unlike traditional physics-informed neur…
-
PaPi integration scheme accelerates physics-informed neural networks
Researchers have developed PaPi, a novel integration scheme for neuro-spectral architectures (NeuSA) that significantly speeds up the training and inference of physics-informed neural networks (PINNs). Unlike traditiona…