Latest Articles for Physics Informed Neural Networks

New techniques improve precision in modeling multi-fluid flows for various industries.

A new method enhances training for neural networks solving partial differential equations.

New techniques improve parameter estimation in partial differential equations for various applications.

Combining physics and geometry for improved acoustic scattering predictions.

This article discusses advanced techniques for modeling fluid behavior in poroelastic materials.

New methods improve modeling of electromagnetic problems with interfaces using neural networks.

This article discusses the advantages of the Chebyshev Spectral Neural Network for solving differential equations.

Discover how machine learning is tackling complex partial differential equations.

New methods utilize neural networks to tackle complex time-fractional equations effectively.

A new approach combines machine learning and physics for more accurate predictions.

A new method enhances training efficiency for complex equations using variable scaling.

This article reviews numerical methods for elliptic PDEs, focusing on collocation and neural networks.

New methods enhance solving complex fractional partial differential equations.

Machine learning enhances quantum control techniques for improved technology applications.

SGM-PINN improves training efficiency for solving complex equations in engineering and physics.

A study on using neural networks for simulating material phase dynamics.

New method improves solving PDEs without global mesh.

New models blend physics and data for better landslide forecasts.

New neural network models improve predictions of wave behaviors.

Discover how physics-informed neural networks tackle partial differential-algebraic equations.

Exploring improved learning rates in neural networks for scientific computing.

New methods improve training and performance of Physics-Informed Kolmogorov-Arnold Networks.

A new method using neural networks improves modeling of complex electromagnetic fields.

A new approach to shape optimization using neural networks enhances performance and efficiency.

Explore neural networks, their structures, and practical applications in various fields.

Exploring necklace beams and how AI enhances their study.

This article discusses using tensor decomposition to improve PINNs for solving complex equations.

PINNs merge physics with data to solve complex scientific problems efficiently.

A new approach improves system performance by addressing uncertainties in design and control.

A novel approach using Galerkin-Boltzmann and neural networks to analyze fluid behavior.

Innovative method combines machine learning and physics for solving differential equations.

A new method enhances neural network performance for solving complex physics equations.

Physics-informed neural networks offer new methods for analyzing complex fluid flows.

Researchers enhance solar magnetic field simulations using advanced modeling techniques.

New method enhances accuracy of seismic wave modeling using advanced techniques.

Discover how FastVPINNs improve fluid dynamics modeling using neural networks.

New methods combine neural networks and finite element techniques to improve fluid flow simulations.

Combining traditional methods with AI to enhance PDE solutions.

Using machine learning to model electrical signals in the heart.

A look into how machine learning improves the study of material flow.