CI-PINN introduces a causal integral neural architecture for evolution equations and PDEs, explicitly modeling temporal dependence through a Volterra-type causal integral module that addresses a limitation of conventional pointwise space-time PINN representations.
See LICENSE fileevolution equationsphysics-informed neural networkscausal integral network
The work develops a theory-grounded method with identifiability guarantees for identifying structural drivers and stochastic drift in delayed physical systems.
See LICENSE filedelayed physical systemsidentifiabilityphysics-informed neural networks
This study develops a PINN framework for the Savage-Hutter model of depth-averaged granular flow to support mountain avalanche hazard assessment. It advances from one-dimensional analytical verification of three problems to two-dimensional experimental validation of avalanche dynamics.
See LICENSE filephysics-informed neural networksavalanche dynamicsdepth-averaged granular flow
This paper introduces a representation curriculum for physics-informed neural networks, implemented through staged depth training that learns representations independently of their predictors and progressively refines them.
See LICENSE filephysics-informed neural networksrepresentation curriculumstaged depth training
This paper develops a tensor-train compressed separable physics-informed neural network framework for high-dimensional parametric PDEs. It uses a Gauss-Newton pullback metric to provide an operator-informed curvature notion and connects second-order PINN optimization with natural-gradient schemes.
See LICENSE filephysics-informed neural networkshigh-dimensional parametric PDEssecond-order optimization
NEXT presents physics-informed neuro-spectral exponential time-differencing architectures for time-dependent PDEs, targeting the spectral bias and causality limitations of PINNs and the numerical instability of NeuSA for stiff differential equations in neural representations.
See LICENSE filephysics-informed neural networksneuro-spectral architecturesexponential time differencing
Physics-informed neural networks recover the time-time component of static, spherically symmetric black-hole exterior metrics from a reduced ODE, using residual losses and asymptotic boundary constraints across charge and cosmological-constant sweeps.
See LICENSE filephysics-informed neural networksblack-hole exterior metricsgeneral relativity
A HuggingFace-hosted model repository for bubble dynamics using Physics-Informed Neural Networks (PINN), with the model name indicating focus on PINN-based bubble dynamics applications.