Numerical Gaussian Processes for Time-Dependent and Nonlinear Partial Differential Equations

From MaRDI portal
Publication:3130409

DOI10.1137/17M1120762zbMath1386.65030arXiv1703.10230OpenAlexW2605147767MaRDI QIDQ3130409

Paris Perdikaris, Maziar Raissi, George Em. Karniadakis

Publication date: 22 January 2018

Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1703.10230




Related Items (74)

Active training of physics-informed neural networks to aggregate and interpolate parametric solutions to the Navier-Stokes equationsRandomised one-step time integration methods for deterministic operator differential equationsOn a multilevel Levenberg–Marquardt method for the training of artificial neural networks and its application to the solution of partial differential equationsAugmented Gaussian random field: theory and computationUsing neural networks to accelerate the solution of the Boltzmann equationSystem identification through Lipschitz regularized deep neural networksA New Artificial Neural Network Method for Solving Schrödinger Equations on Unbounded DomainsSPINN: sparse, physics-based, and partially interpretable neural networks for PDEsSolving and learning nonlinear PDEs with Gaussian processesNormalizing field flows: solving forward and inverse stochastic differential equations using physics-informed flow modelsRevealing hidden dynamics from time-series data by ODENetLearning biological dynamics from spatio-temporal data by Gaussian processesRetracted: Model order reduction method based on machine learning for parameterized time-dependent partial differential equationsAPIK: Active Physics-Informed Kriging Model with Partial Differential EquationsScientific machine learning through physics-informed neural networks: where we are and what's nextAutodifferentiable Ensemble Kalman FiltersA hybrid MGA-MSGD ANN training approach for approximate solution of linear elliptic PDEsWasserstein generative adversarial uncertainty quantification in physics-informed neural networksThe Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error EstimationA survey of unsupervised learning methods for high-dimensional uncertainty quantification in black-box-type problemsStress-based topology optimization under uncertainty via simulation-based Gaussian processConservative physics-informed neural networks on discrete domains for conservation laws: applications to forward and inverse problemsGenerative Stochastic Modeling of Strongly Nonlinear Flows with Non-Gaussian StatisticsThe deep learning Galerkin method for the general Stokes equationsSolving second-order nonlinear evolution partial differential equations using deep learningNumerical solution of nonlinear stochastic differential equations with fractional Brownian motion using fractional-order Genocchi deep neural networksLearning sparse nonlinear dynamics via mixed-integer optimizationThree ways to solve partial differential equations with neural networks — A reviewCovariance models and Gaussian process regression for the wave equation. Application to related inverse problemsUnnamed ItemNumerical Approximations of the Allen-Cahn-Ohta-Kawasaki Equation with Modified Physics-Informed Neural Networks (Pinns)Bi-Orthogonal fPINN: A Physics-Informed Neural Network Method for Solving Time-Dependent Stochastic Fractional PDEs\(\mathrm{U}^p\)-net: a generic deep learning-based time stepper for parameterized spatio-temporal dynamicsDiscovery of PDEs driven by data with sharp gradient or discontinuityOn the influence of over-parameterization in manifold based surrogates and deep neural operatorsSparse Gaussian processes for solving nonlinear PDEsData-driven model identification using forcing-induced limit cyclesAn overview on deep learning-based approximation methods for partial differential equationsMethods to recover unknown processes in partial differential equations using dataData-driven discovery of PDEs in complex datasetsDiscovery of Nonlinear Multiscale Systems: Sampling Strategies and EmbeddingsData-Driven Identification of Parametric Partial Differential EquationsAdversarial uncertainty quantification in physics-informed neural networksApproximate Bayesian model inversion for PDEs with heterogeneous and state-dependent coefficientsPhysics-informed cokriging: a Gaussian-process-regression-based multifidelity method for data-model convergenceDeep learning of dynamics and signal-noise decomposition with time-stepping constraintsEnforcing constraints for interpolation and extrapolation in generative adversarial networksQuantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problemsSparse identification of truncation errorsExtracting Structured Dynamical Systems Using Sparse Optimization With Very Few SamplesAdaptive activation functions accelerate convergence in deep and physics-informed neural networksStructure-Preserving Method for Reconstructing Unknown Hamiltonian Systems From Trajectory DataData-driven rogue waves and parameter discovery in the defocusing nonlinear Schrödinger equation with a potential using the PINN deep learningNumerical solution and bifurcation analysis of nonlinear partial differential equations with extreme learning machinesHidden physics model for parameter estimation of elastic wave equationsDiscovery of Dynamics Using Linear Multistep MethodsDeep learning of vortex-induced vibrationsBayesian learning of orthogonal embeddings for multi-fidelity Gaussian processesBayesian differential programming for robust systems identification under uncertaintyDeep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential EquationsPhysics-Informed Generative Adversarial Networks for Stochastic Differential EquationsBayesian numerical methods for nonlinear partial differential equationsBi-directional coupling between a PDE-domain and an adjacent data-domain equipped with multi-fidelity sensorsMachine Learning of Space-Fractional Differential EquationsOptimally weighted loss functions for solving PDEs with neural networksInterpretable machine learning: fundamental principles and 10 grand challengesData-Driven Learning of Nonautonomous SystemsSparse polynomial chaos expansions using variational relevance vector machinesMonte Carlo fPINNs: deep learning method for forward and inverse problems involving high dimensional fractional partial differential equationsLearning ``best kernels from data in Gaussian process regression. With application to aerodynamicsThe SPDE approach to Matérn fields: graph representationsLearning and meta-learning of stochastic advection–diffusion–reaction systems from sparse measurementsPhysics Information Aided Kriging using Stochastic Simulation ModelsBridging the gap: machine learning to resolve improperly modeled dynamics


Uses Software


Cites Work


This page was built for publication: Numerical Gaussian Processes for Time-Dependent and Nonlinear Partial Differential Equations