The reviewed record of science sign in
Pith

arxiv: 1907.04502 · v2 · pith:DJFIJJJ7 · submitted 2019-07-10 · cs.LG · physics.comp-ph· stat.ML

DeepXDE: A deep learning library for solving differential equations

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:DJFIJJJ7record.jsonopen to challenge →

classification cs.LG physics.comp-phstat.ML
keywords deepxdepinnsproblemspdesequationslearningsolvingalgorithm
0
0 comments X
read the original abstract

Deep learning has achieved remarkable success in diverse applications; however, its use in solving partial differential equations (PDEs) has emerged only recently. Here, we present an overview of physics-informed neural networks (PINNs), which embed a PDE into the loss of the neural network using automatic differentiation. The PINN algorithm is simple, and it can be applied to different types of PDEs, including integro-differential equations, fractional PDEs, and stochastic PDEs. Moreover, from the implementation point of view, PINNs solve inverse problems as easily as forward problems. We propose a new residual-based adaptive refinement (RAR) method to improve the training efficiency of PINNs. For pedagogical reasons, we compare the PINN algorithm to a standard finite element method. We also present a Python library for PINNs, DeepXDE, which is designed to serve both as an education tool to be used in the classroom as well as a research tool for solving problems in computational science and engineering. Specifically, DeepXDE can solve forward problems given initial and boundary conditions, as well as inverse problems given some extra measurements. DeepXDE supports complex-geometry domains based on the technique of constructive solid geometry, and enables the user code to be compact, resembling closely the mathematical formulation. We introduce the usage of DeepXDE and its customizability, and we also demonstrate the capability of PINNs and the user-friendliness of DeepXDE for five different examples. More broadly, DeepXDE contributes to the more rapid development of the emerging Scientific Machine Learning field.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators

    cs.LG 2019-10 conditional novelty 8.0

    DeepONet learns nonlinear operators for differential equations via branch and trunk sub-networks, achieving high-order error convergence on small datasets.

  2. Universal Differential Equations for Scientific Machine Learning

    cs.LG 2020-01 unverdicted novelty 7.0

    Universal Differential Equations unify scientific models with machine learning by embedding flexible approximators into differential equations, enabling applications from biological mechanism discovery to high-dimensi...

  3. Partial-differential-algebraic equations of nonlinear dynamics by Physics-Informed Neural-Network: (I) Operator splitting and framework assessment

    math.NA 2024-07 unverdicted novelty 6.0

    Novel operator-splitting PINN forms for higher-level PDAEs are introduced and assessed against DeepXDE, with a custom JAX implementation showing advantages in avoiding certain pathologies.

  4. Frequency-Domain Neural ODEs for Modeling Non-Linear Dynamical Systems

    cs.LG 2026-06 unverdicted novelty 5.0

    FNODE projects Neural ODE dynamics into the frequency domain via FFT and reports better generalization and convergence stability than GRUs, LSTMs, and ANODE on Lotka-Volterra, forced Duffing, Van der Pol, and Lorenz systems.

  5. Physics-Informed Neural Networks for Solving Two-Flavor Neutrino Oscillations in Vacuum and Matter Environments for Atmospheric and Reactor Neutrinos

    hep-ph 2026-04 unverdicted novelty 5.0

    Physics-informed neural networks solve two-flavor neutrino oscillation equations in vacuum and matter with mean squared errors of order 10^{-3} to 10^{-4}, matching analytical results.

  6. Physics-Informed Neural Networks for Solving Two-Flavor Neutrino Oscillations in Vacuum and Matter Environments for Atmospheric and Reactor Neutrinos

    hep-ph 2026-04 unverdicted novelty 5.0

    PINNs solve two-flavor neutrino oscillation equations in vacuum and matter with mean squared errors of 10^{-3} to 10^{-4}, matching analytical solutions.

  7. Extending deep learning U-Net architecture for predicting unsteady fluid flows in textured microchannels

    cs.CE 2026-04 unverdicted novelty 4.0

    U-Net with attention mechanism predicts unsteady fluid flows in textured microchannels from lattice Boltzmann data with 5.18% average error, outperforming standard U-Net.

  8. Mass-Conserving Physics-Informed Neural Networks For The One-Dimensional Advection-Diffusion Equation

    physics.comp-ph 2026-07 conditional novelty 3.0

    Adding a soft mass-conservation penalty to PINNs for the 1D advection-diffusion equation reduces long-term relative L2 error by 9–67× and mass error by 15–215× compared to vanilla PINNs across Peclet numbers 0.01–20.

  9. Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics

    cs.LG 2022-12 unverdicted novelty 2.0

    A comprehensive review of deep learning techniques for computational mechanics, including LSTM for constitutive modeling, PINNs for PDE solving, optimizers, and kernel methods.