ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2212.04971
11
16

PDE-LEARN: Using Deep Learning to Discover Partial Differential Equations from Noisy, Limited Data

9 December 2022
R. Stephany
Christopher Earls
ArXivPDFHTML
Abstract

In this paper, we introduce PDE-LEARN, a novel deep learning algorithm that can identify governing partial differential equations (PDEs) directly from noisy, limited measurements of a physical system of interest. PDE-LEARN uses a Rational Neural Network, UUU, to approximate the system response function and a sparse, trainable vector, ξ\xiξ, to characterize the hidden PDE that the system response function satisfies. Our approach couples the training of UUU and ξ\xiξ using a loss function that (1) makes UUU approximate the system response function, (2) encapsulates the fact that UUU satisfies a hidden PDE that ξ\xiξ characterizes, and (3) promotes sparsity in ξ\xiξ using ideas from iteratively reweighted least-squares. Further, PDE-LEARN can simultaneously learn from several data sets, allowing it to incorporate results from multiple experiments. This approach yields a robust algorithm to discover PDEs directly from realistic scientific data. We demonstrate the efficacy of PDE-LEARN by identifying several PDEs from noisy and limited measurements.

View on arXiv
Comments on this paper