Pith. sign in

Discovering Nonlinear PDEs from Scarce Data with Physics-encoded Learning

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

There have been growing interests in leveraging experimental measurements to discover the underlying partial differential equations (PDEs) that govern complex physical phenomena. Although past research attempts have achieved great success in data-driven PDE discovery, the robustness of the existing methods cannot be guaranteed when dealing with low-quality measurement data. To overcome this challenge, we propose a novel physics-encoded discrete learning framework for discovering spatiotemporal PDEs from scarce and noisy data. The general idea is to (1) firstly introduce a novel deep convolutional-recurrent network, which can encode prior physics knowledge (e.g., known PDE terms, assumed PDE structure, initial/boundary conditions, etc.) while remaining flexible on representation capability, to accurately reconstruct high-fidelity data, and (2) perform sparse regression with the reconstructed data to identify the explicit form of the governing PDEs. We validate our method on three nonlinear PDE systems. The effectiveness and superiority of the proposed method over baseline models are demonstrated.

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

SlotPi: Physics-informed Object-centric Reasoning Models

cs.CV · 2025-06-12 · conditional · novelty 5.0

SlotPi combines a learned Hamiltonian energy module with spatiotemporal attention to improve object-centric video prediction and visual question answering on several datasets.

citing papers explorer

Showing 1 of 1 citing paper.

  • SlotPi: Physics-informed Object-centric Reasoning Models cs.CV · 2025-06-12 · conditional · none · ref 54 · internal anchor

    SlotPi combines a learned Hamiltonian energy module with spatiotemporal attention to improve object-centric video prediction and visual question answering on several datasets.