Pith. sign in

REVIEW 6 cited by

Continuous PDE Dynamics Forecasting with Implicit Neural Representations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2209.14855 v2 pith:GFH5CMLC submitted 2022-09-29 cs.LG cs.AIcs.NEstat.ML

classification cs.LGcs.AIcs.NEstat.ML
keywords data-drivendinoneuralspatialarbitrarycontinuousdynamicsflexible
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Effective data-driven PDE forecasting methods often rely on fixed spatial and / or temporal discretizations. This raises limitations in real-world applications like weather prediction where flexible extrapolation at arbitrary spatiotemporal locations is required. We address this problem by introducing a new data-driven approach, DINo, that models a PDE's flow with continuous-time dynamics of spatially continuous functions. This is achieved by embedding spatial observations independently of their discretization via Implicit Neural Representations in a small latent space temporally driven by a learned ODE. This separate and flexible treatment of time and space makes DINo the first data-driven model to combine the following advantages. It extrapolates at arbitrary spatial and temporal locations; it can learn from sparse irregular grids or manifolds; at test time, it generalizes to new grids or resolutions. DINo outperforms alternative neural PDE forecasters in a variety of challenging generalization scenarios on representative PDE systems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Disentangled Latent Dynamics Manifold Fusion for Solving Parameterized PDEs

    cs.LG 2026-03 unverdicted novelty 6.0 of 10

    DLDMF maps PDE parameters to latent embeddings that drive a Neural ODE and a shared decoder, improving parameter generalization and long-horizon temporal extrapolation over prior neural surrogates.

  2. Geometric Operator Learning with Optimal Transport

    cs.LG 2025-07 conditional novelty 6.0 of 10

    An optimal transport based geometry embedding, computed independently for each shape, improves accuracy and reduces compute for neural operator predictions of surface pressure and drag on car and airfoil benchmarks.

  3. Physics-based machine learning for mantle convection simulations

    astro-ph.EP 2025-05 conditional novelty 6.0 of 10

    A neural network that predicts divergence-free mantle flow velocities from temperature can replace the Stokes solver in 2D convection simulations, enabling stable rollouts and up to 89x speedup with only 94 training s...

  4. Geometric Neural Process Fields

    cs.CV 2025-02 conditional novelty 6.0 of 10

    Geometric Neural Process Fields use Gaussian geometric bases and hierarchical latent variables to improve neural process generalization to 1D, 2D, and 3D signals.

  5. ECLEIRS: Exact conservation law embedded identification of reduced states for parameterized partial differential equations from sparse and noisy data

    physics.comp-ph 2025-06 conditional novelty 5.0 of 10

    ECLEIRS embeds exact conservation laws into a neural reduced-order model by representing solution and flux as divergences of a skew-symmetric matrix field, improving robustness to sparse and noisy data and accuracy fo...

  6. PDEfuncta: Spectrally-Aware Neural Representation for PDE Solution Modeling

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A Fourier-based weight modulation for shared INR networks improves reconstruction of high-frequency PDE fields and enables bidirectional inference between paired solution spaces.

Pith tools