Lune

ICLR2021Top-tier venue

Learning continuous-time PDEs from sparse data with graph neural networks

Valerii Iakovlev, Markus Heinonen, Harri Lähdesmäki

Abstract

The behavior of many dynamical systems follow complex, yet still unknown partial differential equations (PDEs). While several machine learning methods have been proposed to learn PDEs directly from data, previous methods are limited to discrete-time approximations or make the limiting assumption of the observations arriving at regular grids. We propose a general continuous-time differential model for dynamical systems whose governing equations are parameterized by message passing graph neural networks. The model admits arbitrary space and time discretizations, which removes constraints on the locations of observation points and time intervals between the observations. The model is trained with continuous-time adjoint method enabling efficient neural PDE inference. We demonstrate the model's ability to work with unstructured grids, arbitrary time steps, and noisy observations. We compare our method with existing approaches on several well-known physical systems that involve first and higher-order PDEs with state-of-the-art predictive performance.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

20 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks cites Physics-aware Difference Graph Networks for Sparsely-Observed Dynamics
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers20

  1. DiffusionPDE: Generative PDE-Solving under Partial ObservationJiahe Huang, Guandao Yang, Zichen Wang, Jeong Joon ParkNeurIPS 2024 · 148 citations
  2. ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEsYogesh Verma, Markus Heinonen, Vikas GargICLR 2024 · 93 citations
  3. Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element NetworksMarten Lienen, Stephan GünnemannICLR 2022 · 47 citations
  4. Predicting Ordinary Differential Equations with TransformersSören Becker, Michal Klein, Alexander Neitz, Giambattista Parascandolo et al.ICML 2023 · 28 citations
  5. Reconstructing Nonlinear Dynamical Systems from Multi-Modal Time SeriesDaniel Kramer, Philine Lou Bommer, Daniel Durstewitz, Carlo Tombolini et al.ICML 2022 · 25 citations

Builds on1

  1. Physics-aware Difference Graph Networks for Sparsely-Observed DynamicsSungyong Seo, Chuizheng Meng, Yan LiuICLR 2020 · 65 citations

Related papers

  1. PhyMPGN: Physics-encoded Message Passing Graph Network for spatiotemporal PDE systemsBocheng Zeng, Qi Wang, Mengtao Yan, Yang Liu et al.ICLR 2025
  2. Learning Space-Time Continuous Latent Neural PDEs from Partially Observed StatesValerii Iakovlev, Markus Heinonen, Harri LähdesmäkiNeurIPS 2023 · 3 citations
  3. Weak Form Generalized Hamiltonian LearningKevin Course, Trefor W. Evans, Prasanth B. NairNeurIPS 2020 · 15 citations
  4. Learning to Control PDEs with Differentiable PhysicsPhilipp Holl, Nils Thuerey, Vladlen KoltunICLR 2020 · 221 citations
  5. Neural Dynamics on Complex NetworksChengxi Zang, Fei WangKDD 2020 · 4 citations
Dusk over the sea between two cliffs drawn in fine vertical lines