cs.LGNov 3, 2026

Learning Implicit Solves for Dynamic Simulations

Authors: Chawit Kaewnuratchadasorn, Jiaji Wang, Xin Nie

Organizations: Department of Civil Engineering, The University of Hong Kong, Pok Fu Lam, Hong Kong, China. · Department of Civil Engineering, Tsinghua University, Haidian, Beijing, China.

Abstract

High-fidelity simulation of dynamical systems is central to scientific discovery and engineering design, yet remains computationally demanding. Here we introduce the Implicit Neural Operator Solver (INOS), which learns the implicit solve and encodes a time integrator. INOS pretrains a neural operator from static equilibrium solutions and reuses it within Newmark-ββ integration. At each time increment, the integrator forms an effective equilibrium problem, the pretrained neural operator infers the next-step solution field, and the Newmark relations advance the dynamic state. Numerical examples in linear and nonlinear elastodynamics demonstrate accurate full-field predictions without dynamic trajectory supervision. Comparative results show that INOS, evaluated zero-shot, achieves higher predictive accuracy than neural solver baselines trained on dynamic simulations. In addition, INOS delivers over 4,600×\times speedup in nonlinear simulations over sequential classical finite-element solvers. INOS natively accommodates changes in dynamic conditions and enables reuse of the pretrained operator across spatial and temporal discretizations. Further evaluation demonstrates a stable million-step rollout. These findings establish INOS as a reusable neural implicit solver for accurate, efficient, and robust dynamic modeling.

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Neural Operator Splitting for Fluid Dynamics in Complex Geometry

    Oct 20, 2026Jianxiang Li, Xi Deng, Hong Chul Nam +1PDE Operator LearningNeural Operators

  2. Do Neural PDE Solvers Learn the Right Dynamics?

    Oct 3, 2026Haonan Li, Yue Song, Bin Yang +1Neural PDE SolversDynamical Systems

  3. NN-OpInf: an operator inference approach using structure-preserving composable neural networks

    Mar 9, 2026Eric Parish, Anthony Gruber, Patrick Blonigan +1Structure-Preserving Neural NetworksReduced-Order Modeling