RELift: Learned coarse-to-fine propagators for time-dependent PDEs with applications to plasma dynamics
APL Computational Physics · 01.06.2026 · 2 (2)
DOI: 10.1063/5.0333466 ↗Kurz gefasst
Fachartikel in der Zeitschrift APL Computational Physics, online erschienen am 04.06.2026. Verfasst von Hardeep Bassi und 7 weiteren Autor:innen. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Office of Naval Research, U.S. Department of Energy, Defense Sciences Office, DARPA.
Abstract (Originalsprache)
We present RELift (Restrict, Evolve, Lift), a two-phase learning framework that couples coarse-grid numerical solvers with neural operators to super-resolve and forecast fine-grid dynamics for time-dependent partial differential equations (PDEs). In Phase 1, RELift learns a super-resolution operator that maps the solution on a coarse grid to a fine grid. In Phase 2, this learned operator is composed with a coarse-grid numerical integrator to construct an effective fine-grid propagator for the governing equation. We benchmark RELift on three canonical two-dimensional PDEs of increasing dynamical complexity—the heat equation, the wave equation, and the incompressible Navier–Stokes equations—and we further demonstrate its performance on a representative plasma dynamics case study via the 1D1V Vlasov–Poisson system. Across all examples, RELift delivers high-fidelity super-resolution (Phase 1) and accurate long-horizon rollouts (Phase 2), outperforming standard super-resolution and neural operator baselines in both field-level error metrics and physics-relevant diagnostics. Finally, we provide error analysis of the effective fine-grid propagator, characterizing how approximation errors accumulate over time and explaining the observed numerical stability of the RELift framework.
Förderung
- Office of Naval Research
- U.S. Department of Energy
- Defense Sciences Office, DARPA
- National Science Foundation
Zitieren
APA
Bassi, H., Zhu, Y., Ye, E., Ren, P., Dektor, A., Mahoney, M. W., Bhat, H. S., & Yang, C. (2026). RELift: Learned coarse-to-fine propagators for time-dependent PDEs with applications to plasma dynamics. APL Computational Physics, 2(2). https://doi.org/10.1063/5.0333466
Vancouver
Bassi H, Zhu Y, Ye E, Ren P, Dektor A, Mahoney MW, et al. RELift: Learned coarse-to-fine propagators for time-dependent PDEs with applications to plasma dynamics. APL Computational Physics. 2026;2(2). doi:10.1063/5.0333466
BibTeX
@article{Bassi2026,
author = {Bassi, Hardeep and Zhu, Yuanran and Ye, Erika and Ren, Pu and Dektor, Alec and Mahoney, Michael W. and Bhat, Harish S. and Yang, Chao},
title = {RELift: Learned coarse-to-fine propagators for time-dependent PDEs with applications to plasma dynamics},
journal = {APL Computational Physics},
year = {2026},
volume = {2},
number = {2},
doi = {10.1063/5.0333466}
}
EUVIMED