SIAM Journal on Scientific Computing· 2026Q1
Symplectic Neural Flows for Modeling and Discovery
- 0citations
- Q1SCImago
- 2026year
Short summary
SympFlow, a novel symplectic neural network, accurately models Hamiltonian systems and preserves energy/momentum, outperforming general methods on chaotic/dissipative systems and approximating unknown systems from sparse data.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduces SympFlow, a time-dependent symplectic neural network based on parameterized Hamiltonian flow maps.
- SympFlow ensures preservation of the symplectic structure, crucial for energy and momentum conservation in simulations.
- Effectively models known Hamiltonian systems and approximates unknown systems using trajectory data.
- Outperforms general numerical methods in energy conservation for chaotic and dissipative systems.
- Provides theoretical guarantees for approximating Hamiltonian system flows and a posteriori error estimates.
AI-generated from the title and abstract; the full text is not read.
Abstract
Abstract. Hamilton’s equations are fundamental for modeling complex physical systems, where preserving key properties such as energy and momentum is crucial for reliable long-term simulations. Geometric integrators are widely used for this purpose, but neural network-based methods that incorporate these principles remain underexplored. This work introduces SympFlow, a time-dependent symplectic neural network designed using parameterized Hamiltonian flow maps. This design allows for backward error analysis and ensures the preservation of the symplectic structure. SympFlow allows for two key applications: (i) providing a time-continuous symplectic approximation of the exact flow of a Hamiltonian system—purely based on the differential equations it satisfies, and (ii) approximating the flow map of an unknown Hamiltonian system relying on trajectory data. We demonstrate the effectiveness of SympFlow on diverse problems, including chaotic and dissipative systems, showing improved energy conservation compared to general-purpose numerical methods and accurate approximations from sparse irregular data. We also provide a thorough theoretical analysis of SympFlow, showing it can approximate the flow of any time-dependent Hamiltonian system, and providing an a posteriori error estimate in terms of energy conservation.
The authors' abstract, as published at the source. SIAM Journal on Scientific Computing, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Numerical Analysis
Numerical AnalysisMathematics