Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This study introduces SINFONIA, a framework comprising three neural-flow architectures designed for orbital numerical integration in gravitational-wave modeling, addressing the challenge of maintaining accuracy over long durations. By learning the finite-time evolution map as a differentiable, structure-preserving object, the models achieve significant reductions in phase errors during neutron-star inspirals, outperforming traditional methods at a lower computational cost. The findings reveal that long-time accuracy is influenced by a specific secular channel related to energy-angular-momentum balance, enabling effective physics inference from the learned maps.
Long-duration gravitational-wave modeling can achieve unprecedented accuracy and efficiency by leveraging learned, structure-preserving evolution maps.
Long-duration gravitational-wave modelling must resolve fast orbital motion together with slow dissipative evolution while preventing small numerical errors from accumulating into secular phase drift. Here we ask whether the finite-time evolution map itself can be learned as an explicit, differentiable, structure-preserving object and then repeatedly composed through a complete inspiral. We construct three neural-flow architectures: a symplectic and slimplectic flow on Galley's doubled phase space, [SINFONIA-J0]; a Taylor-anchored flow, [SINFONIA-J1]; and a Magnusian flow that learns the finite-time dissipative correction in the interaction picture, [SINFONIA-J2]. Applied to a 2.5PN neutron-star inspiral, all three expose the same controlling mechanism: long-time accuracy is governed not by pointwise map error alone, but by its signed projection onto a single secular channel fixed by energy--angular-momentum balance. Encoding this structure allows the learned maps to remain accurate through $10^{2}$--$10^{5}$ window compositions to coalescence at timesteps of a full orbital period and beyond, reaching chained phase errors orders of magnitude below a benchmark slimplectic integrator at lower cost. The same secular structure can also be exploited for physics inference: when the channel is left unconstrained, the accumulated phase retains enough information to recover an un-modelled dynamical-friction-like force, both parametrically and as a learned function of separation. Network-off controls isolate the contribution of learning from the analytic structure already built into each map. These results establish a proof of concept for structure-preserving learned evolution maps as tools for fast long-duration integration and physics inference in gravitational-wave source modelling.