Staying on the Attractor: Supervising Neural Surrogates of 3D Turbulence Where They Leave It
This work proposes off-attractor supervision (OAS) to supervise neural surrogates where they leave the attractor and integrates physical models into neural simulation by extending supervision from fixed reference trajectories to states where the surrogate is likely to fail.
Yi-Long Dai, Shaswata Mitra, Raj Patel et al.
· 0 citations