PAINT: Parallel-in-time Neural Twins for Dynamical System Reconstruction
This addresses the challenge of accurate state estimation and decision-making for real systems like fluid dynamics, but it appears incremental as it builds on neural surrogates with a novel training approach.
The paper tackled the problem of creating neural twins that remain on-trajectory for dynamical systems, and the result showed that PAINT stays on-trajectory and predicts states from sparse measurements with high fidelity in a turbulent fluid dynamics problem.
Neural surrogates have shown great potential in simulating dynamical systems, while offering real-time capabilities. We envision Neural Twins as a progression of neural surrogates, aiming to create digital replicas of real systems. A neural twin consumes measurements at test time to update its state, thereby enabling context-specific decision-making. A critical property of neural twins is their ability to remain on-trajectory, i.e., to stay close to the true system state over time. We introduce Parallel-in-time Neural Twins (PAINT), an architecture-agnostic family of methods for modeling dynamical systems from measurements. PAINT trains a generative neural network to model the distribution of states parallel over time. At test time, states are predicted from measurements in a sliding window fashion. Our theoretical analysis shows that PAINT is on-trajectory, whereas autoregressive models generally are not. Empirically, we evaluate our method on a challenging two-dimensional turbulent fluid dynamics problem. The results demonstrate that PAINT stays on-trajectory and predicts system states from sparse measurements with high fidelity. These findings underscore PAINT's potential for developing neural twins that stay on-trajectory, enabling more accurate state estimation and decision-making.