Sparse-to-Field Reconstruction via Stochastic Neural Dynamic Mode Decomposition
By: Yujin Kim, Sarah Dean
Potential Business Impact:
Predicts how things like wind and water move.
Many consequential real-world systems, like wind fields and ocean currents, are dynamic and hard to model. Learning their governing dynamics remains a central challenge in scientific machine learning. Dynamic Mode Decomposition (DMD) provides a simple, data-driven approximation, but practical use is limited by sparse/noisy observations from continuous fields, reliance on linear approximations, and the lack of principled uncertainty quantification. To address these issues, we introduce Stochastic NODE-DMD, a probabilistic extension of DMD that models continuous-time, nonlinear dynamics while remaining interpretable. Our approach enables continuous spatiotemporal reconstruction at arbitrary coordinates and quantifies predictive uncertainty. Across four benchmarks, a synthetic setting and three physics-based flows, it surpasses a baseline in reconstruction accuracy when trained from only 10% observation density. It further recovers the dynamical structure by aligning learned modes and continuous-time eigenvalues with ground truth. Finally, on datasets with multiple realizations, our method learns a calibrated distribution over latent dynamics that preserves ensemble variability rather than averaging across regimes. Our code is available at: https://github.com/sedan-group/Stochastic-NODE-DMD
Similar Papers
Tensor Dynamic Mode Decomposition
Systems and Control
Finds hidden patterns in complex data.
Latent Diffeomorphic Dynamic Mode Decomposition
Machine Learning (CS)
Predicts water flow using smart math.
Dynamic Modes as Time Representation for Spatiotemporal Forecasting
Machine Learning (CS)
Predicts future weather and traffic better.