From Fourier to Koopman: Spectral Methods for Long-term Time Series Prediction

Abstract

We propose spectral methods for long-term forecasting of temporal signals stemming from linear and nonlinear quasi-periodic dynamical systems. For linear signals, we introduce an algorithm with similarities to the Fourier transform but which does not rely on periodicity assumptions, allowing for forecasting given potentially arbitrary sampling intervals. We then extend this algorithm to handle nonlinearities by leveraging Koopman theory. The resulting algorithm performs a spectral decomposition in a nonlinear, data-dependent basis. The optimization objective for both algorithms is highly non-convex. However, expressing the objective in the frequency domain allows us to compute global optima of the error surface in a scalable and efficient manner, partially by exploiting the computational properties of the Fast Fourier Transform. Because of their close relation to Bayesian Spectral Analysis, uncertainty quantification metrics are a natural byproduct of the spectral forecasting methods. We extensively benchmark these algorithms against other leading forecasting methods on a range of synthetic experiments as well as in the context of real-world power systems and fluid flows.

References in corpus (12)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Deep learning for universal linear embeddings of nonlinear dynamics
• Data-driven discovery of coordinates and governing equations
• Koopman invariant subspaces and finite linear representations of nonlinear dynamical systems for control
• Chaos as an Intermittently Forced Linear System
• Extracting spatial-temporal coherent patterns in large-scale neural recordings using dynamic mode decomposition
• Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics
• A Clockwork RNN
• Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability
• Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction
• Bifurcations in a Quasi-Two-Dimensional Kolmogorov-Like Flow
• Human Gait Database for Normal Walk Collected by Smartphone Accelerometer

Cited by in corpus (4)

• Data-driven Modeling of Rotating Detonation Waves
• Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning
• Extraction of instantaneous frequencies and amplitudes in nonstationary time-series data
• Data-driven discovery of quasiperiodically driven dynamics