Deep reconstruction of strange attractors from time series

Abstract

Experimental measurements of physical systems often have a limited number of independent channels, causing essential dynamical variables to remain unobserved. However, many popular methods for unsupervised inference of latent dynamics from experimental data implicitly assume that the measurements have higher intrinsic dimensionality than the underlying system---making coordinate identification a dimensionality reduction problem. Here, we study the opposite limit, in which hidden governing coordinates must be inferred from only a low-dimensional time series of measurements. Inspired by classical analysis techniques for partial observations of chaotic attractors, we introduce a general embedding technique for univariate and multivariate time series, consisting of an autoencoder trained with a novel latent-space loss function. We show that our technique reconstructs the strange attractors of synthetic and real-world systems better than existing techniques, and that it creates consistent, predictive representations of even stochastic systems. We conclude by using our technique to discover dynamical attractors in diverse systems such as patient electrocardiograms, household electricity usage, neural spiking, and eruptions of the Old Faithful geyser---demonstrating diverse applications of our technique for exploratory data analysis.

arXiv comment9 pages, 6 figures, plus appendices

References in corpus (16)

• Scikit-learn: Machine Learning in Python
• Deep learning for universal linear embeddings of nonlinear dynamics
• Data-driven discovery of coordinates and governing equations
• Chaos as an Intermittently Forced Linear System
• Learning data driven discretizations for partial differential equations
• Attractor Reconstruction by Machine Learning
• Discovering Symbolic Models from Deep Learning with Inductive Biases
• A Unified Approach to Attractor Reconstruction
• Cellular automata as convolutional neural networks
• Adaptive, locally-linear models of complex dynamics
• Limits to causal inference with state-space reconstruction for infectious disease
• Multivariate phase space reconstruction by nearest neighbor embedding with different time delays
• Learning Dynamical Systems from Partial Observations
• Phase space embedding of electrocardiograms
• Topological time-series analysis with delay-variant embedding
• Learning low-dimensional state embeddings and metastable clusters from time series data

Cited by in corpus (4)

• Learning Latent Dynamics for Partially-Observed Chaotic Systems
• Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning
• Robust undulatory locomotion via neuromechanical adjustments in a dissipative medium
• How more data can hurt: Instability and regularization in next-generation reservoir computing