Real-time forecasting of chaotic dynamics from sparse data and autoencoders
arXiv:2508.08729 · doi:10.1016/j.cma.2025.118600
Abstract
The real-time prediction of chaotic systems requires a nonlinear-reduced order model (ROM) to forecast the dynamics, and a stream of data from sensors to update the ROM. Data-driven ROMs are typically built with a two-step strategy: data compression in a lower-dimensional latent space, and prediction of the temporal dynamics on it. To achieve real-time prediction, however, there are two challenges to overcome: (i) ROMs of chaotic systems can become numerically unstable; and (ii) sensors' data are sparse, i.e., partial, and noisy. To overcome these challenges, we propose a three-step strategy: (i) a convolutional autoencoder (CAE) compresses the system's state onto a lower-dimensional latent space; (ii) a latent ROM (echo state network, ESN), which is formulated as a state-space model, predicts the temporal evolution on the latent space; and (iii) sequential data assimilation based on the Ensemble Kalman filter (EnKF) adaptively corrects the latent ROM by assimilating noisy and sparse measurements. This provides a numerically stable method (DA-CAE-ESN), which corrects itself every time that data becomes available from sensors. The DA-CAE-ESN is tested on spatio-temporally chaotic partial differential equations: the Kuramoto-Sivashinsky equation, and a two-dimensional Navier-Stokes equation (Kolmogorov flow). We show that the method provides accurate and stable forecasts across different levels of noise, sparsity, and sampling rates. As a by-product, the DA-CAE-ESN acts as a localization strategy that mitigates spurious correlations, which arise when applying the EnKF to high-dimensional systems. The DA-CAE-ESN provides a numerically stable method to perform real-time predictions, which opens opportunities for deploying data-driven latent models.
References in corpus (28)
- Machine Learning for Fluid Mechanics
- Turbulence Modeling in the Age of Data
- Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
- Data-Driven Sparse Sensor Placement for Reconstruction
- Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders
- Convolutional neural network and long short-term memory based reduced order surrogate for minimal turbulent channel flow
- Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data
- On the need for a nonlinear subscale turbulence term in POD models as exemplified for a high Reynolds number flow over an Ahmed body
- Using machine learning to correct model error in data assimilation and forecast applications
- Ensemble Kalman method for learning turbulence models from indirect observation data
- Deep learning to discover and predict dynamics on an inertial manifold
- An extension of the Lyapunov analysis for the predictability problem
- Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systems
- Data-Driven Reduced-Order Modeling of Spatiotemporal Chaos with Neural Ordinary Differential Equations
- Spatio-temporal Proper Orthogonal Decomposition of turbulent channel flow
- Scaling of Lyapunov Exponents in Homogeneous Isotropic Turbulence
- Revealing the state space of turbulence using machine learning
- Inferring unknown unknowns: Regularized bias-aware ensemble Kalman filter
- Data-driven low-dimensional dynamic model of Kolmogorov flow
- Stability, sensitivity and optimisation of chaotic acoustic oscillations
- Stability analysis of chaotic systems from data
- Real-time thermoacoustic data assimilation
- Characterizing viscoelastic materials via ensemble-based data assimilation of bubble collapse observations
- Reconstruction, forecasting, and stability of chaotic dynamics from partial data
- Generalizability of reservoir computing for flux-driven two-dimensional convection
- Decoder Decomposition for the Analysis of the Latent Space of Nonlinear Autoencoders With Wind-Tunnel Experimental Data
- A real-time digital twin of azimuthal thermoacoustic instabilities
- Stochastic Latent Transformer: Efficient Modelling of Stochastically Forced Zonal Jets