Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model

Abstract

A model-based approach to forecasting chaotic dynamical systems utilizes knowledge of the physical processes governing the dynamics to build an approximate mathematical model of the system. In contrast, machine learning techniques have demonstrated promising results for forecasting chaotic systems purely from past time series measurements of system state variables (training data), without prior knowledge of the system dynamics. The motivation for this paper is the potential of machine learning for filling in the gaps in our underlying mechanistic knowledge that cause widely-used knowledge-based models to be inaccurate. Thus we here propose a general method that leverages the advantages of these two approaches by combining a knowledge-based model and a machine learning technique to build a hybrid forecasting scheme. Potential applications for such an approach are numerous (e.g., improving weather forecasting). We demonstrate and test the utility of this approach using a particular illustrative version of a machine learning known as reservoir computing, and we apply the resulting hybrid forecaster to a low-dimensional chaotic system, as well as to a high-dimensional spatiotemporal chaotic system. These tests yield extremely promising results in that our hybrid technique is able to accurately predict for a much longer period of time than either its machine-learning component or its model-based component alone.

References in corpus (4)

• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• Reservoir computing with a single time-delay autonomous Boolean node
• Brain-inspired photonic signal processor for periodic pattern generation and chaotic system emulation

Cited by in corpus (64)

• Attractor Reconstruction by Machine Learning
• Will Artificial Intelligence supersede Earth System and Climate Models?
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• Deep learning of dynamics and signal-noise decomposition with time-stepping constraints
• A deep learning enabler for non-intrusive reduced order modeling of fluid flows
• Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM
• Using machine learning to correct model error in data assimilation and forecast applications
• A non-intrusive reduced order modeling framework for quasi-geostrophic turbulence
• Good and bad predictions: Assessing and improving the replication of chaotic attractors by means of reservoir computing
• Rapid Time Series Prediction with a Hardware-Based Reservoir Computer
• Anticipating synchronization with machine learning
• Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction
• Combining Machine Learning with Knowledge-Based Modeling for Scalable Forecasting and Subgrid-Scale Closure of Large, Complex, Spatiotemporal Systems
• Reservoir Computing with Diverse Timescales for Prediction of Multiscale Dynamics
• A long short-term memory embedding for hybrid uplifted reduced order models
• Memory embedded non-intrusive reduced order modeling of non-ergodic flows
• Combining machine learning and data assimilation to forecast dynamical systems from noisy partial observations
• Physics-Informed Echo State Networks
• Learning Spatiotemporal Chaos Using Next-Generation Reservoir Computing
• Neural Network Forecast of the Sunspot Butterfly Diagram
• Using Machine Learning to Anticipate Tipping Points and Extrapolate to Post-Tipping Dynamics of Non-Stationary Dynamical Systems
• Adaptable Hamiltonian neural networks
• Using reservoir computer to predict and prevent extreme events
• A multi-model ensemble Kalman filter for data assimilation and forecasting
• Using Data Assimilation to Train a Hybrid Forecast System that Combines Machine-Learning and Knowledge-Based Components
• Insight into Delay Based Reservoir Computing via Eigenvalue Analysis
• Catch-22s of reservoir computing
• Quantum reservoir computing in finite dimensions
• Predicting Critical Transitions in Multiscale Dynamical Systems Using Reservoir Computing
• Finding nonlinear system equations and complex network structures from data: a sparse optimization approach
• Model-Size Reduction for Reservoir Computing by Concatenating Internal States Through Time
• Gradient-free optimization of chaotic acoustics with reservoir computing
• Echo State Networks with Self-Normalizing Activations on the Hyper-Sphere
• Reducing network size and improving prediction stability of reservoir computing
• Physics-Informed Echo State Networks for Chaotic Systems Forecasting
• Machine Learning Link Inference of Noisy Delay-coupled Networks with Opto-Electronic Experimental Tests
• Hybridizing Traditional and Next-Generation Reservoir Computing to Accurately and Efficiently Forecast Dynamical Systems
• Chaotic attractor reconstruction using small reservoirs -- the influence of topology
• Comparison of neural closure models for discretised PDEs
• Identification of Chimera using Machine Learning
• Effective models and predictability of chaotic multiscale systems via machine learning
• Inverse Mechano-Electrical Reconstruction of Cardiac Excitation Wave Patterns from Mechanical Deformation using Deep Learning
• Resampling with neural networks for stochastic parameterization in multiscale systems
• Inferring symbolic dynamics of chaotic flows from persistence
• Two methods to approximate the Koopman operator with a reservoir computer
• Artificial Intelligence, Chaos, Prediction and Understanding in Science
• Generalizability of reservoir computing for flux-driven two-dimensional convection
• Reconstruction of Three-dimensional Scroll Waves in Excitable Media from Two-Dimensional Observations using Deep Neural Networks
• Bridging the Gap: Machine Learning to Resolve Improperly Modeled Dynamics
• Analysis of a bistable climate toy model with physics-based machine learning methods
• Quantifying the Classification of Exoplanets: in Search for the Right Habitability Metric
• Characterization of Fractal Basins Using Deep Convolutional Neural Networks
• How more data can hurt: Instability and regularization in next-generation reservoir computing
• Deep Learning-based Analysis of Basins of Attraction
• Temporal Convolution Derived Multi-Layered Reservoir Computing
• Using machine-learning modelling to understand macroscopic dynamics in a system of coupled maps
• Learning-based model augmentation with LFRs
• Improving the prediction of spatio-temporal chaos by combining parallel reservoir computing with dimensionality reduction
• Learning Beyond Experience: Generalizing to Unseen State Space with Reservoir Computing
• Model-free Forecasting of Rogue Waves using Reservoir Computing
• Predicting three-dimensional chaotic systems with four qubit quantum systems
• Incorporating Coupling Knowledge into Echo State Networks for Learning Spatiotemporally Chaotic Dynamics
• Advanced Techniques in Stability Analysis of Trans-Neptunian Objects