Combining Machine Learning with Knowledge-Based Modeling for Scalable Forecasting and Subgrid-Scale Closure of Large, Complex, Spatiotemporal Systems

Abstract

We consider the commonly encountered situation (e.g., in weather forecasting) where the goal is to predict the time evolution of a large, spatiotemporally chaotic dynamical system when we have access to both time series data of previous system states and an imperfect model of the full system dynamics. Specifically, we attempt to utilize machine learning as the essential tool for integrating the use of past data into predictions. In order to facilitate scalability to the common scenario of interest where the spatiotemporally chaotic system is very large and complex, we propose combining two approaches:(i) a parallel machine learning prediction scheme; and (ii) a hybrid technique, for a composite prediction system composed of a knowledge-based component and a machine-learning-based component. We demonstrate that not only can this method combining (i) and (ii) be scaled to give excellent performance for very large systems, but also that the length of time series data needed to train our multiple, parallel machine learning components is dramatically less than that necessary without parallelization. Furthermore, considering cases where computational realization of the knowledge-based component does not resolve subgrid-scale processes, our scheme is able to use training data to incorporate the effect of the unresolved short-scale dynamics upon the resolved longer-scale dynamics ("subgrid-scale closure").

arXiv comment45 pages, 15 figures

References in corpus (6)

• Recent Advances in Physical Reservoir Computing: A Review
• AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
• Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
• High performance photonic reservoir computer based on a coherently driven passive cavity
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• Efficient Design of Hardware-Enabled Reservoir Computing in FPGAs

Cited by in corpus (18)

• Next Generation Reservoir Computing
• Using machine learning to correct model error in data assimilation and forecast applications
• Reconstruction of turbulent data with deep generative models for semantic inpainting from TURB-Rot database
• Combining machine learning and data assimilation to forecast dynamical systems from noisy partial observations
• OnsagerNet: Learning Stable and Interpretable Dynamics using a Generalized Onsager Principle
• Learning Spatiotemporal Chaos Using Next-Generation Reservoir Computing
• Using Data Assimilation to Train a Hybrid Forecast System that Combines Machine-Learning and Knowledge-Based Components
• Knowledge-Based Learning of Nonlinear Dynamics and Chaos
• State, global and local parameter estimation using local ensemble Kalman filters: applications to online machine learning of chaotic dynamics
• Catch-22s of reservoir computing
• Machine Learning Techniques to Construct Patched Analog Ensembles for Data Assimilation
• Model-free prediction of emergence of extreme events in a parametrically driven nonlinear dynamical system by Deep Learning
• Transfer learning of chaotic systems
• Effective models and predictability of chaotic multiscale systems via machine learning
• Generalizability of reservoir computing for flux-driven two-dimensional convection
• Kernel-based parameter estimation of dynamical systems with unknown observation functions
• Model-free Forecasting of Rogue Waves using Reservoir Computing
• Using machine-learning modelling to understand macroscopic dynamics in a system of coupled maps