Discovery of interpretable structural model errors by combining Bayesian sparse regression and data assimilation: A chaotic Kuramoto-Sivashinsky test case

Abstract

Models of many engineering and natural systems are imperfect. The discrepancy between the mathematical representations of a true physical system and its imperfect model is called the model error. These model errors can lead to substantial differences between the numerical solutions of the model and the state of the system, particularly in those involving nonlinear, multi-scale phenomena. Thus, there is increasing interest in reducing model errors, particularly by leveraging the rapidly growing observational data to understand their physics and sources. Here, we introduce a framework named MEDIDA: Model Error Discovery with Interpretability and Data Assimilation. MEDIDA only requires a working numerical solver of the model and a small number of noise-free or noisy sporadic observations of the system. In MEDIDA, first the model error is estimated from differences between the observed states and model-predicted states (the latter are obtained from a number of one-time-step numerical integrations from the previous observed states). If observations are noisy, a data assimilation (DA) technique such as ensemble Kalman filter (EnKF) is employed to provide the analysis state of the system, which is then used to estimate the model error. Finally, an equation-discovery technique, here the relevance vector machine (RVM), a sparsity-promoting Bayesian method, is used to identify an interpretable, parsimonious, and closed-form representation of the model error. Using the chaotic Kuramoto-Sivashinsky (KS) system as the test case, we demonstrate the excellent performance of MEDIDA in discovering different types of structural/parametric model errors, representing different types of missing physics, using noise-free and noisy observations.

arXiv comment9 pages, 2 figures

References in corpus (34)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• Deep learning to represent sub-grid processes in climate models
• Physics-informed learning of governing equations from scarce data
• FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Deep Neural Networks for Data-Driven Turbulence Models
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• Weak SINDy For Partial Differential Equations
• Analog forecasting of extreme-causing weather patterns using deep learning
• Model selection for dynamical systems via sparse regression and information criteria
• Combining data assimilation and machine learning to emulate a dynamical model from sparse and noisy observations: a case study with the Lorenz 96 model
• 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
• Spatially Extended Tests of a Neural Network Parametrization Trained by Coarse-graining
• Using Noisy or Incomplete Data to Discover Models of Spatiotemporal Dynamics
• Robust learning from noisy, incomplete, high-dimensional experimental data via physically constrained symbolic regression
• Sparse Identification of Nonlinear Dynamical Systems via Reweighted ${\ell }_1$-regularized Least Squares
• Discovery of Physics from Data: Universal Laws and Discrepancies
• Applying machine learning to improve simulations of a chaotic dynamical system using empirical error correction
• Feature engineering and symbolic regression methods for detecting hidden physics from sparse sensors
• Discovery of Nonlinear Dynamical Systems using a Runge-Kutta Inspired Dictionary-based Sparse Regression Approach
• Machine Learning for Prediction with Missing Dynamics
• Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning
• Long short-term memory embedded nudging schemes for nonlinear data assimilation of geophysical flows
• Combining machine learning and data assimilation to forecast dynamical systems from noisy partial observations
• Data-driven super-parameterization using deep learning: Experimentation with multi-scale Lorenz 96 systems and transfer-learning
• Climbing down Charney's ladder: Machine Learning and the post-Dennard era of computational climate science
• Using Data Assimilation to Train a Hybrid Forecast System that Combines Machine-Learning and Knowledge-Based Components
• Sparse Methods for Automatic Relevance Determination
• Using Machine Learning to Augment Coarse-Grid Computational Fluid Dynamics Simulations
• Physics-aware registration based auto-encoder for convection dominated PDEs
• BAMCAFE: A Bayesian Machine Learning Advanced Forecast Ensemble Method for Complex Turbulent Systems with Partial Observations
• Correcting Observation Model Error in Data Assimilation

Cited by in corpus (6)

• Deep learning of systematic sea ice model errors from data assimilation increments
• Machine learning for online sea ice bias correction within global ice-ocean simulations
• Learning Closed-form Equations for Subgrid-scale Closures from High-fidelity Data: Promises and Challenges
• CEBoosting: Online Sparse Identification of Dynamical Systems with Regime Switching by Causation Entropy Boosting
• Interpretable structural model error discovery from sparse assimilation increments using spectral bias-reduced neural networks: A quasi-geostrophic turbulence test case
• Remarks on the stabilization of large-scale growth in the 2D Kuramoto-Sivashinsky equation