Using machine learning to correct model error in data assimilation and forecast applications

Abstract

The idea of using machine learning (ML) methods to reconstruct the dynamics of a system is the topic of recent studies in the geosciences, in which the key output is a surrogate model meant to emulate the dynamical model. In order to treat sparse and noisy observations in a rigorous way, ML can be combined to data assimilation (DA). This yields a class of iterative methods in which, at each iteration a DA step assimilates the observations, and alternates with a ML step to learn the underlying dynamics of the DA analysis. In this article, we propose to use this method to correct the error of an existent, knowledge-based model. In practice, the resulting surrogate model is an hybrid model between the original (knowledge-based) model and the ML model. We demonstrate numerically the feasibility of the method using a two-layer, two-dimensional quasi-geostrophic channel model. Model error is introduced by the means of perturbed parameters. The DA step is performed using the strong-constraint 4D-Var algorithm, while the ML step is performed using deep learning tools. The ML models are able to learn a substantial part of the model error and the resulting hybrid surrogate models produce better short- to mid-range forecasts. Furthermore, using the hybrid surrogate models for DA yields a significantly better analysis than using the original model.

References in corpus (4)

• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Bayesian inference of chaotic dynamics by merging data assimilation, machine learning and expectation-maximization
• Combining Machine Learning with Knowledge-Based Modeling for Scalable Forecasting and Subgrid-Scale Closure of Large, Complex, Spatiotemporal Systems
• Combining data assimilation and machine learning to infer unresolved scale parametrisation

Cited by in corpus (19)

• A posteriori learning for quasi-geostrophic turbulence parametrization
• Inferring unknown unknowns: Regularized bias-aware ensemble Kalman filter
• Deep learning of systematic sea ice model errors from data assimilation increments
• State, global and local parameter estimation using local ensemble Kalman filters: applications to online machine learning of chaotic dynamics
• 3D-Var Data Assimilation using a Variational Autoencoder
• Machine learning for online sea ice bias correction within global ice-ocean simulations
• Combining data assimilation and machine learning to estimate parameters of a convective-scale model
• Discovery of interpretable structural model errors by combining Bayesian sparse regression and data assimilation: A chaotic Kuramoto-Sivashinsky test case
• BAMCAFE: A Bayesian Machine Learning Advanced Forecast Ensemble Method for Complex Turbulent Systems with Partial Observations
• Learning complexity to guide light-induced self-organized nanopatterns
• Development of an offline and online hybrid model for the Integrated Forecasting System
• Interpretable structural model error discovery from sparse assimilation increments using spectral bias-reduced neural networks: A quasi-geostrophic turbulence test case
• Variational Data Assimilation with a Learned Inverse Observation Operator
• Real-time forecasting of chaotic dynamics from sparse data and autoencoders
• Filtering Dynamical Systems Using Observations of Statistics
• Exact nonlinear state estimation
• Physically Consistent Global Atmospheric Data Assimilation with Machine Learning in Latent Space
• Latent assimilation with implicit neural representations for unknown dynamics
• Ensemble Transport Filter via Optimized Maximum Mean Discrepancy