Integrating Recurrent Neural Networks with Data Assimilation for Scalable Data-Driven State Estimation

Abstract

Data assimilation (DA) is integrated with machine learning in order to perform entirely data-driven online state estimation. To achieve this, recurrent neural networks (RNNs) are implemented as surrogate models to replace key components of the DA cycle in numerical weather prediction (NWP), including the conventional numerical forecast model, the forecast error covariance matrix, and the tangent linear and adjoint models. It is shown how these RNNs can be initialized using DA methods to directly update the hidden/reservoir state with observations of the target system. The results indicate that these techniques can be applied to estimate the state of a system for the repeated initialization of short-term forecasts, even in the absence of a traditional numerical forecast model. Further, it is demonstrated how these integrated RNN-DA methods can scale to higher dimensions by applying domain localization and parallelization, providing a path for practical applications in NWP.

22 pages, 16 figures

References in corpus (4)

• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Forecasting Chaotic Systems with Very Low Connectivity Reservoir Computers
• Latent Space Data Assimilation by using Deep Learning
• Online learning of both state and dynamics using ensemble Kalman filters

Cited by in corpus (5)

• Deep learning-enhanced ensemble-based data assimilation for high-dimensional nonlinear dynamical systems
• Equation-free surrogate modeling of geophysical flows at the intersection of machine learning and data assimilation
• Latent assimilation with implicit neural representations for unknown dynamics
• Ensemble data assimilation to diagnose AI-based weather prediction model: A case with ClimaX version 0.3.1
• State-observation augmented diffusion model for nonlinear assimilation with unknown dynamics