Latent Space Data Assimilation by using Deep Learning

Abstract

Performing Data Assimilation (DA) at a low cost is of prime concern in Earth system modeling, particularly at the time of big data where huge quantities of observations are available. Capitalizing on the ability of Neural Networks techniques for approximating the solution of PDE's, we incorporate Deep Learning (DL) methods into a DA framework. More precisely, we exploit the latent structure provided by autoencoders (AEs) to design an Ensemble Transform Kalman Filter with model error (ETKF-Q) in the latent space. Model dynamics are also propagated within the latent space via a surrogate neural network. This novel ETKF-Q-Latent (thereafter referred to as ETKF-Q-L) algorithm is tested on a tailored instructional version of Lorenz 96 equations, named the augmented Lorenz 96 system: it possesses a latent structure that accurately represents the observed dynamics. Numerical experiments based on this particular system evidence that the ETKF-Q-L approach both reduces the computational cost and provides better accuracy than state of the art algorithms, such as the ETKF-Q.

arXiv comment15 pages, 7 figures and 3 tables

References in corpus (23)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Sequence to Sequence Learning with Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Solving high-dimensional partial differential equations using deep learning
• Fourier Neural Operator for Parametric Partial Differential Equations
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
• Deep Learning of Vortex Induced Vibrations
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
• Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders
• Combining data assimilation and machine learning to emulate a dynamical model from sparse and noisy observations: a case study with the Lorenz 96 model
• Solving parametric PDE problems with artificial neural networks
• Towards a Robust Parameterization for Conditioning Facies Models Using Deep Variational Autoencoders and Ensemble Smoother
• ReZero is All You Need: Fast Convergence at Large Depth
• Embedding Hard Physical Constraints in Neural Network Coarse-Graining of 3D Turbulence
• Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation
• Differentiable Physics-informed Graph Networks
• Controlling instabilities along a 3DVar analysis cycle by assimilating in the unstable subspace: a comparison with the EnKF
• An iterative ensemble Kalman filter in presence of additive model error
• 4DVAR by ensemble Kalman smoother
• IMEXnet: A Forward Stable Deep Neural Network
• Data assimilation empowered neural network parameterizations for subgrid processes in geophysical flows

Cited by in corpus (3)

• Integrating Recurrent Neural Networks with Data Assimilation for Scalable Data-Driven State Estimation
• Equation-free surrogate modeling of geophysical flows at the intersection of machine learning and data assimilation
• Adjoint-based Particle Forcing Reconstruction and Uncertainty Quantification