Variational Data Assimilation with a Learned Inverse Observation Operator
arXiv:2102.11192
Abstract
Variational data assimilation optimizes for an initial state of a dynamical system such that its evolution fits observational data. The physical model can subsequently be evolved into the future to make predictions. This principle is a cornerstone of large scale forecasting applications such as numerical weather prediction. As such, it is implemented in current operational systems of weather forecasting agencies across the globe. However, finding a good initial state poses a difficult optimization problem in part due to the non-invertible relationship between physical states and their corresponding observations. We learn a mapping from observational data to physical states and show how it can be used to improve optimizability. We employ this mapping in two ways: to better initialize the non-convex optimization problem, and to reformulate the objective function in better behaved physics space instead of observation space. Our experimental results for the Lorenz96 model and a two-dimensional turbulent fluid flow demonstrate that this procedure significantly improves forecast quality for chaotic systems.
arXiv commentPublished at the International Conference on Machine Learning (ICML) 2021
References in corpus (10)
- Machine learning accelerated computational fluid dynamics
- Learning data driven discretizations for partial differential equations
- MetNet: A Neural Weather Model for Precipitation Forecasting
- Using machine learning to correct model error in data assimilation and forecast applications
- Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers
- Learned discretizations for passive scalar advection in a 2-D turbulent flow
- Neural reparameterization improves structural optimization
- Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation
- Combining data assimilation and machine learning to infer unresolved scale parametrisation
- Learning Composable Energy Surrogates for PDE Order Reduction