A competitive baseline for deep learning enhanced data assimilation using conditional Gaussian ensemble Kalman filtering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Malik, Zachariah, Maulik, Romit
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916405918564352
author Malik, Zachariah
Maulik, Romit
author_facet Malik, Zachariah
Maulik, Romit
contents Ensemble Kalman Filtering (EnKF) is a popular technique for data assimilation, with far ranging applications. However, the vanilla EnKF framework is not well-defined when perturbations are nonlinear. We study two non-linear extensions of the vanilla EnKF - dubbed the conditional-Gaussian EnKF (CG-EnKF) and the normal score EnKF (NS-EnKF) - which sidestep assumptions of linearity by constructing the Kalman gain matrix with the `conditional Gaussian' update formula in place of the traditional one. We then compare these models against a state-of-the-art deep learning based particle filter called the score filter (SF). This model uses an expensive score diffusion model for estimating densities and also requires a strong assumption on the perturbation operator for validity. In our comparison, we find that CG-EnKF and NS-EnKF dramatically outperform SF for a canonical problem in high-dimensional multiscale data assimilation given by the Lorenz-96 system. Our analysis also demonstrates that the CG-EnKF and NS-EnKF can handle highly non-Gaussian additive noise perturbations, with the latter typically outperforming the former.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14300
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A competitive baseline for deep learning enhanced data assimilation using conditional Gaussian ensemble Kalman filtering
Malik, Zachariah
Maulik, Romit
Machine Learning
Dynamical Systems
Atmospheric and Oceanic Physics
Ensemble Kalman Filtering (EnKF) is a popular technique for data assimilation, with far ranging applications. However, the vanilla EnKF framework is not well-defined when perturbations are nonlinear. We study two non-linear extensions of the vanilla EnKF - dubbed the conditional-Gaussian EnKF (CG-EnKF) and the normal score EnKF (NS-EnKF) - which sidestep assumptions of linearity by constructing the Kalman gain matrix with the `conditional Gaussian' update formula in place of the traditional one. We then compare these models against a state-of-the-art deep learning based particle filter called the score filter (SF). This model uses an expensive score diffusion model for estimating densities and also requires a strong assumption on the perturbation operator for validity. In our comparison, we find that CG-EnKF and NS-EnKF dramatically outperform SF for a canonical problem in high-dimensional multiscale data assimilation given by the Lorenz-96 system. Our analysis also demonstrates that the CG-EnKF and NS-EnKF can handle highly non-Gaussian additive noise perturbations, with the latter typically outperforming the former.
title A competitive baseline for deep learning enhanced data assimilation using conditional Gaussian ensemble Kalman filtering
topic Machine Learning
Dynamical Systems
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2409.14300