Saved in:
Bibliographic Details
Main Authors: Solvik, Kylen, Penny, Stephen G., Hoyer, Stephan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.02767
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911979288920064
author Solvik, Kylen
Penny, Stephen G.
Hoyer, Stephan
author_facet Solvik, Kylen
Penny, Stephen G.
Hoyer, Stephan
contents Constraining a numerical weather prediction (NWP) model with observations via 4D variational (4D-Var) data assimilation is often difficult to implement in practice due to the need to develop and maintain a software-based tangent linear model and adjoint model. One of the most common 4D-Var algorithms uses an incremental update procedure, which has been shown to be an approximation of the Gauss-Newton method. Here we demonstrate that when using a forecast model that supports automatic differentiation, an efficient and in some cases more accurate alternative approximation of the Gauss-Newton method can be applied by combining backpropagation of errors with Hessian approximation. This approach can be used with either a conventional numerical model implemented within a software framework that supports automatic differentiation, or a machine learning (ML) based surrogate model. We test the new approach on a variety of Lorenz-96 and quasi-geostrophic models. The results indicate potential for a deeper integration of modeling, data assimilation, and new technologies in a next-generation of operational forecast systems that leverage weather models designed to support automatic differentiation.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02767
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle 4D-Var using Hessian approximation and backpropagation applied to automatically-differentiable numerical and machine learning models
Solvik, Kylen
Penny, Stephen G.
Hoyer, Stephan
Machine Learning
Dynamical Systems
Geophysics
J.2; I.6.5; G.1.6
Constraining a numerical weather prediction (NWP) model with observations via 4D variational (4D-Var) data assimilation is often difficult to implement in practice due to the need to develop and maintain a software-based tangent linear model and adjoint model. One of the most common 4D-Var algorithms uses an incremental update procedure, which has been shown to be an approximation of the Gauss-Newton method. Here we demonstrate that when using a forecast model that supports automatic differentiation, an efficient and in some cases more accurate alternative approximation of the Gauss-Newton method can be applied by combining backpropagation of errors with Hessian approximation. This approach can be used with either a conventional numerical model implemented within a software framework that supports automatic differentiation, or a machine learning (ML) based surrogate model. We test the new approach on a variety of Lorenz-96 and quasi-geostrophic models. The results indicate potential for a deeper integration of modeling, data assimilation, and new technologies in a next-generation of operational forecast systems that leverage weather models designed to support automatic differentiation.
title 4D-Var using Hessian approximation and backpropagation applied to automatically-differentiable numerical and machine learning models
topic Machine Learning
Dynamical Systems
Geophysics
J.2; I.6.5; G.1.6
url https://arxiv.org/abs/2408.02767