Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Adrian, Melissa, Sanz-Alonso, Daniel, Willett, Rebecca
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2405.13180
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909486797553664
author Adrian, Melissa
Sanz-Alonso, Daniel
Willett, Rebecca
author_facet Adrian, Melissa
Sanz-Alonso, Daniel
Willett, Rebecca
contents Modern data-driven surrogate models for weather forecasting provide accurate short-term predictions but inaccurate and nonphysical long-term forecasts. This paper investigates online weather prediction using machine learning surrogates supplemented with partial and noisy observations. We empirically demonstrate and theoretically justify that, despite the long-time instability of the surrogates and the sparsity of the observations, filtering estimates can remain accurate in the long-time horizon. As a case study, we integrate FourCastNet, a weather surrogate model, within a variational data assimilation framework using partial, noisy ERA5 data. Our results show that filtering estimates remain accurate over a year-long assimilation window and provide effective initial conditions for forecasting tasks, including extreme event prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13180
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Data Assimilation with Machine Learning Surrogate Models: A Case Study with FourCastNet
Adrian, Melissa
Sanz-Alonso, Daniel
Willett, Rebecca
Signal Processing
Machine Learning
Chaotic Dynamics
Atmospheric and Oceanic Physics
Applications
Modern data-driven surrogate models for weather forecasting provide accurate short-term predictions but inaccurate and nonphysical long-term forecasts. This paper investigates online weather prediction using machine learning surrogates supplemented with partial and noisy observations. We empirically demonstrate and theoretically justify that, despite the long-time instability of the surrogates and the sparsity of the observations, filtering estimates can remain accurate in the long-time horizon. As a case study, we integrate FourCastNet, a weather surrogate model, within a variational data assimilation framework using partial, noisy ERA5 data. Our results show that filtering estimates remain accurate over a year-long assimilation window and provide effective initial conditions for forecasting tasks, including extreme event prediction.
title Data Assimilation with Machine Learning Surrogate Models: A Case Study with FourCastNet
topic Signal Processing
Machine Learning
Chaotic Dynamics
Atmospheric and Oceanic Physics
Applications
url https://arxiv.org/abs/2405.13180