Continuous Ensemble Weather Forecasting with Diffusion models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Andrae, Martin, Landelius, Tomas, Oskarsson, Joel, Lindsten, Fredrik
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915239232012288
author Andrae, Martin
Landelius, Tomas
Oskarsson, Joel
Lindsten, Fredrik
author_facet Andrae, Martin
Landelius, Tomas
Oskarsson, Joel
Lindsten, Fredrik
contents Weather forecasting has seen a shift in methods from numerical simulations to data-driven systems. While initial research in the area focused on deterministic forecasting, recent works have used diffusion models to produce skillful ensemble forecasts. These models are trained on a single forecasting step and rolled out autoregressively. However, they are computationally expensive and accumulate errors for high temporal resolution due to the many rollout steps. We address these limitations with Continuous Ensemble Forecasting, a novel and flexible method for sampling ensemble forecasts in diffusion models. The method can generate temporally consistent ensemble trajectories completely in parallel, with no autoregressive steps. Continuous Ensemble Forecasting can also be combined with autoregressive rollouts to yield forecasts at an arbitrary fine temporal resolution without sacrificing accuracy. We demonstrate that the method achieves competitive results for global weather forecasting with good probabilistic properties.
format Preprint
id arxiv_https___arxiv_org_abs_2410_05431
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Continuous Ensemble Weather Forecasting with Diffusion models
Andrae, Martin
Landelius, Tomas
Oskarsson, Joel
Lindsten, Fredrik
Machine Learning
Atmospheric and Oceanic Physics
Weather forecasting has seen a shift in methods from numerical simulations to data-driven systems. While initial research in the area focused on deterministic forecasting, recent works have used diffusion models to produce skillful ensemble forecasts. These models are trained on a single forecasting step and rolled out autoregressively. However, they are computationally expensive and accumulate errors for high temporal resolution due to the many rollout steps. We address these limitations with Continuous Ensemble Forecasting, a novel and flexible method for sampling ensemble forecasts in diffusion models. The method can generate temporally consistent ensemble trajectories completely in parallel, with no autoregressive steps. Continuous Ensemble Forecasting can also be combined with autoregressive rollouts to yield forecasts at an arbitrary fine temporal resolution without sacrificing accuracy. We demonstrate that the method achieves competitive results for global weather forecasting with good probabilistic properties.
title Continuous Ensemble Weather Forecasting with Diffusion models
topic Machine Learning
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2410.05431