Exploring the differences in atmospheric mesoscale kinetic energy spectra between AI based and physics based models

Abstract It is an urgent need to understand the ability of current artificial intelligence (AI) models in simulating atmospheric mesoscale aspects. This paper compares mesoscale kinetic energy spectra from an 11-day experiment simulated by a novel AI-based model (Pangu) and a physics-based model (MP...

Full description

Saved in:
Bibliographic Details
Main Authors: Zongheng Li, Jun Peng, Lifeng Zhang, Hanyan Wu, Wei Zhang, Juan Zhu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-99815-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850042658710355968
author Zongheng Li
Jun Peng
Lifeng Zhang
Hanyan Wu
Wei Zhang
Juan Zhu
author_facet Zongheng Li
Jun Peng
Lifeng Zhang
Hanyan Wu
Wei Zhang
Juan Zhu
author_sort Zongheng Li
collection DOAJ
description Abstract It is an urgent need to understand the ability of current artificial intelligence (AI) models in simulating atmospheric mesoscale aspects. This paper compares mesoscale kinetic energy spectra from an 11-day experiment simulated by a novel AI-based model (Pangu) and a physics-based model (MPAS), using ERA5 reanalysis as a reference. Based on the commonly used evaluation metrics of latitude weighted root mean square error (RMSE) and anomaly correlation coefficient (ACC), the AI-based model has better short to medium-range weather forecasting skill compared to the physics-based model. However, the AI-based model cannot replicate the mesoscale − 5/3 spectral slope and underestimates the mesoscale energy at wavelength smaller than 1000 km. As altitude increases and scale decreases, the deviation of the AI-based model from the reanalysis significantly increases. These features prove that the AI-based model has the lower effective resolution compared to the physics-based model with the close nominal resolution. Compared to the physics-based simulations, AI-based model has stronger downscale energy flux at larger mesoscales, which is dominated by divergent kinetic energy flux. But it rapidly becomes the weakest at smaller mesoscales. The diagnosed vertical velocity of AI-based model and its related budget terms are closest to those of the reanalysis at large scales. Overall, the AI-based model Pangu shows closer agreement with ERA5 at large scales, likely due to its use of the latter as training data, but significantly underestimates mesoscale kinetic energy compared to the physics-based model MPAS. Note that these findings are specific to the models and configurations used and should be interpreted with caution.
format Article
id doaj-art-2c218fc4b80249c381f892f3b04f80a7
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-2c218fc4b80249c381f892f3b04f80a72025-08-20T02:55:29ZengNature PortfolioScientific Reports2045-23222025-05-0115111110.1038/s41598-025-99815-xExploring the differences in atmospheric mesoscale kinetic energy spectra between AI based and physics based modelsZongheng Li0Jun Peng1Lifeng Zhang2Hanyan Wu3Wei Zhang4Juan Zhu5College of Meteorology and Oceanography, National University of Defense TechnologyCollege of Meteorology and Oceanography, National University of Defense TechnologyCollege of Meteorology and Oceanography, National University of Defense TechnologyCollege of Meteorology and Oceanography, National University of Defense TechnologyCollege of Meteorology and Oceanography, National University of Defense TechnologyZhangzhou Base Preparation Office, National Ocean Technology CenterAbstract It is an urgent need to understand the ability of current artificial intelligence (AI) models in simulating atmospheric mesoscale aspects. This paper compares mesoscale kinetic energy spectra from an 11-day experiment simulated by a novel AI-based model (Pangu) and a physics-based model (MPAS), using ERA5 reanalysis as a reference. Based on the commonly used evaluation metrics of latitude weighted root mean square error (RMSE) and anomaly correlation coefficient (ACC), the AI-based model has better short to medium-range weather forecasting skill compared to the physics-based model. However, the AI-based model cannot replicate the mesoscale − 5/3 spectral slope and underestimates the mesoscale energy at wavelength smaller than 1000 km. As altitude increases and scale decreases, the deviation of the AI-based model from the reanalysis significantly increases. These features prove that the AI-based model has the lower effective resolution compared to the physics-based model with the close nominal resolution. Compared to the physics-based simulations, AI-based model has stronger downscale energy flux at larger mesoscales, which is dominated by divergent kinetic energy flux. But it rapidly becomes the weakest at smaller mesoscales. The diagnosed vertical velocity of AI-based model and its related budget terms are closest to those of the reanalysis at large scales. Overall, the AI-based model Pangu shows closer agreement with ERA5 at large scales, likely due to its use of the latter as training data, but significantly underestimates mesoscale kinetic energy compared to the physics-based model MPAS. Note that these findings are specific to the models and configurations used and should be interpreted with caution.https://doi.org/10.1038/s41598-025-99815-x
spellingShingle Zongheng Li
Jun Peng
Lifeng Zhang
Hanyan Wu
Wei Zhang
Juan Zhu
Exploring the differences in atmospheric mesoscale kinetic energy spectra between AI based and physics based models
Scientific Reports
title Exploring the differences in atmospheric mesoscale kinetic energy spectra between AI based and physics based models
title_full Exploring the differences in atmospheric mesoscale kinetic energy spectra between AI based and physics based models
title_fullStr Exploring the differences in atmospheric mesoscale kinetic energy spectra between AI based and physics based models
title_full_unstemmed Exploring the differences in atmospheric mesoscale kinetic energy spectra between AI based and physics based models
title_short Exploring the differences in atmospheric mesoscale kinetic energy spectra between AI based and physics based models
title_sort exploring the differences in atmospheric mesoscale kinetic energy spectra between ai based and physics based models
url https://doi.org/10.1038/s41598-025-99815-x
work_keys_str_mv AT zonghengli exploringthedifferencesinatmosphericmesoscalekineticenergyspectrabetweenaibasedandphysicsbasedmodels
AT junpeng exploringthedifferencesinatmosphericmesoscalekineticenergyspectrabetweenaibasedandphysicsbasedmodels
AT lifengzhang exploringthedifferencesinatmosphericmesoscalekineticenergyspectrabetweenaibasedandphysicsbasedmodels
AT hanyanwu exploringthedifferencesinatmosphericmesoscalekineticenergyspectrabetweenaibasedandphysicsbasedmodels
AT weizhang exploringthedifferencesinatmosphericmesoscalekineticenergyspectrabetweenaibasedandphysicsbasedmodels
AT juanzhu exploringthedifferencesinatmosphericmesoscalekineticenergyspectrabetweenaibasedandphysicsbasedmodels